A particle filter (PF) has been introduced for effective position estimation of moving targets for non-Gaussian and nonlinear systems. The time difference of arrival (TDOA) method using acoustic sensor array has normally been used to for estimation by concealing the location of a moving target, especially underwater. In this paper, we propose a GPU -based acceleration of target position estimation using a PF and propose an efficient system and software architecture. The proposed graphic processing unit (GPU)-based algorithm has more advantages in applying PF signal processing to a target system, which consists of large-scale Internet of Things (IoT)-driven sensors because of the parallelization which is scalable. For the TDOA measurement from the acoustic sensor array, we use the generalized cross correlation phase transform (GCC-PHAT) method to obtain the correlation coefficient of the signal using Fast Fourier Transform (FFT), and we try to accelerate the calculations of GCC-PHAT based TDOA measurements using FFT with GPU compute unified device architecture (CUDA). The proposed approach utilizes a parallelization method in the target position estimation algorithm using GPU-based PF processing. In addition, it could efficiently estimate sudden movement change of the target using GPU-based parallel computing which also can be used for multiple target tracking. It also provides scalability in extending the detection algorithm according to the increase of the number of sensors. Therefore, the proposed architecture can be applied in IoT sensing applications with a large number of sensors. The target estimation algorithm was verified using MATLAB and implemented using GPU CUDA. We implemented the proposed signal processing acceleration system using target GPU to analyze in terms of execution time. The execution time of the algorithm is reduced by 55% from to the CPU standalone operation in target embedded board, NVIDIA Jetson TX1. Also, to apply large-scaled IoT sensing applications, we use NVIDIA Tesla K40c as target GPU. The execution time of the proposed multi-state-space model-based algorithm is similar to the one-state-space model algorithm because of GPU-based parallel computing. Experimental results show that the proposed architecture is a feasible solution in terms of high-performance and area-efficient architecture.

Moving-Target Position Estimation Using GPU-Based Particle Filter for IoT Sensing Applications

For proper diagnosis, location of the wireless video capsule endoscope is required to be known by the physicians. In this paper, we propose an algorithm of localizing the capsule using path loss-based calibrated weighted centroid localization (CWCL). The main challenge in path loss-based localization is the highly randomness of measured path loss due to shadow fading and multi-path propagation effects of human body channel. To address the randomness in the measured path loss, we propose two methods of path loss estimation using Gaussian weighted average filter and the multiple input multiple output diversity scheme. Then, we calculate the weight of the sensor receiver position using the estimated path loss. Finally, the position of the capsule is estimated using position-bounded CWCL. We propose a realistic suboptimal method of estimating the calibration coefficient and also compute the optimal value of coefficient to set the benchmark. Additionally, we propose two boundary conditions on the estimated positions to improve the localization accuracy. We simulate our proposed algorithms using MATLAB to validate the accuracy and observe significant improvements without any prior knowledge of channel parameters. The proposed algorithms improve the accuracy up to 5.14-mm root mean square error and outperform the existing literature.

Non-Parametric Approach of Video Capsule Endoscope Localization Using Suboptimal Method of Position Bounded CWCL

Wireless video capsule endoscope (VCE) is used to diagnose intestinal abnormalities. The physicians need to know the exact location of the images sent by the VCE for proper diagnosis and treatment of abnormalities. In this paper, we propose path loss bounded weighted centroid localization (PB-WCL) algorithm to estimate 3-D coordinate position of the VCE. The main challenge in VCE localization is the tissue characteristics of human body and the signal attenuation due to the complex non-homogeneous environment. The path loss suffers from high randomness due to the shadow fading and multi-path propagation effects caused by non-homogeneous tissues. To address the highly random scattered path loss issue, we propose maximum likelihood estimated path loss by using the received RF signal packets transmitted from randomly distributed neighboring positions of the VCE. Then we propose path loss bounded weight of the reference positions of sensor receivers which is not dependent on any channel parameters or unknown prior. Finally, we estimate the position of VCE using PB-WCL and apply two boundary conditions on the estimated positions to improve the accuracy. We develop a simulation platform using MATLAB to present and validate the results. We observe that our proposed position bounded PB-WCL shows significantly improved performance and outperforms the existing literature.

Non-Parametric Approach Using ML Estimated Path Loss Bounded WCL for Video Capsule Endoscope Localization

A wireless capsule endoscope (WCE) is a promising medical device for diagnosis of digestive organs, which takes pictures inside digestive organs, such as large and small intestines and transmits them through implant wireless communications. In a realistic WCE scenario, it is important to precisely estimate the WCE location. Generally, the superiority of TOA-based localization over RSSI-based localization has been pointed out in many papers in wireless communication systems. However, because the propagation speed inside of a human body varies due to the influence of its biological tissues (namely, the relative permittivity of human tissues), the realization of precise TOA-based localization needs to accurately estimate the propagation velocity of implant communication signals. So, in this paper, we propose a TOA-based method for joint location/relative permittivity estimation, and then compare the performances between TOA- and RSSI-based WCE location estimation methods. Our computer simulation results reveal that, the TOA-based localization with accurate relative permittivity information outperforms the RSSI-based localization in terms of the localization accuracy, whereas the RSSI-based localization is advantageous if accurate relative permittivity is not obtained. Additionally, the proposed TOA-based localization can achieve not only better localization accuracy than that of the RSSI-based localization but also accurate averaged relative permittivity estimation.

Performance comparison between TOA- and RSSI-based localization methods for wireless capsule endoscopy systems

Localization is a fundamental task in many swarm robotic applications, such as foraging and exploration. Magnetic induction communications, which rely on the magnetic component of an antenna's near-field, have gathered interest as means to perform localization in underground and underwater environments. MI signals propagate through lossy environments better than traditional RF signals, and can offer advantages over acoustics. In prior work, we developed a localization method based on MI signals to calculate the range between two moving MI antennas. A core aspect of the method is a particle filter that relies on the received signal strength and speed of the antennas to produce location estimates. In this paper, we first empirically find the amount of noise present in our signal strength measurements in underwater environments. Then we propose a model to capture the impact of the noise on the range calculations and apply it to improve the particle filter's location estimations.

Underwater Robot Localization Using Magnetic Induction: Noise Modeling and Hardware Validation

Multipath propagation and reverberation of underwater acoustic signal affect the accuracy of localization estimation based on time difference of arrival (TDOA). To solve the problem, a novel algorithm is proposed to improve the accuracy of localization estimation of underwater acoustic source. Based on the signals received at an array of sensors, a general framework for acoustic source localization using particle filtering is proposed. A generic particle filtering framework was derived. The simulation results demonstrate the superiority of the proposed method. The resulting particle filter is shown to outperform traditional acoustic source localization method.

Underwater acoustic source localization method based on TDOA with particle filtering

A gas outburst prediction model based on multiple strategy fusion and improved snake optimization algorithm (MFISO) and temporal convolutional network (TCN) is proposed to address the problems of low accuracy of deep learning prediction models for gas outburst in underground mines. By adopting the phase space reconstruction method, the time series of multiple complex influencing factors related to gas outburst were reconstructed and used as model inputs. Sine chaos mapping, spiral search strategy and snake dynamic adaptive weight are introduced to improve the snake optimization algorithm (SO), which enhances the local optimal escape capability and global search capability of the algorithm. The tangent-based rectified linear unit (ThLU) was used to improve the rectified linear unit (ReLU) of the standard TCN to strengthen the generalization capability of the model. The MFISO algorithm was used to optimize the relevant hyperparameters of the improved TCN model to optimize the accuracy of gas outburst prediction. The TCN, GRU, LSTM, SO-TCN, WOA-TCN, and PSO-TCN prediction models were selected to compare the prediction performance with the MFISO-TCN gas outburst prediction model, and the results showed that the mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE) of the MFISO-TCN model were 3.11%, 0.47% and 3.31% are lower than those of other models, which verifies that the method of this paper effectively intensifies the performance of gas outburst prediction model in underground mines.

https://ieeexplore.ieee.org/ielx7/6287639/6514899/09943531.pdf

Research on Gas Outburst Prediction Model Based on Multiple Strategy Fusion Improved Snake Optimization Algorithm With Temporal Convolutional Network

The bidirectional gated recurrent unit (BiGRU) method based on dissolved gas analysis (DGA) has been studied in the field of power transformer fault diagnosis. However, there are still some shortcomings such as the fuzzy boundaries of DGA data, and the BiGRU parameters are difficult to determine. Therefore, this paper proposes a power transformer fault diagnosis method based on landmark isometric mapping (L-Isomap) and Improved Sand Cat Swarm Optimization (ISCSO) to optimize the BiGRU (ISCSO-BiGRU). Firstly, L-Isomap is used to extract features from DGA feature quantities. In addition, ISCSO is further proposed to optimize the BiGRU parameters to build an optimal diagnosis model based on BiGRU. For the ISCSO, four improvement methods are proposed. The traditional sand cat swarm algorithm is improved using logistic chaotic mapping, the water wave dynamic factor, adaptive weighting, and the golden sine strategy. Then, benchmarking functions are used to test the optimization performance of ISCSO and the four algorithms, and the results show that ISCSO has the best optimization accuracy and convergence speed. Finally, the fault diagnosis method based on L-Isomap and ISCSO-BiGRU is obtained. Using the model for fault diagnosis, the example simulation results show that using L-ISOMP to filter and downscale the model inputs can better improve model performance. The results are compared with the SCSO-BiGRU, WOA-BiGRU, GWO-BiGRU, and PSO-BiGRU fault diagnosis models. The results show that the fault diagnosis rate of ISCSO-BiGRU is 94.8%, which is 11.69%, 10.39%, 7.14%, and 5.9% higher than that of PSO-BiGRU, GWO-BiGRU, WOA-BiGRU, and SCSO-BiGRU, respectively, and validate that the proposed method can effectively improve the fault diagnosis performance of transformers.

/pdf/a-power-transformer-fault-diagnosis-method-based-on-improved-134ygglr.pdf

A Power Transformer Fault Diagnosis Method Based on Improved Sand Cat Swarm Optimization Algorithm and Bidirectional Gated Recurrent Unit

Research on transformer fault diagnosis based on ISOMAP and IChOA‐LSSVM

In this study, the GA-CNN model is proposed to realize the automatic recognition of rolling bearing running state. Firstly, to avoid the over-fitting and gradient dispersion in the training process of the CNN model, the BN layer and Dropout technology are introduced into the LeNet-5 model. Secondly, to obtain the automatic selection of hyperparameters in CNN model, a method of hyperparameter selection combined with genetic algorithm (GA) is proposed. In the proposed method, each hyperparameter is encoded as a chromosome, and each hyperparameter has a mapping relationship with the corresponding gene position on the chromosome. After the process of chromosome selection, crossover and variation, the fitness value is calculated to present the superiority of the current chromosome. The chromosomes with high fitness values are more likely to be selected in the next genetic iteration, that is, the optimal hyperparameters of the CNN model are obtained. Then, vibration signals from CWRU are used for the time-frequency analysis, and the obtained time-frequency image set is used to train and test the proposed GA-CNN model, and the accuracy of the proposed model can reach 99.85% on average, and the training speed is four times faster than the model LeNet-5. Finally, the result of the experiment on the laboratory test platform The experimental results confirm the superiority of the method and the transplantability of the optimization model.

https://journals.sagepub.com/doi/pdf/10.1177/16878132221095635

Yaosong Xu

Papers

Underwater acoustic source localization method based on TDOA with particle filtering

Research on Gas Outburst Prediction Model Based on Multiple Strategy Fusion Improved Snake Optimization Algorithm With Temporal Convolutional Network

A Power Transformer Fault Diagnosis Method Based on Improved Sand Cat Swarm Optimization Algorithm and Bidirectional Gated Recurrent Unit

Research on transformer fault diagnosis based on ISOMAP and IChOA‐LSSVM

Recognition of rolling bearing running state based on genetic algorithm and convolutional neural network