A correlation coefficient for belief functions

Dempster–Shafer evidence theory is widely used in the information fusion field for its effectivity in representing and handling uncertain information. However, applications of Dempster rule in combining multiple conflicting evidence often cause counterintuitive results. One of the existing researches on conflict is based on the similarity of evidence. However, due to the fact that computational complexity of the existing methods is large, it is difficult to meet the real-time requirements of systems. Therefore, new effective methods with acceptable expense should be explored. In this article, following the idea of modifying the source model of evidence, a new method based on DEMATEL is proposed to take the weight of each evidence into consideration. First, the total-relation matrix is determined by the similarity among evidence. Second, prominence and importance are calculated. Finally, the weighted average combination result can be obtained based on Dempster’s rule of combination. Numerical examples are used to demonstrate that the proposed model is efficient to both deals with conflicting evidence and reduce computational complexity.

Combining conflicting evidence using the DEMATEL method

With the popularity and development of network technology and the Internet, intrusion detection systems (IDSs), which can identify attacks, have been developed. Traditional intrusion detection algorithms typically employ mining association rules to identify intrusion behaviors. However, they fail to fully extract the characteristic information of user behaviors and encounter various problems, such as high false alarm rate (FAR), poor generalization capability, and poor timeliness. In this paper, we propose a network intrusion detection model based on a convolutional neural network-IDS (CNN-IDS). Redundant and irrelevant features in the network traffic data are first removed using different dimensionality reduction methods. Features of the dimensionality reduction data are automatically extracted using the CNN, and more effective information for identifying intrusion is extracted by supervised learning. To reduce the computational cost, we convert the original traffic vector format into an image format and use a standard KDD-CUP99 dataset to evaluate the performance of the proposed CNN model. The experimental results indicate that the AC, FAR, and timeliness of the CNN-IDS model are higher than those of traditional algorithms. Therefore, the model we propose has not only research significance but also practical value.

/pdf/an-intrusion-detection-model-based-on-feature-reduction-and-31yb8gvr9s.pdf

An Intrusion Detection Model Based on Feature Reduction and Convolutional Neural Networks

Mechanical fault diagnosis and prediction in IoT based on multi-source sensing data fusion

Dempster–Shafer evidence theory is widely used in many applications such as decision making and pattern recognition. However, Dempster’s combination rule often produces results that do not reflect the actual distribution of belief when collected evidence highly conflicts each other. In this paper, a base belief function is proposed to modify the classical basic probability assignment before combination in closed-world. Base belief function focuses on making combination result intuitive especially when evidences highly conflict each other. Compared to other methods, the combination result produced by proposed method is logical and consistent with real world with less computational complexity and better performance. The advantage of base belief function is that it can avoid high conflicts between evidences and is especially suitable for the situation where the evidences appear in sequence. Several numerical examples as well as experiments using real data sets from the UCI machine learning repository for classification are employed to verify the rationality of the proposed method.

Base belief function: an efficient method of conflict management

Deep learning (DL) models are vulnerable to adversarial attacks, by adding a subtle perturbation which is imperceptible to the human eye, a convolutional neural network (CNN) can lead to erroneous results, which greatly reduces the reliability and security of the DL tasks. Considering the wide application of modulation recognition in the communication field and the rapid development of DL, by adding a well-designed adversarial perturbation to the input signal, this article explores the performance of attack methods on modulation recognition, measures the effectiveness of adversarial attacks on signals, and provides the empirical evaluation of the reliabilities of CNNs. The results indicate that the accuracy of the target model reduce significantly by adversarial attacks, when the perturbation factor is 0.001, the accuracy of the model could drop by about 50 ${\%}$ on average. Among them, iterative methods show greater attack performances than that of one-step method. In addition, the consistency of the waveform before and after the perturbation is examined, to consider whether the added adversarial examples are small enough (i.e., hard to distinguish by human eyes). This article also aims at inspiring researchers to further promote the CNNs reliabilities against adversarial attacks.

Adversarial Attacks in Modulation Recognition With Convolutional Neural Networks

Information fusion is a very important technology which can use multisensor network data to get a better performance than single one; therefore, it is widely used in the filed of target recognition, target tracking, automatic control, decision making and so on. However, because of noise and interference, sometimes the sensors may obtain erroneous, inaccurate or heterogeneous data, which will produce the conflict information among different sensors and get the wrong result after information fusion. In this paper, based on the Dempster---Shafer (D---S) theory, we introduce how to set up the model of multisensor network information fusion. And then, we discuss the problem of conflict information fusion in the framework of evidence and several improved methods are introduced. Finally, based on Mahalanobis distance, an improved solution method is presented. The numerical simulation results prove that this new improved method can get the same result as traditional methods, beyond which it can make a reasonable decision with high conflict information. Therefore, this new improved method can be used in the filed of high noise and interference.

A new combination method for multisensor conflict information

Energy consumption and channel access time are two of the most crucial design issues in underwater acoustic communication networks since prolonging the network lifetime and improving the network throughput depends on the efficient energy resource management and channel access rules. This paper proposes a new full-duplex based and distance aware channel access protocol for ad-hoc underwater acoustic communication networks. The protocol saves transmission energy by avoiding collisions while maximizing throughput, and solves the hidden/exposed terminal problems efficiently. It is based on the full-duplex communication where we virtually separate the channel into two portions, using different frequency bands and different modulation/demodulation to transmit control packages and data packages separately. This protocol achieves a throughput several times higher than that of the traditional CSMA, while offering similar savings in energy. We have evaluated performance, efficiency and engineering feasibility of this protocol by both simulations and sea trails.

A full-duplex based protocol for underwater acoustic communication networks

In underwater acoustic orthogonal frequency division multiplexing (OFDM) communication system, channel variations would introduce inter-carrier interference (ICI). This gets more severe as mobile speed, carrier frequency or OFDM symbol duration increases. In this paper, we propose a kind of parallel iterative ICI cancellation algorithm to combat that problem. The proposed method extracts channel variations from the adjacent OFDM symbols, and constantly improves the estimation accuracy of ICI through iteration. Finally, simulation and trial in real lake channel verify the availability and stability of the algorithm in the underwater acoustic time varying channel. In addition, this algorithm avoids the matrix inversion, reducing the complexity of the algorithm, and has the obvious advantage in accuracy and speed.

Parallel Iterative Inter-carrier Interference Cancellation in Underwater Acoustic Orthogonal Frequency Division Multiplexing

Machine learning and deep learning algorithms have proved to be a powerful tool for developing data-driven signal processing algorithms for challenging engineering problems. This paper studies the modern machine learning algorithm for modeling nonlinear devices like power amplifiers (PAs) for underwater acoustic (UWA) orthogonal frequency divisional multiplexing (OFDM) communication. The OFDM system has a high peak to average power ratio (PAPR) in the time domain because the subcarriers are added coherently via inverse fast Fourier transform (IFFT). This causes a higher bit error rate (BER) and degrades the performance of the PAs; hence, it reduces the power efficiency. For long-range underwater acoustic applications such as the long-term monitoring of the sea, the PA works in full consumption mode. Thus, it becomes a challenging task to minimize power consumption and unnecessary distortion. To mitigate this problem, a receiver-based nonlinearity distortion mitigation method is proposed, assuming that the transmitting side has enough computation power. We propose a novel approach to identify the nonlinear power model using a modern deep learning algorithm named frequentative decision feedback (FFB); PAPR performance is verified by the clipping method. The simulation results prove the better performance of the PA model with a BER with the shortest learning time.

https://www.mdpi.com/2076-3417/10/14/4986/pdf

A Nonlinear Distortion Removal Based on Deep Neural Network for Underwater Acoustic OFDM Communication with the Mitigation of Peak to Average Power Ratio

Xuefei Ma

Papers

Adversarial Attacks in Modulation Recognition With Convolutional Neural Networks

A new combination method for multisensor conflict information

A full-duplex based protocol for underwater acoustic communication networks

Parallel Iterative Inter-carrier Interference Cancellation in Underwater Acoustic Orthogonal Frequency Division Multiplexing

A Nonlinear Distortion Removal Based on Deep Neural Network for Underwater Acoustic OFDM Communication with the Mitigation of Peak to Average Power Ratio