The wireless sensor network (WSN) profoundly impacts the routing technology of the Internet of Things, which has received tremendous attention in terms of energy cost, Quality of Service (QoS) and security. In this way, it is particularly significant to find a multihop path with low-energy consumption, delay, delay jitter, packet loss rate and high bandwidth, credibility in WSN. However, the existing energy-efficient secure QoS routing problem has been proven to be an NP-hard that forces a tradeoff between energy cost, communication quality and security. To address this problem, a new energy-efficient secure QoS routing model is designed, which precisely replicates the communication scenario of WSN and comprehensively considers energy cost, latency, delay jitter, bandwidth, credibility, and packet loss rate. Subsequently, a novel energy-efficient secure QoS routing algorithm based on elite niche clonal evolutionary computing (ESQRA-ENCEC) is proposed, which includes three novel operators named niche selection, clone operator and elite optimization. These operators are designed to significantly increase the quality of solutions, vigorously develop convergence speed and successfully avoid local optima. The suggested algorithm not only considerably lowers energy consumption, delay, delay jitter, and packet loss rate but also effectively increases bandwidth and credibility. The simulation of ESQRA-ENCEC is performed in different scenarios. Experiment results reveal that the ESQRA-ENCEC has improved by 5.21% and 11.26% in energy cost, 5.31% and 7.94% in bandwidth, 6.44% and 10.80% in delay, 5.85% and 12.79% in delay jitter, 8.58% and 14.39% in packet loss rate, and 8.03% and 15.58% in credibility compared with two existing algorithms, respectively.

In recent years, achievements of deep learning in face recognition have exceeded those of traditional machine learning methods do. To achieve better recognition performance, the architectures of the neural network tend to be deeper and more complex, which wastes the time and space. Aiming at this issue, a series of light convolutional neural network (Light CNN) has been proposed, which consume less hardware resources while has excellent performance. In this paper, we propose a Normalized Light CNN model modified from a Light CNN model. We introduced a normalized layer to this model in both training and test phase. The normalized layer normalizes the output features, making it represent images better. We evaluate our model on LFW dataset. The accuracy of face verification reaches 98.46%, which is better than the original model.

Maximizing longevity and improving the communication quality of wireless sensor networks (WSNs) are two pivotal objectives in addressing clustering routing issues. However, existing methods suffer from low Quality of Service (QoS), and accumulating unnecessary monitoring data results in a reduced network lifetime. In this regard, a new multi-objective quantum adaptive grey wolf optimization-based energy-efficient clustering routing (MQAGWO-EECR) algorithm is proposed, which vigorously prolongs the network lifetime, and considerably reduces delay and packet loss rate. Two novel operators named quantum calculation and adaptive adjustment are devised in conjunction with grey wolf optimization, which significantly enhances solution quality, and obviously improves convergence rate. Additionally, a new energy-efficient clustering routing model involves sleep scheduling, cluster head (CH) selection, and multi-hop routing, which accurately captures the data transmission process. To be specific, sleep scheduling alternates nodes between active and sleep modes to reduce unnecessary energy usage. Moreover, clustering routing is designed by concurrently considering energy cost, node density, the distance between CH nodes and the base station, delay, and packet loss rate, ensuring CH selection is rational and significantly guaranteeing QoS performance. Experimental results demonstrate that the proposed MQAGWO-EECR effectively optimizes energy efficiency and further extends network longevity by at least 11.09% compared to EM-LEACH, KSA-DEEC, and GAPHO-H. Additionally, it decreases transmission delay by at least 5.27% and reduces packet loss rate by at least 4.84% compared to the other three algorithms.

The learning-based hashing has recently made encouraging progress in face recognition. However, most existing hashing methods disregard the discrete constraint during optimization, inducing the accumulated quantization errors. In this work, we develop an effective learning-based hashing model, namely local feature hashing with binary auto-encoder (LFH-BAE), to directly learn local binary descriptors in the Hamming space. It attempts to exploit structure factors to well reconstruct the face image from binary codes. Specifically, we first introduce a binary auto-encoder to learn a hashing function to project each face region into high-quality binary codes. Since the original problem is a tricky combinational function, we then present a softened version to decompose it into separate tractable sub-problems. Next, we propose an effective alternating algorithm based on the augmented Lagrange method (ALM) to solve these sub-problems, which helps to generate strong discriminative and excellent robust binary codes. Moreover, we utilize the discrete cyclic coordinate descent (DCC) method to optimize binary codes to reduce the loss of useful information. Lastly, we cluster and pool the obtained binary codes, and construct a histogram feature as the final face representation for each image. Extensive experimental results on four public datasets including FERET, CAS-PEAL-R1, LFW and PaSC show that our LFH-BAE is superior to most state-of-the-art face recognition algorithms.

As more and more surveillance cameras are deployed in the Internet of Things, it takes more and more work to ensure the cameras are not occluded. An algorithm of detecting whether the surveillance camera is occluded is proposed by comparing the similarity of the images in this paper. Firstly, the background modeling method based on frame difference is improved. The combination method of the background difference and frame difference is proposed, and the experimental results showed that the combination algorithm can extract the background image of the video more quickly and accurately. Secondly, the LBP (Local Binary Patterns) algorithm is used to compare the similarity between the background image and the reference image. By changing the window size of the LBP algorithm and setting an appropriate threshold, the actual demands can be satisfied. So, the algorithms proposed in this paper have high application value and practical significance.