11 August 2022 in IEEE Transactions on Geoscience and Remote Sensing
In the complex and changeable marine environment, it is difficult to achieve high-performance detection based on statistical theory for small sea surface detectors in practical applications. In this work, a method for detecting small targets on the sea surface based on sequence features is proposed from the perspectives of feature extraction and feature classification on a basis of real data. The sequence-feature method first extracts three sequence features from the radar echo sequence, namely, the instantaneous phase (IP), Doppler spectrum entropy, and short-time Fourier transform (STFT) marginal spectrum. The features are used to train the bidirectional long short-term memory (Bi-LSTM) networks model so that it has the ability to distinguish the target and the sea clutter. The measured dataset verifies that the proposed detector can achieve the detection of sea surface targets with controllable false alarm rate (FAR), and the performance is better than several existing detectors.
22 February 2010 in IEEE Transactions on Vehicular Technology
Foliage is a rich scattering environment that is slowly time varying. Most previous investigations in foliage models center on the statistical modeling of clutters and targets. Ideally, it would be desirable to characterize the nature of the propagation channel in foliage; however, it has not been investigated in detail up until now. This paper studies the problem of nonline-of-sight (NLOS) channel modeling based on extensive data collected using both narrowband and ultrawideband (UWB) radars. The modeling adopts the CLEAN algorithm, in which the channel-impulse response (CIR) is accomplished. It is observed that the multipath contributions arriving at the receiver are grouped into clusters. The arrival of clusters can be modeled as a Poisson process, whereas within each cluster, subsequent multipath contributions or rays also arrive according to a Poisson process. However, the arrival rate is quite different, along with the carrier frequency. It is also proposed that the amplitude of multipath channels can more accurately be characterized by a log-logistic distribution (LLD) other than commonly used clutter models such as the log-normal, the Weibull, or the Rayleigh fading model. The proposed foliage channel model is extendable to other outdoor environments. This is a great advantage for the specification and development of future wireless systems.
9 October 2017 in IEEE Internet of Things Journal
Soil moisture (SM) retrieval using wireless signals has become a research focus with the development of sensor devices in internet of things (IOT). Studies applying ground-penetrating radar (GPR) have improved the accuracy of SM retrieval, however the field-scaled data are hardly satisfactory mainly due to the frequency response of the antenna, and it’s not cost-effective for farmers to monitor the soil conditions. In this paper, we compare two fuzzy logic systems (FLS) -type-1 fuzzy logic system (T1FLS) and adaptive network-based fuzzy inference system (ANFIS) to extract fuzzy parameters of soil. Moreover, two machine learning (ML) algorithms - random forest (RF) and artificial neural network (ANN) with principal component analysis (PCA) are applied in the SM classifications. 9 types of UWB soil echoes of different texture and volume water content (VWC) are collected and investigated using our approaches. Final analysis shows that ANFIS with RF provides the best VWC correct recognition rate (CRR) compared to other algorithms.
26 August 2008 in IEEE Transactions on Vehicular Technology
In this paper, we present two practical algorithms for selecting a subset of channels in virtual multiple-input-multiple-output (MIMO) wireless sensor networks (WSNs) to balance the MIMO advantage consumption of sensor cooperation. If intracluster node-to-node multihop needs be taken into account, the maximum spanning tree searching (MASTS) algorithm, with respect to the cross-layer design, always provides a path connecting all sensors. When the WSN is organized in a manner of cluster-to-cluster multihop, the singular-value decomposition-QR with threshold (SVD-QR-T) approach selects the best subset of transmitters while keeping all receivers active. The threshold is adaptive by means of fuzzy c-means (FCM). These two approaches are compared by simulation against the case without channel selection in terms of capacity, bit error rate (BER), and multiplexing gain with water filling or equal transmission power allocation. Despite less multiplexing gain, when water filling is applied, MASTS achieves higher capacity and lower BER than virtual MIMO without channel selection at moderate-to-high signal-to-noise ratio (SNR), whereas SVD-QR-T by FCM provides the lowest BER at high SNR; in the case of no water filling and equal transmission power allocation, MASTS still offers the highest capacity at moderate-to-high SNR, but SVD-QR-T by FCM achieves the lowest BER. Both algorithms provide satisfying performances with reduced resource consumption.
24 July 2023 in IEEE Transactions on Geoscience and Remote Sensing
Cognitive radar (CR) automatically improves itself via ceaseless interaction with the environment and learning from the experience. It continuously adjusts its waveform, parameters, and illuminates strategies based on obtained knowledge to achieve robust target tracking despite complex and changing scenarios. Waveform development for CR has attracted sustaining attention in promoting tracking performance. In this paper, we propose a novel framework of CR waveform selection for the tracking of high maneuvering targets in a cluttered environment with an interactive multi-model (IMM) probabilistic data association (PDA) algorithm. Based on this framework, criterion-based optimization (CBO) and entropy-rewarded Q-learning (ERQL) methods are designed to perform waveform selection, which is divided into pure parameters selection and joint selection of waveforms and parameters. This method integrates the radar target into a closed loop and realizes the real-time update of the transmitted waveform with the change of the target state, to achieve the best tracking performance of the target. The simulations performed on radar target tracking have demonstrated that the proposed ERQL method outperforms the existing method in both time complexity and tracking accuracy. Furthermore, field experiments have confirmed that the ERQL method is more effective in target tracking than the existing method.
1 August 2010 in Pattern Recognition Letters