Industrial Internet of Things (IIoT) provides significant support for observing and controlling industrial machinery. In this paper, a novel hierarchical feature enhancement network (HFEN) is proposed by combining signal processing and representation learning. The signal processing is based on frequency and time frequency analysis, which extracts features with definite physical significance, whereas representation learning improves the representability of the physical features by connecting stacked denoising autoencoders and squeeze-and-excitation networks. A novel two-stream architecture is designed for HFEN to fuse two types of features. Consequently, HFEN can extract features that can be analyzed for physical significance and that are also representative in terms of recognizable patterns. The experimental results prove that the performance of HFEN is satisfactory in terms of accuracy and efficiency when compared to other methods. Finally, this study also aims to demonstrate the potential of a new pairing that fuses the model- and data-driven strategies for IIoT.

The traditional Low Energy Adaptive Cluster Hierarchy (LEACH) routing protocol is a clustering-based protocol. The uneven selection of cluster heads results in premature death of cluster heads and premature blind nodes inside the clusters, thus reducing the overall lifetime of the network. With a full consideration of information on energy and distance distribution of neighboring nodes inside the clusters, this paper proposes a new routing algorithm based on differential evolution (DE) to improve the LEACH routing protocol. To meet the requirements of monitoring applications in outdoor environments such as the meteorological, hydrological and wetland ecological environments, the proposed algorithm uses the simple and fast search features of DE to optimize the multi-objective selection of cluster heads and prevent blind nodes for improved energy efficiency and system stability. Simulation results show that the proposed new LEACH routing algorithm has better performance, effectively extends the working lifetime of the system, and improves the quality of the wireless sensor networks.

Depth estimation is a fundamental issue in computational stereo. To obtain accurate stereo depth estimation, all mechanical parameters with a high precision need to be measured in order to achieve subpixel accuracy and to match features between two different images. This paper investigates accurate depth estimation with different mechanical parameter errors, such as camera calibration and alignment errors, which mainly result from camera lens distortion, camera translation, rotation, pitch, and yaw. For each source of the errors, a model for the error description is presented, and the accurate depth estimation due to this error is quantitatively analyzed. Depth estimation algorithms under an individual error, and with all the errors, are given. Experimental results show that the proposed models can rectify the errors and calculate the accurate depths effectively.