This paper presents novel machine-learning-based methods for estimating the state of charge (SoC) of lithium-ion batteries, which use the Gaussian process regression (GPR) framework. The measured battery parameters, such as voltage, current, and temperature, are used as inputs for regular GPR, whereas the SoC estimate at the previous sample is fed back and incorporated into the input vector for recurrent GPR. The proposed methods consist of two parts. In the first part, training is performed wherein the optimal hyperparameters of a chosen kernel function are determined to model data properties. In the second part, online SoC estimation is carried out according to the trained model. One of the practical advantages of a GPR framework is to quantify estimation uncertainty and, hence, to enable reliability assessment of the battery SoC estimate. The performance of the proposed methods is evaluated by using a simulated dataset and two experimental datasets, one with constant and the other with dynamic charge and discharge currents. The simulations and experimental results show the superiority of the proposed methods in comparison to state-of-the-art techniques including a support vector machine, a relevance vector machine, and a neural network.

The increasing deployment of battery storage applications in both grid storage and electric vehicle fields is generating a vast used battery market. These batteries are typically recycled but could be reused in second-life applications. One of the challenges is to obtain an accurate remaining useful life (RUL) estimation algorithm, which determines whether a battery is suitable for reuse and estimates the number of second-life cycles the battery will last. In this article, the RUL estimation problem is considered. We propose several health indicators (HIs), some of which have not been explored before, along with simple yet effective estimation and classification algorithms. These algorithms include classification techniques such as regularized logistic regression (RLR), and regression techniques such as multivariable linear regression (MLR) and multilayer perceptron (MLP). As a more advanced solution, a multiple expert system combining said techniques is proposed. The performance of the algorithms and features is evaluated on a recent lithium iron phosphate (LFP) data set from Toyota Research Institute. We obtain satisfactory results in the estimation of RUL cycles with errors down to 49 root mean square error (RMSE) cycles for cells that live up to 1200 cycles, and 0.24% mean relative error (MRE) for the prediction of the evolution of capacity.

The minimum power distortionless response (MPDR) beamformer minimizes the output power while passing the look direction signal with unity gain. To alleviate the performance degradation caused by estimating the spatial correlation matrix with a relatively small number of snapshots of the received signal compared to the number of sensors, a regularization implemented via diagonal loading of the estimated correlation matrix is used. This paper presents a study for the optimal diagonal loading that minimizes the estimation mean square error (MSE) of two diagonally loaded MPDR beamformer-based spatial power estimators in the snapshot deficient regime. First, the asymptotic behavior of the power estimators for fixed diagonal loading is analyzed and the approximate characterization of their expectations is derived. Second, it is conjectured that because of the snapshot deficient sample support, the squared bias is the factor that primarily controls the optimal diagonal loading. Finally, the respective performances of the two power estimators are compared using MSE as the metric and it is shown that one outperforms the other. The analytical results are validated using simulation data.

In this paper, we investigate the detection problem for a massive machine-type communication (mMTC) system that has correlated user activities. Two deep learning assisted algorithms are proposed to exploit the user activity correlation to facilitate channel estimation and user identification. Due to the dependency among user activities, conventional element-wise minimum mean square error (MMSE) denoiser used in the orthogonal approximate message passing (OAMP) algorithm cannot achieve satisfying performance during the two-step iterative process. Therefore, we propose a deep learning modified OAMP (DL-mOAMP) algorithm, which iteratively modifies the user activity ratio via exploiting the user activity correlation in the MMSE denoiser based on the estimated sequence during each OAMP iteration. Moreover, given a specific false alarm probability, a constant threshold employed in the conventional user identification is not optimal in the presence of user activity correlation. Thus, we propose a neural network framework that is dedicated to the user identification (DL-mOAMP-UI algorithm), which minimizes the missed detection probability under a pre-determined false alarm probability. Numerical results show that the proposed DL-mOAMP algorithm provides a substantial mean squared error performance gain compared to the conventional OAMP algorithm and the DL-mOAMP-UI algorithm can further improve the user identification accuracy of an mMTC system.

We present a method for separating collided signals from multiple users in the presence of strong and wideband interference/jamming signal. More specifically, we consider a massive connectivity setup where few, out of a large number of users, equipped with spreading codes, synchronously transmit symbols. The received signal is a noisy mixture of symbols transmitted through users' flat fading channels, impaired by fast frequency hopping jamming signal of relatively large power. In the absence of any conventional technique suitable for the considered setup, we propose a "model-driven" deep learning method, based on convolution neural network, to suppress jamming signal from the received signal, and detect active users together with their transmitted symbols. A numerical study of the proposed method confirms its effectiveness in scenarios where classical techniques fail. As such, in a two user scenario with wideband jamming signal of power $20$ dB above the power any active user, the proposed algorithm achieves error rates $10^{-2}$ for a wide range of AWGN variances.

One of the most essential prerequisites behind a successful task execution of a team of agents is to accurately estimate and track their poses. We consider a cooperative multi-agent positioning problem where each agent performs single-agent positioning until it encounters some other agent. Upon the encounter, the two agents measure their relative pose, and exchange particle clouds representing their poses. We propose a cooperative positioning algorithm which fuses the received information with the locally available measurements and infers an agent's pose within Bayesian framework. The algorithm is scalable to multiple agents, has relatively low computational complexity, admits decentralized implementation across agents, and imposes relatively mild requirements on communication coverage and bandwidth. The experiments indicate that the proposed algorithm considerably improves single-agent positioning accuracy, reduces the convergence time of a particle cloud and, unlike its single-agent positioning counterpart, exhibits immunity to an impeding feature-scarce and symmetric environment layout.