Deep learning (DL) has been widely applied to forecast the sales volume of household appliances with high accuracy. Unfortunately, in small towns, due to the limited amount of historical sales data, it is difficult to forecast household appliance sales accurately. To overcome the above-mentioned challenge, we propose a novel household appliance sales forecasting algorithm based on transfer learning, temporal convolutional network (TCN), long short-term memory (LSTM), and attention mechanism (called “TransTLA”). Firstly, we combine TCN and LSTM to exploit the spatiotemporal correlation of sales data. Secondly, we utilize the attention mechanism to make full use of the features of sales data. Finally, in order to mitigate the impact of data scarcity and regional differences, a transfer learning technique is used to improve the predictive performance in small towns, with the help of the learning experience from the megacity. The experimental outcomes reveal that the proposed TransTLA model significantly outperforms traditional forecasting methods in predicting small town household appliance sales volumes. Specifically, TransTLA achieves an average mean absolute error (MAE) improvement of 27.60% over LSTM, 9.23% over convolutional neural networks (CNN), and 11.00% over the CNN-LSTM-Attention model across one to four step-ahead predictions. This study addresses the data scarcity problem in small town sales forecasting, helping businesses improve inventory management, enhance customer satisfaction, and contribute to a more efficient supply chain, benefiting the overall economy.
17 March 2023 in IEEE Transactions on Vehicular Technology
In cognitive radios (CR), compressive spectrum sensing (CSS) is a promising technique to detect wideband spectrum holes with reduced sampling rate requirement of analog-to-digital converter (ADC). It is implied in compressive sensing (CS) that the minimum sampling rate is determined by the sparsity order of the observed wideband signal. Unfortunately, the sparsity order is previously unknown and dynamically varies. Meanwhile, CS technology fails to work efficiently for the nonsparse spectrum case. For example, the CSS performance degenerates significantly for low signal-to-noise ratio (SNR) scenarios since the observed signal becomes nonsparse in frequency domain. To overcome the above-mentioned challenges, we propose a novel CSS algorithm with temporally-correlated prior knowledge mining (TPKM-CSS) to detect spectrum holes without a prior sparsity order information. The proposed scheme can handle both the sparse and nonsparse spectrum cases. The proposed solution has three contributions: firstly, CR implements multiple parallel sampling simultaneously to acquire wireless spectrum signals, which have a low-rank spectrum matrix. Secondly, the temporal correlation between continuous CS data is further exploited to improve the estimation accuracy of the current spectrum. Finally, the theoretical performance of the proposed TPKM-CSS is evaluated, wherein the cumulative distribution function (CDF) of the spectrum reconstruction error is derived in the closed form. The simulation results show that the proposed scheme works well for both sparse and nonsparse spectrum scenarios. Compared with the CSS schemes that are based on low-rank matrix recovery (LMR-CSS), maximizing correlation (MC), iterative compressive filtering (ICF), or Bayesian CS (BCS), the proposed scheme yields the superior performance in terms of the probability of detection and the probability of false alarm, especially for nonsparse signals. Furthermore, the simulated statistical performance of the spectrum reconstruction error matches well the theoretical CDF curve.
27 May 2025 in IEEE Transactions on Wireless Communications
Adaptive compressive spectrum sensing (ACSS) plays a vital role in cognitive radio networks due to its reduced sampling rate and power consumption. Most of the existing ACSS schemes focus on the improvement of spectrum sensing performance, but do not provide the deterministic assurance of sensing results. Hence, we propose an ACSS based on deterministic estimation model (ACSS-DEM) to provide the confidence level of the reconstructed signals. This is realized by deriving the closed-form expression of the cumulative distribution function (CDF) of reconstructed errors. Firstly, in each sensing interval of ACSS, we propose a novel signal reconstruction algorithm that incorporates the prior knowledge into ℓ2,1-norm minimization of block-sparse signals. Secondly, a prior knowledge refining strategy is designed through convex geometry theory to further improve the reconstruction accuracy. Finally, the CDF of reconstruction error is derived and regarded as a stopping criteria for observation sample collection. The experiment results demonstrate that the proposed ACSS-DEM delivers optimal spectrum-sensing performance, offering over a 12.2% improvement in detection performance at a false alarm probability of 0.1, compared with other typical ACSS methods, e.g., ACSS-JL, ACSS-SOC, and ACSS-CV.
12 July 2023 in IEEE Transactions on Wireless Communications
Compressive spectrum sensing (CSS) is regarded as one of the promising techniques to detect wideband spectrum holes. How to formulate an accurate prior knowledge in CSS is still an important and open topic. In this paper, we propose a novel CSS algorithm with cascade forward-backward propagation and prior knowledge refining. Firstly, the wideband signal reconstruction model is formulated as a ℓ p -norm (0 < p < 1) nonconvex optimization problem where the temporal correlation between continuous observed spectrum signals is exploited to improve the reconstruction accuracy of the current spectrum signal, and such nonconvex optimization problem is solved by iteratively reweighted least squares algorithm. Then, the multiple reconstructed versions of the current spectrum signal obtained by forward-backward propagation are fused into a prior. Finally, such fused prior is modified adaptively in each iteration, and thus significantly improves the accuracy of spectrum decision and speeds up the convergence. The simulation results show that compared with other CSS schemes based on weighted ℓ 1 minimization, ℓ 1 -ℓ 1 minimization, ℓ 1 -ℓ 2 minimization, and maximizing correlation, the proposed scheme has more than 7% and 10% detection performance improvement when the probability of false alarm is 10%, under received signal-to-noise ratio as -10 dB and -5 dB, respectively.
Ray tracing (RT) has become an important method for train-to-ground (T2G) wireless channel modeling due to its physical interpretability. In rail transit scenarios, RT suffers from modeling errors that arise due to environmental reconstruction and uncertainties in electromagnetic parameters, as well as dynamic phase errors caused by coherent multi-path superposition that is further triggered by such modeling errors. Phase errors significantly affect both the calibration accuracy and prediction precision of RT. Therefore, this paper proposes an intelligent RT calibration method based on local phase errors. The method builds a phase error distribution model and uses constraints from limited measurements to explicitly estimate and correct phase errors in RT-generated channel responses. Firstly, the method applies the Variational Expectation–Maximization (VEM) algorithm to optimize the phase error model, where the expectation step derives an approximate posterior distribution and the maximization step updates parameters conditioned on this posterior. Secondly, experiments are conducted using differentiable RT implemented in the Sionna library, which explicitly provides gradients of environmental and link parameters with respect to channel frequency responses, enabling end-to-end calibration. Finally, experimental results show that in railway scenarios, compared with calibration methods based on phase error-oblivious and uniform phase error, the proposed approach achieves average gains of about 10 dB at SNR = 0 dB and 20 dB at SNR = 30 dB.
1 August 2025 in IEEE Transactions on Vehicular Technology