Distributed Decision Fusion Research Articles

M-ary Distributed Decision Fusion for Multihop Relay Wireless Sensor Networks: Decision Fusion Rule, Implementation Framework, and Performance Analysis

M-ary Distributed Decision Fusion for Multihop Relay Wireless Sensor Networks: Decision Fusion Rule, Implementation Framework, and Performance Analysis

Distributed Decision Fusion in Wireless Sensor Networks for Contextual Experience Sensing and Recommendation Forming in E-Commerce

Distributed Decision Fusion in Wireless Sensor Networks for Contextual Experience Sensing and Recommendation Forming in E-Commerce

Distributed Decision Fusion with M-ary Signaling and k-bit Transmission on Sensor Observation in Wireless Sensor Networks

Multi-level decisions on sensor detection is able to improve the detection performance on the final decision made at the fusion center (FC) in wireless sensor networks (WSN). In this paper, the performance analysis of an M-ary signaling (MS) scheme using analog transmission and a k-bit transmission (KB) scheme is both examined for distributed binary detection. Under the multi-level decision algorithms, each sensor sends a signal carrying the information of a quantized version of a local decision statistic such as the conditional mean or the log-likelihood ratio. In MS, the output of the quantizer is transmitted directly without digitalizing and coding process, while in KB, each quantization output is coded with k bits and hereby a sensor sends a k-bit hard local decision to the FC. At the FC, the linear combiner detection rule on the transmission schemes is both adopted to make the final decision. The effects of the sensor decision and the transmission errors are incorporated in the analysis of the erroneous performance of the final decision. The goal of the proposed schemes is to minimize the final errors at the FC via optimizing the region allocation on the multi-level decision at the sensor. The numerical results illustrate that the proposed schemes achieve significant improvement in error performance over the conventional schemes under either additive white Gaussian noise (AWGN) channel or Rayleigh faded channel.

Experimental Analysis of Wideband Spectrum Sensing Networks Using Massive MIMO Testbed

In this paper, we investigate the practical implication of employing virtual massive multiple-input-multiple output (MIMO) based distributed decision fusion (DF) for collaborative wideband spectrum sensing (WSS) in a cognitive radio (CR)-like network. Towards that end, an indoor-only measurement campaign has been conducted to capture the propagation statistics of a 4 × 64 massive MIMO system with one authorized primary user (PU) and 4 unauthorized secondary users (SUs) transmitting simultaneously over a 20 MHz band divided into 1200 subcarriers. The frequency subcarriers belong to an Orthogonal-frequency-division-multiplexing (OFDM)-like set-up without the addition of cyclic prefix (CP) to the transmit symbols. Measurements are accumulated for different relative positions of the SUs which are analyzed to extract fading, shadowing, noise and interference power statistics. Log-likelihood ratio (LLR) based fusion rule and three different sets of sub-optimum fusion rules along with their time-reversed versions are formulated for combining decisions on the availability of each subcarrier transmitted by the SUs. The extracted channel characteristics are incorporated in both analytical and simulated performance analysis of the devised fusion rules for comparison and testing the validity of distributed DF in realistic collaborative WSS scenario.

Analytic Sensor Rules for Optimal Distributed Decision Given $K$-Out-of-$L$ Fusion Rule Under Monte Carlo Approximation

With the development of large-scale sensor networks, there is an increasing interest for high dimensional distributed decision fusion problem in statistical decision, machine learning, control theory, etc. In this article, we investigate the optimal sensor quantized rules of the distributed decision under a given fusion rule for conditionally dependent and high dimensional sensor observations. We provide a Monte Carlo importance sampling method to reduce the computational complexity of the distributed decision fusion. For the K-out-of-L rule, we derive a group of analytic sensor rules based on the necessary and sufficient condition of the optimal sensor rules. In term of efficiency, it is significantly better than the traditional iterative search algorithms, such as the Riemann sum approximation iteration algorithm. The analytic solution is also a general result since it does not rely on the specific K value of the K-out-of-L rule, the specific conditional probability density function and the dimension of sensor observations. Thus, it can be applied to multisensor decision fusion problems with high dimensional dependent sensor observations. For the general fusion rules rather than the K-out-of-L rule, the Monte Carlo Gauss-Seidel algorithm is also provided. The numerical examples demonstrate the effectiveness of the analytic solution and the Monte Carlo Gauss-Seidel algorithm.

Decision Fusion in Distributed Cooperative Wireless Sensor Networks

In this paper, the distributed decision fusion (DF) problem of cooperative wireless sensor networks is considered, where a group of sensors send their local decisions to a fusion center via a set of relays using decode-and-forward relaying. The likelihood ratio test under Neyman–Pearson sense is used to derive the optimal DF rule (DFR). Moreover, three suboptimal fusion rules are derived to enable a broad range of complexity-performance tradeoffs. The performance of the optimal and suboptimal fusion schemes is evaluated in terms of probability of detection, false alarm, and fusion decision error where analytical expressions are derived for the suboptimal schemes, while Monte Carlo simulation is used for the optimal DFR. The obtained analytical and simulation results show that the decision error performance of the network is mainly determined by the number and accuracy of the local sensors, while the relaying process could be effective in mitigating the fading channel effects. Furthermore, no significant improvement is achieved by increasing the number of relays beyond three for each sensor.

Distributed decision fusion under nonideal communication channels with adaptive topology

Multi-sensor decision fusion has attracted some attention in information fusion field, meanwhile, the distributed target detection has been a well-studied topic in the multi-sensor detection theory. This paper investigates the increase in detection reliability that an adaptive network (with adaptive topologies and nonideal channels and decision fusion rules) can provide, compared with a fixed topology network. We consider a network, consisting of K-local uncertainty sensors and a Fusion Center (FC) tasked with detecting the presence or absence of a target in the Region of Interest (ROI). Sensors transmit binary modulated local decisions over nonideal channels modeled as Gaussian noise or fading channels. Assuming that the signal intensity emitted by a target follows the isotropic attenuation power model, we consider three classes of network topology architectures: (1) serial topology; (2) tree topology, and (3) parallel topology. Under the Neyman–Pearson (NP) criterion, we derive the optimal threshold fusion rule with adaptive topology to minimize the error probability. Extensive simulations are conducted to validate the correctness and effectiveness of the proposed algorithms.

Dynamic Fuzzy Rule-based Source Selection in Distributed Decision Fusion Systems

ABSTRACTA key challenge in decision fusion systems is to determine the best performing combination of local decision makers. This selection process can be performed statically at the training phase or dynamically at the execution phase, taking into consideration various features of the data being processed. Dynamic algorithms for the selection of competent sources are generally more accurate, but they are also computationally more intensive and require more memory. In this research, we propose a fuzzy rule-based approach for dynamic source selection (FDSS) that compresses the knowledge from local sources using a divide-and-conquer strategy along with the basic concepts of coverage and truth value criteria, leading to less memory requirement and faster processing. A top-down approach to FDSS is then used to reach a parameter-free algorithm, i.e. one that avoids the restrictive parameters/threshold settings of FDSS. The rule bases in both approaches are created recursively and use the conditional probabilities of each class's correctness as the rule's weight. The proposed approaches are compared against several competing dynamic classifier selection methods based on local accuracy. Results indicate that the proposed fuzzy rule structures are generally faster and require less memory, while they also lead to more accurate decisions from the uncertain decisions from multiple sources.

Distributed Decision Fusion over Nonideal Channels Using Scan Statistics

Distributed Decision Fusion over Nonideal Channels Using Scan Statistics

Distributed decision fusion over fading channels in hierarchical wireless sensor networks

In this work, we investigate distributed decision fusion in hierarchical wireless sensor networks that are degraded by fading and noise. With the use of the complete fading channel state information (CSI), we first derive the likelihood ratio test (LRT) based optimum fusion rule, which we call LRT–CSI. Then, we relax the use of the complete CSI and only the exact phase information is employed together with channel envelope statistics (CS), and we develop another LRT based fusion rule named LRT–CS, which is computationally simpler to implement compared to LRT–CSI. Finally, we analyze the detection performance of all the proposed fusion rules through extensive numerical results.

Performance Analysis of Distributed Decision Fusion Using A Multilevel Censoring Scheme in Wireless Sensor Networks

Sensor-censoring schemes have been widely applied to distributed detection to achieve the goal of energy saving in limited-energy wireless sensor networks (WSNs). In the traditional censoring scheme, the sensor transmits data to the fusion center (FC) only when the reliability is beyond a specified threshold, and hereby, energy saving is achieved. To further exploit the energy-efficiency capability of the censoring decision scheme, this paper proposes a new multilevel sensor-censoring scheme. As opposed to our earlier proposed three-region censoring scheme, the number of censoring levels in the proposed scheme is not restricted. A criterion on computing the reliability of the observation in each region is quantitatively determined, which controls the power of the signal transmitted to the FC. When the observation falls within the region with high reliability, the power of the transmitted signal is high, and vice versa. Both soft- and hard-decision fusion rules under the considered multilevel censoring strategy are investigated. For a given fusion rule, the main problem of this work is to minimize the error probability of the global decisions made by the FC by obtaining the best region allocation on the observation, which corresponds to the optimum multilevel censoring regions. The performance of the proposed multilevel censoring scheme is examined in terms of both energy saving and error performance. We compare the multilevel censoring scheme with the conventional scheme, which censors no sensor observations. The results show that the multilevel censoring scheme not only offers us a more flexible design of the censoring strategy but consumes much less energy as well, compared with the conventional scheme when the same error probability constraint is given. In addition, the obtained result shows that the superiority of the multilevel censoring scheme becomes more remarkable when the signal strength of the sensor observations is small.

Performance Analysis of Distributed Decision Fusion Using a Censoring Scheme in Wireless Sensor Networks

Sensor-censoring schemes have been widely applied to distributed detection to achieve the goal of energy saving in limited-energy wireless sensor networks (WSNs). In the traditional censoring scheme, the sensor transmits data to the fusion center (FC) only when the reliability is beyond a specified threshold, and hereby, energy saving is achieved. To further exploit the energy-efficiency capability of the censoring decision scheme, this paper proposes a new multilevel sensor-censoring scheme. As opposed to our earlier proposed three-region censoring scheme, the number of censoring levels in the proposed scheme is not restricted. A criterion on computing the reliability of the observation in each region is quantitatively determined, which controls the power of the signal transmitted to the FC. When the observation falls within the region with high reliability, the power of the transmitted signal is high, and vice versa. Both soft- and hard-decision fusion rules under the considered multilevel censoring strategy are investigated. For a given fusion rule, the main problem of this work is to minimize the error probability of the global decisions made by the FC by obtaining the best region allocation on the observation, which corresponds to the optimum multilevel censoring regions. The performance of the proposed multilevel censoring scheme is examined in terms of both energy saving and error performance. We compare the multilevel censoring scheme with the conventional scheme, which censors no sensor observations. The results show that the multilevel censoring scheme not only offers us a more flexible design of the censoring strategy but consumes much less energy as well, compared with the conventional scheme when the same error probability constraint is given. In addition, the obtained result shows that the superiority of the multilevel censoring scheme becomes more remarkable when the signal strength of the sensor observations is small.

A Low-Cost VLSI Architecture for Fault-Tolerant Fusion Center in Wireless Sensor Networks

A fault-tolerant distributed decision fusion in the presence of sensor faults via collaborative sensor fault detection (CSFD) was proposed in our previous research . The scheme can identify the faulty nodes efficiently and improve the performance of the decision fusion significantly. It achieves very good performance at the expense of such extensive computations as exponent and multiplication/division in the detecting process. In many real-time WSN applications, the fusion center might be implemented in an ASIC and included in a standalone device. Therefore, a simple and efficient decision fusion scheme requiring lower hardware cost and power consumption is extremely desired. In this paper, we propose the approximated collaborative sensor fault detection (ACSFD) scheme and its VLSI architecture. Given the low circuit complexity, it is suitable for hardware implementation. The ACSFD circuit contains 9265 gates and requires a core size of 368 × 358 ¿m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> by using TSMC 0.18 ¿m cell library. It can operate at a clock rate of 102 MHz with a power consumption of 2.516 mW. Simulation results indicate that ACSFD performs better in fault tolerance than the conventional approach.

An iterative method for decision fusion in multiple sensor systems

Distributed decision fusion has been intensively studied in the past. This interest has been sparked by the requirement of a distributed surveillance system to be more reliable and immune to electronic attack than a single sensor system. In this paper, we consider a binary decentralized distributed decision fusion in which a system of multiple independent sensors monitors a common volume and provides relevant binary decisions about the state of the environment to a data fusion center. The fusion center combines the binary decisions of the individual distributed sensors into a final global decision. We propose a simple iterative method for optimizing multiple sensor decision fusion systems, in terms of both the sensors and the fusion center. The proposed iterative method determines, for a given global false alarm probability, the corresponding optimum setting of the individual sensors thresholds and the fusion center combining strategy that yields maximum global detection probability. The proposed method enables efficient search for the optimum solution by starting from a variety of initial trial values. The performance of the proposed method is provided in case of Rayleigh distributed observations and is proved to be cost effective and efficient.

Fault-tolerant decision fusion via collaborative sensor fault detection in wireless sensor networks

This work addresses fault-tolerant distributed decision fusion in the presence of sensor faults when local sensors sequentially send their local decisions to a fusion center. This work also proposes a collaborative sensor fault detection (CSFD) scheme for eliminating unreliable local decisions when performing distributed decision fusion. In particular, the concept of pseudo-sensor faults is presented. Due to the difficulty in determining pseudo-sensor faults in real time based on the minimization of the error probability, an upper bound is established on the fusion error probability, where distributions of local decisions are not necessarily identical. Given a pre-designed fusion rule under the assumption of identical local decision rules in fault-free environments, this bound can then characterize the fusion error probability when local decisions are no longer identical due to sensor faults. Hence, a criterion is proposed based on this error bound to determine a set of pseudo-faulty nodes at each time. Once the fusion center identifies the pseudo-faulty nodes, all corresponding local decisions are removed from the computation of likelihood ratios adopted to make the final decision. To enhance the efficiency of the proposed search criterion, another, less complex criterion is developed by integrating the Kullback-Leibler distance. Simulation results indicate that this less complex criterion provides even better fault-tolerance capability in some situations when sensor faults significantly deviate from normally operating sensors. Performance evaluation results also indicate that the fault-tolerance capability of the proposed approach employing a CSFD scheme is superior to conventional decision fusion.

Optimal decision fusion given sensor rules

When all the rules of sensor decision are known, the optimal distributed decision fusion, which relies only on the joint conditional probability densities, can be derived for very general decision systems. They include those systems with interdependent sensor observations and any network structure. It is also valid for m-ary Bayesian decision problems and binary problems under the Neyman-Pearson criterion. Local decision rules of a sensor with communication from other sensors that are optimal for the sensor itself are also presented, which take the form of a generalized likelihood ratio test. Numerical examples are given to reveal some interesting phenomena that communication between sensors can improve performance of a senor decision, but cannot guarantee to improve the global fusion performance when sensor rules were given before fusing.

Distributed Decision Fusion With a Random-Access Channel for Sensor Network Applications

The envisioned use of sensor networks for military and civilian applications calls for the deployment of a large number of sensors for extended periods over wide geographical areas. Due to energy and bandwidth constraints, most sensor fields would be dormant, initiating communication only when a threat is detected. Many architectures under consideration call for compression of locally sensed data into binary decisions. These schemes use a common channel for communication between local detectors (LDs) and the decision fusion center (DFC) that integrates the multiple detector decisions. Unlike most parallel fusion schemes, which use a dedicated communication channel between every LD and the DFC, sensor fields would employ a single shared, time-slotted communication link for all LDs to transmit decisions to the DFC. In this paper, we introduce two window-based methods for managing traffic over this channel. The first allows simultaneous messages to collide. The DFC uses the statistics of the channel states (i.e., the numbers of successful transmissions, idle slots, and collisions during a specified time period) to make its global target/no target decision. The second method uses a simple collision resolution algorithm (CRA), similar to slotted-ALOHA, with dynamically updated retransmission probability. With this scheme, the DFC makes its decision based on data communicated successfully within a specified time window. Overall performance of the two approaches are presented and compared. Simple rules are developed for assessing the conditions under which each one is preferred.

Distributed decision fusion in the presence of link failures

The problem of optimal data fusion involving detector unit communication link failures is considered. Two strategies for decision making in presence of link failures are examined and an optimal decision making scheme in the sense of the Neyman-Pearson (N-P) test is proposed. The performance of q+1 reliable links versus q reliable links are examined theoretically, as well as, numerically using the receiver operating characteristics (ROCs).

Distributed decision fusion under unknown distributions

The problem of distributed decision fusion is studied in the case when the probability distributions of the individual detectors are not available. The detector system is available so that a training sample can be generated by sensing objects with known parameters or classification. Earlier solutions to this problem required some knowledge of the error distributions of the detectors, for example, either in a parametric form or in a closed analytical form. Here we present three methods that, given a sufficiently large training sample, yield an approximation to the optimal fusion rule with an arbitrary level of confidence. These methods are based on (i) empirical estimation, (ii) approximate decision rule, and (iii) nearest-neighbor rule. We show that a nearest-neighbor rule provides a computationally viable solution, which approximates a neural network-based one while ensuring fast computation. {copyright} {ital 1996 Society of Photo{minus}Optical Instrumentation Engineers.}

Dignet: an unsupervised-learning clustering algorithm for clustering and data fusion

Dignet is a self-organizing artificial neural network (ANN) that exhibits deterministically reliable behavior-to-noise interference, when the noise does not exceed a prespecified level of tolerance. The complexity of the proposed ANN, in terms of neuron requirements versus stored patterns, increases linearly with the number of stored patterns and their dimensionality. The self-organization of Dignet is based on the idea of competitive generation and elimination of attraction well in the pattern space. Dignet is used for detection and distributed decision fusion. Analytical and numerical results are included. >