Multi Branch Research Articles

Application analysis of heuristic algorithms integrating dynamic programming in RNA secondary structure prediction

Ribonucleic acid is a crucial biomolecule in living organisms, with various types. To promote the research process of ribonucleic acid function, this study is for analyzing the utilization of heuristic algorithms on the ground of fusion dynamic programming in predicting the secondary structure of ribonucleic acid. Research on novel use of tree models for RNA secondary structure comparison, and use heuristic algorithms to optimize the multi branch structure comparison of tree models. Firstly, this study utilized dynamic programming algorithms to construct a comparison matrix and successfully found the backtracking path in the matrix. Meanwhile, for ensuring that the structural information of ribonucleic acid is not lost during the comparative analysis process, the study applies the idea of heuristic algorithms to calculate the optimal comparison between multi branched loops. Finally, the weights are adjusted using neural network algorithms to predict the optimal alignment structure. The results showed that the fusion dynamic programming heuristic algorithm achieved generalization performance of 0.928, 0.856, 0.842, and 0.793 on the target base data test sets of humans, mice, yeast, and spotted fish, respectively. Compared with the SimTree algorithm, the generalization performance has been improved by 15.13 %, 27.38 %, 27.77 %, and 38.88 %, respectively. In summary, the application of heuristic algorithms integrating dynamic programming in predicting the secondary structure of ribonucleic acid has good predictive performance. This has reference value for a deeper understanding of the structure and function relationship of ribonucleic acid.

Enhanced multi-label cardiology diagnosis with channel-wise recurrent fusion

The timely detection of abnormal electrocardiogram (ECG) signals is vital for preventing heart disease. However, traditional automated cardiology diagnostic methods have the limitation of being unable to simultaneously identify multiple diseases in a segment of ECG signals, and do not consider the potential correlations between the 12-lead ECG signals. To address these issues, this paper presents a novel network architecture, denoted as Branched Convolution and Channel Fusion Network (BCCF-Net), designed for the multi-label diagnosis of ECG cardiology to achieve simultaneous identification of multiple diseases. Among them, the BCCF-Net incorporates the Channel-wise Recurrent Fusion (CRF) network, which is designed to enhance the ability to explore potential correlation information between 12 leads. Furthermore, the utilization of the squeeze and excitation (SE) attention mechanism maximizes the potential of the convolutional neural network (CNN). In order to efficiently capture complex patterns in space and time across various scales, the multi branch convolution (MBC) module has been developed. Through extensive experiments on two public datasets with seven subtasks, the efficacy and robustness of the proposed ECG multi-label classification framework have been comprehensively evaluated. The results demonstrate the superior performance of the BCCF-Net compared to other state-of-the-art algorithms. The developed framework holds practical application in clinical settings, allowing for the refined diagnosis of cardiac arrhythmias through ECG signal analysis.

Study on Flow Line Characteristics and Well Test Interpretation Methods of Multi Branch Fractured Wells in Dual Porous Media

Fractured reservoirs have developed fractures, strong heterogeneity, and complex seepage patterns. The analysis of core and imaging logging data in Bohai BZ Oilfield shows that there are a large number of fractures developed in the formation, with some wells having up to 6-8 fractures per meter. To study the impact of fractures on seepage, a multi fracture system seepage field simulation method was established, and the characteristic curves of flow lines under different fracture shapes were drawn. The fracture flow line morphology shows that there is a significant difference in the distribution of flow lines between the presence and absence of fractures, and the location of the fractures The size and shape of the reservoir have varying degrees of influence on the distribution of the streamline. The streamline around the well is distributed radially around it. When the fluid encounters an area with developed fractures, it first flows into the fractures and then flows from the fractures towards the wellbore. At the same time, based on the characteristics of fracture development in BZ oilfield and the theory of vertical fracture well testing, a dual medium multi fracture system oil well testing model was established. The model was numerically solved using Laplace transform, and a dual logarithmic curve chart for dual pore medium multi branch fracture well testing was obtained. The effects of fracture branching number, fracture length, conductivity coefficient ratio, and fracture conductivity on the shape of the testing curve were analyzed. The established well testing interpretation model can analyze oilfield stratigraphic information, reservoir fracture development, and boundary conditions. The research results have important guiding significance for evaluating the dynamic performance of oil wells in a dual pore medium multi fracture system and designing oilfield development plans.

Multi-Stage Network with Geometric Semantic Attention for Two-View Correspondence Learning.

The removal of outliers is crucial for establishing correspondence between two images. However, when the proportion of outliers reaches nearly 90%, the task becomes highly challenging. Existing methods face limitations in effectively utilizing geometric transformation consistency (GTC) information and incorporating geometric semantic neighboring information. To address these challenges, we propose a Multi-Stage Geometric Semantic Attention (MSGSA) network. The MSGSA network consists of three key modules: the multi-branch (MB) module, the GTC module, and the geometric semantic attention (GSA) module. The MB module, structured with a multi-branch design, facilitates diverse and robust spatial transformations. The GTC module captures transformation consistency information from the preceding stage. The GSA module categorizes input based on the prior stage's output, enabling efficient extraction of geometric semantic information through a graph-based representation and inter-category information interaction using Transformer. Extensive experiments on the YFCC100M and SUN3D datasets demonstrate that MSGSA outperforms current state-of-the-art methods in outlier removal and camera pose estimation, particularly in scenarios with a high prevalence of outliers. Source code is available at https://github.com/shuyuanlin.

Data Processing from Bank Cheques by Utilising Split Attribute Character Analysis and Multi Branch Network Forest Classifier Techniques

Bank cheques are primarily used for conducting financial transactions, resulting in their substantial daily processing volumes worldwide. The automation of the whole process of recognising and verifying cheques has the potential to significantly reduce both the time and expenditures associated with cheque execution. The field of automatic bank cheque processing system is now gaining prominence in the realm of computer vision, image processing, pattern recognition, machine learning, and deep learning. The study places particular emphasis on the sequential processes involved in the automated bank Cheque processing system, including picture capture, pre-processing, and extraction and identification. This article provides an overview of the sequential processes included in the automated data extraction system. This research aims to propose strategies for the automated processing of bank cheque images via the use of Split Attribute character analysis and Multi branch network forest classifier. The study indicates that the recommended technique demonstrates satisfactory performance by achieving high levels of accuracy, precision, recall, and F score.

CFMB-T: A cross-frequency multi-branch transformer for low-quality infrared remote sensing image super-resolution

Aiming at the problems of low resolution and fuzzy details of infrared remote sensing images, paper proposed a multi branch super-resolution method based on wavelet decomposition and a dataset processing method based on real degradation process. To improve the super-resolution reconstruction effect, the modulation transfer function is used to add the degradation process of the real environment to the dataset at first, and based on this, CFMB-T is proposed. CFMB-T took SwinIR as the architecture, separated the frequency information of the infrared remote sensing image through wavelet decomposition, and introduced a degenerate prior to focus on the recovery of high-frequency information. Moreover, CFMB-T also introduced a recursive module to ensure the ability of feature extraction while reducing model parameters. The detailed experiments on degraded datasets show that CFMB-T achieves better reconstruction results than other super-resolution models. Compared with SwinIR, with limited data and training rounds, the PSNR and SSIM of CFMB-T are improved by 1.07% and 0.71%, respectively, over SwinIR on the 4x super-resolution task, and 3.28% and 0.09%, respectively, on the 2x super-resolution task. The results demonstrate its great potential for infrared remote sensing super-resolution reconstruction.

An adaptive weighted attention-enhanced deep convolutional neural network for classification of MRI images of Parkinson's disease

BackgroundParkinson's disease (PD) is the second prevalent neurological diseases with a significant growth rate in incidence. Convolutional neural networks using structural magnetic resonance images (sMRI) are widely used for PD classification. However, the areas of change in the patient's MRI images are small and unfixed. Thus, capturing the features of the areas accurately where the lesions changed became a problem. MethodWe propose a deep learning framework that combines multi-scale attention guidance and multi-branch feature processing modules to diagnose PD by learning sMRI T2 slice features. In this scheme, firstly, to achieve effective feature transfer and gradient descent, a deep convolutional neural network framework based on dense block is designed. Next, an Adaptive Weighted Attention algorithm is proposed, whose pursers is to extract multi branch and even diverse features. Finally, Dropout layer and SoftMax layer are added to the network structure to obtain good classification results and rich and diverse feature information. The Dropout layer is used to reduce the number of intermediate features to increase the orthogonality between features of each layer. The activation function SoftMax increases the flexibility of the neural network by increasing the degree of fitting to the training set and converting linear to nonlinear. ResultsThe best performance of the proposed method an accuracy of 92%, a sensitivity of 94%, specificity of 90% and a F1 score of 95% respectively for identifying PD and HC. ConclusionExperiments show that the proposed method can successfully distinguish PD and NC. Good classification results were obtained in PD diagnosis classification task and compared with advanced research methods.

Android static taint analysis based on multi branch search association

Taint analysis is a method used to detect system security problems by tracking the flow of user input or information leakage through the system. In the taint analysis for Android applications, the complete taint propagation path is generally obtained by tracking the taint data. There is often a compromise between efficiency and analysis accuracy in the method of obtaining the taint propagation path, or false positives and false negatives due to the neglect of Android features. Given the problems, a novel multi-branch taint search association algorithm is proposed, which optimized the processing of Android component features in taint analysis. It directly finds taint related codes and associates them according to predefined rules. It has effective Android taint analysis ability including alias analysis and reduced the negative impact of taint unrelated codes on the performance of taint analysis. At the same time, the Android static taint analysis prototype tool TaintSA is implemented based on the multi-branch taint search association algorithm. The experimental results show that TaintSA can not only ensure the analysis results' accuracy but also reduce the time and space required for taint analysis. The accuracy rate of 91.5% and the recall rate of 75.6% on the DroidBench2.0 test set are better than the taint analysis tool FlowDroid. The time consumption and memory consumption of about 30% and 20% are reduced at the same time. In terms of the representation of taint propagation edges, compared with FlowDroid, the taint propagation path output by TaintSA does not contain intermediate variables, and the form is more concise. In addition, TaintSA can output the taint propagation path without taint leakage, which is helpful for further taint analysis.

Detection of inferior myocardial infarction based on multi branch hybrid network

Background and ObjectivesEarly and accurate detection of inferior myocardial infarction (IMI) is important for reducing the risk of mortality from a heart attack. Although previous work has demonstrated IMI detection, the differences among patients have been ignored. Most models display excellent performance in the intra-patient scheme, but the inter-patient test results are not ideal. The present paper proposes a model based on densely connected convolutional and gated recursive unit (GRU) networks to enhance the generalization ability of the model. MethodsFirstly, the data of multi-lead beat in series is used with GRU, to obtain more inter-lead and intra-lead time correlation information. This correlation information is scientific and significant for IMI detection. Secondly, the proposed model retains both deep and shallow features of ECG through DenseNet, which include more detailed information of IMI. Finally, through the feature connection, the multi-dimensional features enrich the description of ECG signals, and help the network learn more essential characteristics of IMI, so as to enhance the generalization ability of the model. ResultsThe proposed method was verified by the PTB diagnostic database of the German National Metrology Institute. The generalization ability of the model was tested by intra-patient and inter-patient schemes. After 5-fold cross-validation, the average accuracy, sensitivity and specificity were 99.95%, 99.94% and 99.96% in the intra-patient scheme respectively. Furthermore, these parameters were 88.68%, 90.33% and 87.04% in the inter-patient scheme. ConclusionsThe experimental results show that the model displays good generalization ability, which has important clinical significance.

RepHAR: Decoupling Networks With Accuracy-Speed Tradeoff for Sensor-Based Human Activity Recognition

Sensor-based human activity recognition (HAR) can provide users with more convenience and security than machine vision-based methods. The ideal HAR application would achieve high-accuracy and low-latency performance with minimal hardware consumption. However, so far, the speed-accuracy tradeoff in mobile device-based HAR has rarely been systematically analyzed and discussed. In contrast to the static networks of existing deep HAR models, this article aims to design a resource-efficient dynamic network, called RepHAR, for low-cost hardware-constrained HAR tasks. This article first combines multibranch (MB) topologies and structured reparameterization techniques for HAR. Specifically, RepHAR decouples the model into a training time and inference time architecture using the idea of structural reparameterization. That is to say, the model has a MB topology at training time, but it no longer has the same model structure at inference time and is transformed into a plain convolutional neural network (CNN) structure. As a result, RepHAR achieves a trade-off between speed and accuracy by simultaneously obtaining the accuracy gain of a MB network and the high-speed inference of a plain CNN. On four publicly available datasets (including UCI-HAR, PAMAP2, UNIMIB-SHAR, and OPPORTUNITY), RepHAR can achieve 0.83%–2.18% accuracy improvement and 12%–44% parameter reduction, which demonstrates the effectiveness of the proposed method. Finally, on the embedded Raspberry Pi, the RepHAR runs 72% faster than the MB CNN model, demonstrating its usefulness and practicality. Our model and codes will be released soon.

A Model Combining Multi Branch Spectral-Temporal CNN, Efficient Channel Attention, and LightGBM For MI-BCI Classification.

Accurately decoding motor imagery (MI) brain-computer interface (BCI) tasks has remained a challenge for both neuroscience research and clinical diagnosis. Unfortunately, less subject information and low signal-to-noise ratio of MI electroencephalography (EEG) signals make it difficult to decode the movement intentions of users. In this study, we proposed an end-to-end deep learning model, a multi-branch spectral-temporal convolutional neural network with channel attention and LightGBM model (MBSTCNN-ECA-LightGBM), to decode MI-EEG tasks. We first constructed a multi branch CNN module to learn spectral-temporal domain features. Subsequently, we added an efficient channel attention mechanism module to obtain more discriminative features. Finally, LightGBM was applied to decode the MI multi-classification tasks. The within-subject cross-session training strategy was used to validate classification results. The experimental results showed that the model achieved an average accuracy of 86% on the two-class MI-BCI data and an average accuracy of 74% on the four-class MI-BCI data, which outperformed current state-of-the-art methods. The proposed MBSTCNN-ECA-LightGBM can efficiently decode the spectral and temporal domain information of EEG, improving the performance of MI-based BCIs.

Dynamic Multi-Graph Convolution based Channel-Weighted Transformer Feature Fusion Network for Epileptic Seizure Prediction.

Electroencephalogram (EEG) based seizure prediction plays an important role in the closed-loop neuromodulation system. However, most existing seizure prediction methods based on graph convolution network only focused on constructing the static graph, ignoring multi-domain dynamic changes in deep graph structure. Moreover, the existing feature fusion strategies generally concatenated coarse-grained epileptic EEG features directly, leading to the suboptimal seizure prediction performance. To address these issues, we propose a novel multi-branch dynamic multi-graph convolution based channel-weighted transformer feature fusion network (MB-dMGC-CWTFFNet) for the patient-specific seizure prediction with the superior performance. Specifically, a multi-branch (MB) feature extractor is first applied to capture the temporal, spatial and spectral representations fromthe epileptic EEG jointly. Then, we design a point-wise dynamic multi-graph convolution network (dMGCN) to dynamically learn deep graph structures, which can effectively extract high-level features from the multi-domain graph. Finally, by integrating the local and global channel-weighted strategies with the multi-head self-attention mechanism, a channel-weighted transformer feature fusion network (CWTFFNet) is adopted to efficiently fuse the multi-domain graph features. The proposed MB-dMGC-CWTFFNet is evaluated on the public CHB-MIT EEG and a private intracranial sEEG datasets, and the experimental results demonstrate that our proposed method achieves outstanding prediction performance compared with the state-of-the-art methods, indicating an effective tool for patient-specific seizure warning. Our code will be available at: https://github.com/Rockingsnow/MB-dMGC-CWTFFNet.

Integration of maXs-type microcalorimeter detectors for high-resolution x-ray spectroscopy into the experimental environment at the CRYRING@ESR electron cooler

We report on the first integration of novel magnetic microcalorimeter detectors (MMCs), developed within SPARC (Stored Particles Atomic Physics Research Collaboration), into the experimental environment of storage rings at GSI 6 6 GSI Helmholtzzentrum für Schwerionenforschung GmbH, Planckstraße 1, 64 291 Darmstadt., Darmstadt, namely at the electron cooler of CRYRING@ESR. Two of these detector systems were positioned at the 0° and 180° view ports of the cooler section to obtain high-resolution x-ray spectra originating from a stored beam of hydrogen-like uranium interacting with the cooler electrons. While previous test measurements with microcalorimeters at the accelerator facility of GSI were conducted in the mode of well-established stand-alone operation, for the present experiment we implemented several notable modifications to exploit the full potential of this type of detector for precision x-ray spectroscopy of stored heavy ions. Among these are a new readout system compatible with the multi branch system data acquisition platform of GSI, the synchronization of a quasi-continuous energy calibration with the operation cycle of the accelerator facility, as well as the first exploitation of the maXs detectors’ time resolution to apply coincidence conditions for the detection of photons and charge-changed ions.

A multi‐view image fusion algorithm for industrial weld

Multi-view image fusion can be used to extract features from redundant and complementary multisource images. And the technique of obtaining high quality fusion images has become one of the research hotspots for image processing. In order to realize defect detection and intelligent grinding smoothly, multi-view fusion technology was applied in the field of overexposure and underexposure industrial welds, achieving high quality image enhancement. When preparing the data set of multi-view images, a hybrid registration algorithm with high matching ability is proposed. The data set of overexposure and underexposure weld images was obtained successfully by using the registration algorithm. In order to improve the fusion ability of overexposure and underexposure industrial welds, we propose a novel multi-view image fusion algorithm based on deep learning. The multi-view fusion algorithm uses an autoencoder network structure, and its innovation lies in a parallel branch network with lightweight structure and strong generalization ability. The experimental results demonstrate that compared with other classical multi-view algorithms, our proposed algorithm gets the best parameters on the industrial weld data set in peak signal to noise ratio (PSNR) and root mean square error (RMSE), reaching 59.12 and 0.084, respectively. And the ablation and performance comparison experiments verify that the proposed parallel branch network has better generalization ability and fusion accuracy than other classical multi branch networks.

Autonomous obstacle avoidance of UAV based on deep reinforcement learning1

In the intelligent unmanned systems, unmanned aerial vehicle (UAV) obstacle avoidance technology is the core and primary condition. Traditional algorithms are not suitable for obstacle avoidance in complex and changeable environments based on the limited sensors on UAVs. In this article, we use an end-to-end deep reinforcement learning (DRL) algorithm to achieve the UAV autonomously avoid obstacles. For the problem of slow convergence in DRL, a Multi-Branch (MB) network structure is proposed to ensure that the algorithm can get good performance in the early stage; for non-optimal decision-making problems caused by overestimation, the Revise Q-value (RQ) algorithm is proposed to ensure that the agent can choose the optimal strategy for obstacle avoidance. According to the flying characteristics of the rotor UAV, we build a V-Rep 3D physical simulation environment to test the obstacle avoidance performance. And experiments show that the improved algorithm can accelerate the convergence speed of agent and the average return of the round is increased by 25%.

Adaptive Selection Algorithm of Paragraph Selection Structure Based on Complex Data Type

In the automatic generation of standard documents, the replacement method of template is cumbersome and difficult to modify and maintain in the later stage when dealing with the selection structure in the paragraph template. To solve this problem, an adaptive paragraph selection structure selection algorithm based on complex data types is proposed. On the basis of the tree structure, each node is abstracted into a class, selection nodes are set, and attributes and methods are set for the selection nodes. The deletion and retention of nodes in the paragraph template are completed through the attributes and methods of the selection nodes. The experiment shows that it has a good effect in paragraphs with multi branch sentences.

Key Performance Indicator for Multi Branch Employee Performance Assessment Based on Simple Additive Weighting

The success of the company in managing human resources is very crucial, especially companies that have different locations. Different locations are termed multi-branch, which is management of human resource performance based on clear and anti-subjective assessment parameters and carried out regularly. The performance parameters of employees in a company can be influenced by various factors including motivation, competence, and perceived organizational support. Futhermore, the company parameters will concern about the cost and benefits. Managing a business with one building location will be different from managing a business in many locations, especially with the number of subsidiaries reaching 13 locations. The complexity of corporate governance will be higher, therefore a mechanism is needed to simplify this complexity from point of view of the Simple Additive Weighting Method where the determinant of the variable is initiated as Ci-Cn to obtain a normalized matrix of R for Benefit (B) and Cost (C) values. This research, the Benefit values are C1,C3,C4 while the Cost values are C2,C5,C6. The normalization for Benefit is initiated as Rij = (Xij/XijMax) and Rij = (XijMin/Xij)for the initiation of the Cost of calculating normalization R. The results obtained are then processed into a normal matrix with the initiation W = [(C1),(C2),(C3),(C4),(C5),(C6)].

A CNN-based regression framework for estimating coal ash content on microscopic images

Coal ash content is an important criterion for evaluating coal quality. In recent years, the online ash measurement approach based on a convolutional neural network (CNN) has gotten a lot of attention. However, learning continuous targets from a small and unbalanced dataset is one of the biggest challenges for ash content estimation using CNN. In this paper, a CNN-based regression framework was proposed for rapidly estimating the ash content of coal. Firstly, data synthesis was performed to augment the limited dataset, and label distribution smoothing (LDS) was employed to alleviate the imbalance in datasets. Secondly, separable convolution (SC) and attention modules were introduced into multi-branch (MB) blocks of the backbone. SC was applied to fuse both spatial and channel-wise information, and attention modules were used to enhance feature extraction capability. Finally, as a final estimation value, the regression head outputted a float in the range [0, 100]. The results showed that the proposed approach achieved 0.31% error on the 1,145 test images, where 81.76% had a margin of error less than 0.5% and 96.25% less than 1.0%. Furthermore, the prediction error analysis revealed that the accuracy of the predictions was highly related to the homogeneity of the materials. The visualization results demonstrated that the proposed regression framework could merge multi-scale information and that the synthetic dataset was viable.

Diffuse large B-cell lymphoma segmentation in PET-CT images via hybrid learning for feature fusion.

Diffuse large B-cell lymphoma (DLBCL) is an aggressive type of lymphoma with high mortality and poor prognosis that especially has a high incidence in Asia. Accurate segmentation of DLBCL lesions is crucial for clinical radiation therapy. However, manual delineation of DLBCL lesions is tedious and time-consuming. Automatic segmentation provides an alternative solution but is difficult for diffuse lesions without the sufficient utilization of multimodality information. Our work is the first study focusing on positron emission tomography and computed tomography (PET-CT) feature fusion for the DLBCL segmentation issue. We aim to improve the fusion performance of complementary information contained in PET-CT imaging with a hybrid learning module in the supervised convolutional neural network. First, two encoder branches extract single-modality features, respectively. Next, the hybrid learning component utilizes them to generate spatial fusion maps which can quantify the contribution of complementary information. Such feature fusion maps are then concatenated with specific-modality (i.e., PET and CT) feature maps to obtain a representation of the final fused feature maps in different scales. Finally, the reconstruction part of our network creates a prediction map of DLBCL lesions by integrating and up-sampling the final fused feature maps from encoder blocks in different scales. The ability of our method was evaluated to detect foreground and segment lesions in three independent body regions (nasopharynx, chest, and abdomen) of a set of 45 PET-CT scans. Extensive ablation experiments compared our method to four baseline techniques for multimodality fusion (input-level (IL) fusion, multichannel (MC) strategy, multibranch (MB) strategy, and quantitative weighting (QW) fusion). The results showed that our method achieved a high detection accuracy (99.63% in the nasopharynx, 99.51% in the chest, and 99.21% in the abdomen) and had the superiority in segmentation performance with the mean dice similarity coefficient (DSC) of 73.03% and the modified Hausdorff distance (MHD) of 4.39mm, when compared with the baselines (DSC: IL: 53.08%, MC: 63.59%, MB: 69.98%, and QW: 72.19%; MHD: IL: 12.16mm, MC: 6.46mm, MB: 4.83mm, and QW: 4.89mm). A promising segmentation method has been proposed for the challenging DLBCL lesions in PET-CT images, which improves the understanding of complementary information by feature fusion and may guide clinical radiotherapy. The statistically significant analysis based on P-value calculation has indicated a degree of significant difference between our proposed method and other baselines (almost metrics: P<0.05). This is a preliminary research using a small sample size, and we will collect data continually to achieve the larger verification study.

Tomlinson-Harashima Precoded Rate-Splitting With Stream Combiners for MU-MIMO Systems

This article introduces multiuser multiple-input multiple-output (MU-MIMO) architectures based on non-linear precoding and stream combining techniques using rate-splitting (RS), where the transmitter often has only partial knowledge of the channel state information (CSI). In contrast to existing works, we consider deployments where the receivers may be equipped with multiple antennas. This allows us to employ linear combining techniques based on the Min-Max, the maximum ratio and the minimum mean-square error criteria along with Tomlinson-Harashima precoders (THP) for RS-based MU-MIMO systems to enhance the sum-rate performance. Moreover, we incorporate the Multi-Branch (MB) concept into the RS architecture to further improve the sum-rate performance. Closed-form expressions for the signal-to-interference-plus-noise ratio and the sum-rate at the receiver end are devised through statistical analysis. Simulation results show that the proposed RS-THP schemes achieve better performance than conventional linear and THP precoders.