Fusion Node Research Articles

Sub‐optimal Internet of Thing devices deployment using branch and bound method

AbstractThe Internet of Thing (IoT) network deployments are widely investigated in 4G and 5G systems and will still be key technical systems to drive massive connectivity of 6G systems. In 6G, IoT systems will operate with 6G new technologies such as Integrated Sensing and Communications. The IoT systems of 6G will be a platform to collect information in real world and create new use cases and business models. As the IoT devices and cellular networks are getting smarter, the IoT ecosystem allows us to bridge between human life and digital life and accelerate the transition towards a hyper‐connected world. Optimal and scalable IoT network design has been investigated in many research groups but key challenges in this topic still remain. An IoT devices deployment problem is investigated to minimise the transmission and computation cost among network nodes. The IoT devices deployment problem is formulated as Mixed‐Integer Nonlinear Programming problem. After relaxing the constraints and transforming the problem to a mixed integer linear programming (MILP) problem, the authors propose a new branch and bound (BB) method with a machine learning function and solve the MILP problem as a sub‐optimal solution. In the numerical analysis, the authors evaluate both conventional BB method and the proposed BB method with weighting factors and compare the objective function values, the number of explored nodes, and computational time. The performances of the proposed BB method are significantly improved under the given simulation configuration. The author finds the optimal mapping of IoT devices to fusion nodes.

Distributed matrix-weighted fusion model predictive control algorithm

This paper is concerned with model predictive control (MPC) for multisensor linear systems. In order to fully utilize information and achieve higher control accuracy, two fusion MPC algorithms are proposed. The first algorithm is named estimation-fusion model predictive controller (E-F MPC), which local estimations are fused and then fusion control input is obtained by the fusion estimation. The second algorithm is named control-fusion model predictive controller (C-F MPC), which fuses the control inputs obtained from local systems. The relationships, differences and complexity of the two algorithms are analyzed. The advantages of E-F MPC are that it is simple and easy to implement with high control accuracy, while the disadvantage is the bad robustness because of the heavy estimation, prediction and control tasks for the fusion node. For C-F MPC, with a small loss of accuracy, network throughput and computational cost of its fusion node will be greatly reduced, which makes it good robustness and flexibility. Simulation analysis verifies the effectiveness and correctness of the conclusion.

A novel robust multivariate Laplace distribution-based distributed consensus information fusion

The multivariate Laplace distribution (MLD) possesses a lesser set of prior parameters compared to the Student’s t-distribution, thus simplifying the modeling of measurement data subject to heavy-tailed noise corruption. This short communication introduces a novel distributed hybrid consensus fusion algorithm utilizing the MLD modeling and variational Bayesian approach. Firstly, we formulate the measurement noise associated with individual sensor nodes and introduce the hierarchical Gaussian form of MLD to enhance the feasibility of variational inference. Secondly, we opt for the inverse-Wishart (IW) distribution to serve as the conjugate prior to the positive definite matrix, enabling adaptive parameter learning within the MLD context. As a result, a novel hierarchical Gaussian state–space model (SSM) is established for multi-sensors network. Subsequently, we derive a novel local information filter to acquire higher precision information and innovation vector–matrix pairs, outperforming the Student’s t distribution-based filter. These derivations are grounded in the new hierarchical SSM, and the vector–matrix pairs aid in information fusion across the network. Lastly, we present a distributed robust consensus filter for fusing local information using a hybrid consensus approach that devoid of a central fusion node. Simulation results demonstrate that the proposed consensus filter can obtain better estimation accuracy under the interference of heavy-tailed measurement outliers.

A novel framework for motor bearing fault diagnosis based on multi-transformation domain and multi-source data

Through the application of deep learning and multi-sensor data, fault features can be automatically extracted and valuable information can be integrated to tackle intricate challenges in motor bearing fault diagnosis. Most existing fusion models focus primarily on the original time series signal with information extraction largely restricted to the time domain (without extensions into multiple transformation domains). Also, in most fusion models, the sensor fusion level is kept relatively simple which could lead to the oversight of correlations and complementarities among the information. To enhance the recognition capability of diagnostic network features, in this paper, we propose a novel framework for motor bearing fault diagnosis from the perspectives of multi-transformation domain and multi-source data fusion. Within this framework, feature extraction and fusion from various source data are achieved in the time domain, frequency domain, and time–frequency domain. Distinct independent networks are set up within these domains: one network is designated for overseeing feature fusion, while the others are dedicated to extracting features from individual sensors. To support the extraction of pivotal features across multiple fusion layers in various transformation domains, several fusion nodes are inserted between the layers of the multiple feature extraction networks and the feature summarization network. Furthermore, a channel attention mechanism is introduced as a fusion strategy that serves to pinpoint the significance of different features, thus enhancing the efficiency of feature extraction. Experimental evaluation reveals the efficacy of the proposed model and highlights its noteworthy performance attributes such as scalability and universality.

不平衡图多尺度融合节点分类方法

不平衡图多尺度融合节点分类方法

Distributed minimum error entropy Kalman filter

Recently, the distributed Kalman filter (DKF) has been considered a major method for the applications of Wireless sensor networks (WSNs), for instance, the Internet of Things, and Swarm Intelligence, in which non-Gaussian noise influence is an urgent issue. In this paper, taking any sensor of WSNs as a fusion node, a dynamic Gain Matrix is constructed for its neighbors’ information fusion. Then, the Minimum Error Entropy (MEE) is furtherly introduced into the information fusion process, a modified DKF algorithm called the Distributed Fusion MEE Kalman Filter (DF-MEE-KF) is proposed for eliminating the non-Gaussian noise influence, which improved the estimation accuracy well. Moreover, considering many bad communication conditions of WSNs, such as Communication Denial Environments, and Underwater Acoustic Communication Environments, it is required that the higher estimation accuracy the better, and the lower communication cost the better. Therefore, the diffusion rule is applied for the nodes’ information fusion by constructed fusion weights, thereby an extended DF-MEE-KF algorithm, the Diffusion MEE Kalman filter (Diff-MEE-KF), is obtained. Finally, the convergence of the proposed DF-MEE-KF and Diff-MEE-KF algorithms is proved. Numerical simulation examples also demonstrate that the DF-MEE-KF algorithm performs good estimation accuracy, and the Diff-MEE-KF algorithm achieves a lower communication cost under the same estimation accuracy, when in non-Gaussian noise-influenced WSNs’ applications.

GPS Spoofing Detection and Mitigation for Drones Using Distributed Radar Tracking and Fusion

In today’s world, Global positioning system (GPS)-based navigation is inexpensive for providing position, velocity, and time (PVT) information. GPS receivers are widely used on unmanned aerial vehicles (UAVs), and these targets are vulnerable to deliberate interference such as spoofing. In this paper, GPS spoofing detection and mitigation for UAVs are proposed using distributed radar ground stations equipped with a local tracker. In the proposed approach, UAVs and local trackers are linked to the fusion node. The UAVs estimate their position and covariance using the extended Kalman filter framework and send it to a fusion node as primary data. Simultaneously, the time-varying kinematics of the UAVs are estimated using the extended Kalman filter and global nearest neighbor association tracker frameworks, and this data is transmitted to the central fusion node as secondary data. A track-to-track association is proposed to detect spoofing attacks using available primary and secondary data. After detecting the spoofing attack, the secondary data is subjected to a correlation-free fusion. We propose using this fused state as a control input to the UAVs to mitigate the spoofing attack. The spoofing scenario results show that using the predicted fusion state provides the same accuracy as a GPS receiver in a clean environment. Furthermore, because the innovation is calculated using the predicted fused state, there is no effect on the number of satellite signals on PRMSE. Additionally, in terms of PRMSE, radars with low measurement noise outperform radars with high measurement noise. The proposed algorithm is best suited for use in drone swarm applications.

Cooperative Fusion Architecture-based Distributed Spectrum Sensing Under Rayleigh Fading Channel

Cognitive radio is one of the most promising technologies due to the spectrum scarcity, especially in the microwave band. Spectrum sensing forms an essential functionality for CR systems. However, such detection performance is usually compromised by shadowing and fading channel conditions. Cooperative sensing is one of the crucial solutions to overcome degraded detection performance. A distributed architecture for the processing and fusion of sensing information is proposed to improve sensing performance and reduce reporting error. The decision fusion for cooperated users could be complex in dense network scenarios and reported sensing traffic may require significant bandwidth. The paper presents a new cooperative distributed PUs detection and proposes dynamic threshold based on controlled probability of false alarm to enhance sensing efficiency and reliability in a Rayleigh fading environments. A cooperative distributed PUs detection is realized by fusion node (FNs) that dynamically selected from the group members. The adaptive detection threshold is computed dynamically using the link quality indicators (LQIs) of the sensing channels. Moreover, the proposed scheme can significantly minimize the typically transmitted bits in the reporting channels. This work also deliberated the design parameters of the CR on the performance of fusion values. The simulation evaluation presents that the adapted threshold considerably improves the performance of the distributed cooperative sensing (DCS) process. The simulation results verified that the error was minimized remarkably. The ROC graph is notably enhanced for the sensing process in term of probability of detection and probability of false alarm. Finally, it was presented that with the proposed scheme the sensitivity requirements could be significantly enhanced up to 0.95.

Sequential Fusion Based Approach for Estimating Range Gate Pull-Off Parameter in a Networked Radar System: An ECCM Algorithm

Networked radar is an emerging and effective alternative to traditional radar systems to provide improved performance by fusing information from multiple radars. Further, networked radar systems (NRS) have found numerous deployments in military and civilian infrastructures in recent years. Electronic countermeasures (ECM) like jamming, Range Gate Pull-Off (RGPO), and Velocity Gate Pull-Off (VGPO) generally pose a high risk to the radar systems by injecting intentional interference. This paper proposes networked radar to detect the RGPO ECM attack and estimate the range gate deception parameter of the deceived local track in an NRS. Each radar comprises a local tracker to provide the local estimates (updated state and updated covariance), and these estimates are then sent to the fusion node. Thereafter, a track-to-track association (T2TA) is formulated at the fusion node to detect the deceived tracks using all the available local tracks. For the deceived track, the pseudo-measurements are created using the inverse Kalman filter-based tracklets. All the local tracks except deceived track are compensated and sequentially fused to create a reference measurement. After that, the deception parameter of the deceived track is estimated by using pseudo-measurement and the reference measurement by employing the recursive least square estimator (RLSE). In addition, the proposed algorithm is analyzed for single and multiple RGPO based ECM scenarios. Further, the Cramer Rao Lower Bound (CRLB) for the proposed methodology is derived. The results are quantified with a Position Root Mean Square Error (PRMSE), CRLB, innovation test, normalized estimation error squared (NEES) test, and confidence interval. The simulation results demonstrate that the proposed estimation technique provides good performance in the presence of all the local tracks are being attacked by RGPO ECM. Besides, it is evident from the results that estimator efficiency is falling below the 5% tail probability of the chi-square distribution.

Edge-Conditioned Feature Transform Network for Hyperspectral and Multispectral Image Fusion

Despite recent advances achieved by deep learning techniques in the fusion of low-spatial-resolution hyperspectral image (LR-HSI) and high-spatial-resolution multispectral image (HR-MSI), it remains a challenge to reconstruct the high-spatial-resolution HSI (HR-HSI) with more accurate spatial details and less spectral distortions, since the low-level structure information such as sharp edges tends to be weakened or lost as the network depth grows. To tackle this issue, we creatively propose an edge-conditioned feature transform network (EC-FTN) in this article, which is mainly composed of three parts, namely, feature extraction network (FEN), feature fusion and transformation network (FFTN), and image reconstruction network (IRN). First, two computationally efficient FENs with 3-D convolutions and reshaping layers are employed to extract the joint spectral-spatial features of input images. Then, the FFTN conditioned on the edge map prior can fuse and transform the features adaptively, in which a fusion node and several cascaded feature modulation modules (FMMs) equipped with feature-wise modulation layers are constructed. Specifically, the edge map is generated via transfer learning, i.e., by applying the Sobel operator to feature maps of the red-green-blue (RGB) version of HR-MSI resulting from the pretrained VGG16 model without extra training. Finally, the desired HR-HSI is recovered from the transformed features through IRN. Furthermore, we elaborately design a weighted combinatorial loss function consisting of mean absolute error, image gradient difference, and spectral angle terms to guide the training. Experiments on both ground-based and remotely sensed datasets demonstrate that our EC-FTN outperforms state-of-the-art methods in visual and quantitive evaluations, as well as in fine details reconstruction.

MPTC-FPN: A Multilayer Progressive FPN With Transformer-CNN Based Encoder for Salient Object Detection

Due to the development of Convolutional Neural Networks (CNN), significant progress has been made in Salient Object Detection (SOD). However, methods based on CNN are difficult to achieve good results in learning global context information. Recently, with the rapid development of vision transformer, it provides a new perspective for the performance improvement of salient object detection.Benefiting from the powerful capability of global modeling, transformer can supplement rich global contextual information. For lacking the ability to learn local details, it is suboptimal to only adopt transformer as encoder. Therefore, how to skillfully combine local details and global context information is crucial. We conbine CNN and transformer to propose a Multilayer Progressive FPN with Transformer-CNN Based Encoder For Salient Object Detection (MPTC-FPN). Similar to most of the previous methods, we adopt the FPN network as the basic structure. But the difference from previous methods is that we have six initial features before feature fusion, instead of the traditional four or five. We use a low-level feature generation module (LFGM) to generate a lower-level feature to supplement local details. In addition, we also propose a module to reduce the difference between features (DRM), making the features more conducive to fusion. On the basis of FPN, we add a large number of feature fusion nodes, which makes the process of feature fusion smoother. Moreover, we adjust the supervision strategy, use multiple supervision points, and adopt an appropriate weight distribution strategy among the multiple supervision points. A series of comprehensive experimental results demonstrates that our proposed method outperforms previous state-of-the-art methods on five datasets.

Cross‐scale feature fusion connection for a YOLO detector

Multi-scale feature fusion is often used to address the issue of scale variations in object detection. However, most of the proposed network architectures only combine the features of two adjacent levels sequentially, so the first fusion nodes in both top-down and bottom-up pathways must be blank nodes that only have one input with no feature fusion. In this work, cross-scale feature fusion connection (CFFC) is proposed which aims to enhance the entire feature hierarchy by propagating the features of each level more efficiently. The proposed method reuses and aggregates all the features of other scales to the blank nodes in both top-down and bottom-up pathways. Furthermore, the authors remove the 1 × 1 convolutional layer and replace the shortcut with concatenation before fusing multiple features. These concatenated feature maps are then supervised by the channel attention block at the fusion nodes. This modification allows the network to learn the important degree of each level in concatenated feature maps along the channel dimension. It is also observed that the proposed method alleviates the inconsistency in feature pyramids with fewer parameters. The performance of a YOLO object detector equipped with the proposed method on the COCO test-dev 2017 is evaluated. The results show that the proposed method outperforms other architectures presented in the literature.

Remote Sensing Change Detection Based on Multidirectional Adaptive Feature Fusion and Perceptual Similarity

Remote sensing change detection (RSCD) is an important yet challenging task in Earth observation. The booming development of convolutional neural networks (CNNs) in computer vision raises new possibilities for RSCD, and many recent RSCD methods have introduced CNNs to achieve promising improvements in performance. In this paper we propose a novel multidirectional fusion and perception network for change detection in bi-temporal very-high-resolution remote sensing images. First, we propose an elaborate feature fusion module consisting of a multidirectional fusion pathway (MFP) and an adaptive weighted fusion (AWF) strategy for RSCD to boost the way that information propagates in the network. The MFP enhances the flexibility and diversity of information paths by creating extra top-down and shortcut-connection paths. The AWF strategy conducts weight recalibration for every fusion node to highlight salient feature maps and overcome semantic gaps between different features. Second, a novel perceptual similarity module is designed to introduce perceptual loss into the RSCD task, which adds perceptual information, such as structure and semantic information, for high-quality change map generation. Extensive experiments on four challenging benchmark datasets demonstrate the superiority of the proposed network compared with eight state-of-the-art methods in terms of F1, Kappa, and visual qualities.

Modified CSMA/CA protocol for real-time data fusion applications based on clustered WSN

The large amount of data generated by the Internet of Things (IoT) is exploited by the data fusion process to improve the quality of services (QoS) requested by the user. Data fusion systems typically collect and fuse data from various sensor nodes to achieve better data quality (more precision, accuracy, or global view) on the field of interest. For the specific case of the wireless sensor network (WSN) based on cluster-tree topology, the data transmission between nodes and the intermediate data fusion node (DFN) depends primarily on the channel access often managed by the Carrier-Sens Multiple Access with Collision Avoidance (CSMA/CA) protocol. In this article, a modified CSMA/CA is proposed to meet the requirements of the WSN real-time data fusion applications and, in particular, to ensure better management of the transmission channel. It takes into account a transmission time-delay, schedules the retransmission dynamically, and eliminates data packets scheduled beyond the predefined time-delay, thereby releasing the channel to the benefit of other nodes. Moreover, before proceeding with the fusion at the DFN level, it optimizes the probability of receiving data from each node in the specified time-delay. The proposed solution is implemented under the Contiki operating system; it aims to collect data from all nodes within a given time-delay. The results of simulations and experiments show increasing in the data received within time-delay, collisions reduction, and saving energy in the WSN. Moreover, two real-time data fusion applications, namely mobile localization and majority decision-making, are also simulated to support the found results. Compared to the use of CSMA/CA as implemented in Contiki, using the proposed modified CSMA/CA in both data fusion applications improves QoS.

Long-term tracing and staining of carbon nanoparticles for axillary lymph nodes in patients with locally advanced breast cancer treated with neoadjuvant chemotherapy

BackgroundThe regression of positive nodes in breast cancer after neoadjuvant chemotherapy (NAC) remains unknown. This study aimed to investigate this regression by injecting and tracing carbon nanoparticles (CNs) into the fusion node prior to NAC in patients with breast cancer. MethodsGuided by ultrasound, 0.3 mL of CNs suspension was injected in the fusion node prior to NAC in 110 patients with local advanced breast cancer. Then the patients underwent breast surgery and total axillary lymph node dissection following 2–6 cycles of NAC. The distribution by intercostobrachial nerves (ICBN) of positive nodes and black-stained nodes was researched, and the relationship between the distribution and lymphovascular invasion were investigated by response to NAC. ResultsWhen patients were ranked by response to NAC (from sensitive to resistance), the number of positive nodes increased, as did the proportion of lymphovascular invasion, the number of black-stained nodes decreased. A significantly negative relationship was found between the number of positive nodes and the number of black-stained nodes (p < 0.001). The positive nodes in patients with sensitive consequence followed the rule from under the ICBN to above the ICBN. However, there was counter-example (skip metastasis) in the patients with resistance result. ConclusionThe regression of positive nodes follows the rule from upper to under, inner to outer in the patients with sensitive consequence to NAC. Long-term staining and tracing by CNs might provide an acceptable and feasible technique to investigate the regression of positive nodes, and would be a potential method for NAC-treated patients by using of ICBN. Trial registrationNCT 03355261. Retrospectively registered on November 28, 2017.

From Simultaneous Localization and Mapping to Collaborative Localization for Intelligent Vehicles

This paper describes a new method for real-time collaborative localization for intelligent vehicles based on a combination of an extension of simultaneous localization and mapping and track-to-track fusion methods. This strategy aims to overcome the shortcomings of the embedded proprioceptive sensors and solve the localization issues in a cluster of intelligent vehicles, which are equipped with low-cost navigation systems (global position systems, rangefinders, and vehicle to vehicle communication means) in an unknown environment. The strategy improves the vehicles’ localization accuracy and tracks a cluster of vehicles for advanced driver assistance systems and vehicles self-driving. For real-time purposes, the computational complexity of standard solutions, which are based on Kalman filter derivatives, is transformed, herein, from cubic to quadratic with respect to the state vector of the cluster. Furthermore, the correlated data is another challenge that needs to be solved in cooperative localization scenarios. To this end, two independent, local and global, fusion nodes are associated with each vehicle. The local node exploits multiple forms of the extended Kalman filter and its dual extended information filter to estimate the vehicles’ state, information vectors, covariance and information matrices in the moments and information forms, respectively. Then, the vehicles broadcast the result of their respective local fusion node to cluster. The information is used to solve the second problem, which is a track-to-track fusion on distributed architectures, with two methods: covariance intersection and information matrix fusion in the global fusion node. The simulation and the experimental results of the proposed methods, on distributed architectures, are compared to the optimal solution of centralized data fusion, and to the traditional SLAM method in terms of root mean square errors and consistency.

Cooperative Spectrum Sensing with Distributed/Centralized Relay Selection

In this paper, we suggest a new Cooperative Spectrum Sensing (CSS) algorithm using Distributed Relay Selection. Spectrum sensing is performed at Fusion Node (FN) using only the signal from Primary User (PU) when its Signal to Noise Ration (SNR) is larger than threshold $$\gamma _{th}$$ . If SNR of the link between PU and FN is lower than $$\gamma _{th}$$ , a relay is activated using distributed relay selection. All relays compare their SNRs to threshold $$\alpha$$ and transmit only if the SNR exceeds $$\alpha$$ . If the SNR of all relays are less than $$\alpha$$ , there is an outage event, no relay is selected and only the signal from PU will be used for spectrum sensing. If SNRs of more relays than two relays are larger than $$\alpha$$ , a collision occurs and spectrum sensing uses only the signal from PU. Threshold $$\alpha$$ is optimized using the Gradient algorithm to yield the largest detection probability. We also compare our results to spectrum sensing with centralized relay selection using opportunistic Amplify and Forward (OAF) or Partial Relay Selection (PRS). In OAF, the end-to-end SNR between PU, relays and FN are sent to the FN to be compared and the relay with largest SNR is activated. In PRS, the SNR at the relays are sent to the FN in order to be compared. Then, the relay with largest SNR of first hop, between PU and relays, is activated. CSS with distributed relay selection is novel and no yet studied.

Integrated hybrid optical networking for 5G access networks

Today, deployment of optical fiber has offered large transmission capacity which cannot be efficiently utilized by the electronic switches. Rather, Integrated Hybrid Optical Network (IHON) is a promising approach which combines both packet and circuit switching techniques. As a result, it achieves efficient utilization of the bulk capacity and guarantees absolute Quality of Service (QoS) by optimizing the advantages of the two switching schemes while diminishing their disadvantages. Transpacket has developed a Fusion node implementing IHON principles in Ethernet for the data plane. Hence, this paper investigates and evaluates IHON network for 5G access networks. The simulated results and numerical analysis confirm that the Packet Delay Variation (PDV), Delay and Packet Loss Ratio (PLR) of Guaranteed Service Transport. (GST) traffic in IHON network met the requirements of 5G mobile fronthaul using CPRI. The number of nodes in the network limits the maximum separation distance between Base Band Unit. (BBU) and Remote Radio Head (RRH), link length; for increasing the number of nodes, the link length decreases. In addition to this, we verified how the leftover capacity of fusion node can be used to carry the low priority packets and how the GST traffic can have deterministic characteristics on a single wavelength by delaying it with Fixed Delay Line (FDL). For example, for L&lt;sup&gt;SM&lt;/sup&gt;&lt;sub&gt;1GE&lt;/sub&gt;=0.3 the added Statistical Multiplexing (SM) traffic increases the 10GE wavelength utilization up to 89% without any losses and with SM PLR=1&lt;em&gt;E&lt;/em&gt;&lt;sup&gt;−03&lt;/sup&gt; up to 92% utilization.

A Swarm Optimization-Enhanced Data Aggregation Tree Based on a Nonuniform Clustering Structure for Long and Linear Wireless Sensor Networks

A reasonable clustering structure can make data aggregation methods run efficiently in most wireless sensor networks (WSNs). However, compared with other WSNs, the energy imbalance problem of long and linear WSNs is more serious, and the delay is higher. It is still impossible to achieve efficient data aggregation by optimizing the clustering structure. Therefore, this letter proposes a novel data aggregation tree based on a clustering structure. First, through the optimization of cluster head selection and multihop path selection, this letter proposes a long and linear nonuniform clustering structure to improve the energy balance. Furthermore, taking the minimum delay as the objective function and the number of fusion nodes and energy balance as the constraint, an aggregation node selection mechanism based on a swarm optimization algorithm is proposed to build a data aggregation tree based on a long and linear nonuniform clustering structure. The simulation results show that the proposed method can effectively reduce the delay and energy consumption and that it is suitable for long and linear WSNs.

Cooperative spectrum sensing with incremental relaying

In this article, we suggest a new Spectrum Sensing (SS) algorithm using Incremental Relaying (IR). In previous studies, the relays always cooperate in the SS process. However, sometimes the Signal to Noise Ratio (SNR) of the direct link between the Primary User (PU) and the Fusion Node (FN) is high and cooperation is not required. We suggest to activate the relays only when the SNR of direct link is lower than a predefined threshold T. Otherwise, the relays should be idle. In the proposed SS algorithm with IR, all relays can amplify the PU signal to FN only when the SNR of direct link is lower than T. We can also implement IR with relay selection techniques. When the SNR of direct link is lower than T, we select the best relay. Three relay selection algorithms are investigated such as opportunistic amplify and forward, partial and reactive relay selection.