Electric load forecasting (ELF) is vitally beneficial for electrical power planning and economical running in smart grid. However, the medium-term load forecasting has been rarely studied. In addition, existing ELF models mainly consider the impact of limited external factors, which are usually difficult to forecast accurately. In this paper, the characteristics of the electric loads are analyzed and used as a guideline for the design of the proposed methods. To fully exploit the quasi-periodicity with different time ranges, i.e., year, quarter, month, and week, two deep learning methods, time-dependency convolutional neural network (TD-CNN), and cycle-based long short-term memory (C-LSTM) network are proposed to improve the forecasting performance of short-term load forecasting and MTLF with a little payload of computational complexity. Both of them only utilize the historical electric load and can mine the underlying load patterns by extracting the long-term global integrated features and short-term local similar features. By representing the loads as pixels and rearranging them into a 2-D photograph, TD-CNN transforms the temporal correlation of load series into the spatial correlation and keeps the long-term memory. Specifically, the convolutional kernel with special size targeted to load data is designed to extract the local pattern with similar characteristic, while the pooling layer is removed in order to keep the finer features. Moreover, in order to extract the temporal correlation between the long-term sequences with lower complexity, the proposed C-LSTM method generates a new short series from the original long load series without information loss. The LSTM is then applied to model the dynamical relationship of the load series with shorter time steps. The experimental results show that the proposed methods outperform the existing method with greatly reduced computation complexity, whose training time is about two-to-five times shorter than the existing method.

Extracting roads from high-resolution remote sensing images (HRSIs) is vital in a wide variety of applications, such as autonomous driving, path planning, and road navigation. Due to the long and thin shape as well as the shades induced by vegetation and buildings, small-sized roads are more difficult to discern. In order to improve the reliability and accuracy of small-sized road extraction when roads of multiple sizes coexist in an HRSI, an enhanced deep neural network model termed dual-decoder-U-net (DDU-Net) is proposed in this article. Motivated by the U-Net model, a small decoder is added to form a dual-decoder structure for more detailed features. In addition, we introduce the dilated convolution attention module (DCAM) between the encoder and decoders to increase the receptive field as well as to distill multiscale features through cascading dilated convolution and global average pooling. The convolutional block attention module (CBAM) is also embedded in the parallel dilated convolution and pooling branches to capture more attention-aware features. Extensive experiments are conducted on the Massachusetts Roads dataset with experimental results showing that the proposed model outperforms the state-of-the-art DenseUNet, DeepLabv3+, and D-LinkNet by 6.5%, 3.3%, and 2.1% in the mean intersection over union (mIoU), and by 4%, 4.8%, and 3.1% in the F1 score, respectively. Both ablation and heatmap analysis are presented to validate the effectiveness of the proposed model. Moreover, the designed small decoder and introduced DCAM can be used as a portable module to be embedded in other U-Net-like models with encoder–decoder structure to enhance the road detection performance, especially for small-sized roads. The high portability of the designed module is validated by embedding it in the LinkNet, which greatly improves the road segmentation performance.

Landslide is one of the most dangerous and frequently occurred natural disasters. The semantic segmentation technique is efficient for wide area landslide identification from high-resolution remote sensing images (HRSIs). However, considerable challenges exist because the effects of sediments, vegetation and human activities over long periods of time make visually blurred old landslides very challenging to detect based upon HRSIs. Moreover, terrain features like slopes, aspect and altitude variations cannot be sufficiently extracted from 2D HRSIs but from digital elevation model (DEM) data. Then, a feature-fusion based segmentation network (FFS-Net) is proposed, which can extract texture and shape features from 2D HRSIs and terrain features from DEM data before fusing these two distinct types of features in a higher feature layer. In order to segment landslides from background, a multi-scale channel attention module is purposely designed to balance the low-level fine information and high-level semantic features. In the decoder, transposed convolution layer replaces original mathematical bilinear interpolation to better restore image resolution via learnable convolutional kernels, and both dropout and batch normalization are introduced to prevent over-fitting and accelerate the network convergence. Experimental results are presented to validate that the proposed FFS-Net can greatly improve the segmentation accuracy of visually blurred old landslides. Compared to U-Net and DeepLabV3+, FFS-Net can improve the mIoU metric from 0.508, 0.624 to 0.67, the F1 metric from 0.254, 0.516 to 0.596, and the PA metric from 0.874, 0.906 to 0.92, respectively. For the detection of visually distinct landslides, FFS-NET also offers comparable detection performance, and the segmentation is improved for visually distinct landslides with similar color and texture to surroundings.

One of the fundamental problems in cryptography is the generation of a common secret key between two legitimate parties to prevent eavesdropping. In this paper, we propose an information-theoretic secret key generation (SKG) method for time division duplexing (TDD)-based orthogonal frequency-division multiplexing (OFDM) systems over multipath fading channels. By exploring physical layer properties of the wireless medium, i.e., the reciprocity, randomness, and privacy features of the radio channel, an SKG method is proposed to maximize the number of secret bits given a target secret key disagreement ratio (SKDR). In the proposed SKG method, the phase information of the estimated channel state information (CSI) is distilled for SKG, and a special guard band (GB) scheme is designed to achieve the target SKDR with a small phase information loss. The proposed GB consists of both the amplitude GB (AGB) and phase GB (PGB), where the AGB is determined by the average signal-to-interference plus noise ratio (SINR), whereas the PGB adapts itself to the instantaneous SINR and thus incurs a smaller phase information loss in the higher SINR region. Analyses show that this GB scheme trades off a small loss of channel phase information for a better SKDR performance, and achieves a much larger number of quantization levels for a given SKDR due to the fact that the PGB decreases quickly as the SINR increases. Based on the performance analysis on the SKDR, the average secret key length, the phase information loss percentage (PILP), and the optimal GB and quantization level of the adaptive quantizor are derived for a given target SKDR. Both analytical and simulation results are presented to demonstrate the superiority of the proposed scheme for TDD-OFDM systems over frequency-selective fading channels.

In this letter, we focus on the efficient channel estimation problem for millimeter wave (MMW) systems with massive antenna arrays and RF constraints, aiming at achieving a fast and high resolution angle-of-arrival/angle-of-departure (AoA/AoD) estimation. We first propose a presentation of antenna array with virtual elements (AAVE) by appending additional virtual antenna elements into the original antenna array. On the basis of the AAVE structure, we explore the channel sparsity in the angular domain and develop an efficient angle estimation algorithm by using compressive sensing theories. We then proposed a training design and prove that the sensing matrix in the proposed training can guarantee the accurate detection of angles with a high probability. Both the analytical and simulation results show that, without changing the physical antenna arrays, the proposed approach can achieve not only a lower overhead, but also a significantly higher resolution in angles estimation, compared to the existing algorithms.

The geological characteristics of old landslides can provide crucial information for the task of landslide protection. However, detecting old landslides from high-resolution remote sensing images (HRSIs) is of great challenges due to their partially or strongly transformed morphology over a long time and thus the limited difference with their surroundings. Additionally, small-sized datasets can restrict in-depth learning. To address these challenges, this paper proposes a new iterative classification and semantic segmentation network (ICSSN), which can significantly improve both object-level and pixel-level classification performance by iteratively upgrading the feature extraction module shared by the object classification and semantic segmentation networks. To improve the detection performance on small-sized datasets, object-level contrastive learning is employed in the object classification network featuring a siamese network to realize global features extraction, and a sub-object-level contrastive learning method is designed in the semantic segmentation network to efficiently extract salient features from boundaries of landslides. An iterative training strategy is also proposed to fuse features in the semantic space, further improving both the object-level and pixel-level classification performances. The proposed ICSSN is evaluated on a real-world landslide dataset, and experimental results show that it greatly improves both the classification and segmentation accuracy of old landslides. For the semantic segmentation task, compared to the baseline, the F1 score increases from 0.5054 to 0.5448, the mIoU improves from 0.6405 to 0.6610, the landslide IoU grows from 0.3381 to 0.3743, the PA is improved from 0.945 to 0.949, and the object-level detection accuracy of old landslides surges from 0.55 to 0.90. For the object classification task, the F1 score increases from 0.8846 to 0.9230, and the accuracy score is up from 0.8375 to 0.8875.