Person tracking in hazardous goods factories can provide a significant improvement in security and safety. This article proposes a face verification model which can be used to record travel paths for staff or related persons in the factory. As face images are captured from the dynamic crowd at entrance–exit gates of workshops, face verification is challenged by polymorphic faces, poor illumination and changing of a person’s pose. To adapt to this situation, a new face verification model is proposed, which is composed of two advanced deep learning neural network models. Firstly, MTCNN (Multi-Task Cascaded Convolutional Neural Network) is used to construct a face detector. Based on the SphereFace-20 network model, we have reconstructed a convolutional network architecture with the embedded Batch Normalization elements and the optimized network parameters. The new model, which is called the MDCNN, is used to extract efficient face features. A set of specific processing algorithms is used in the model to process polymorphic face images. The multi-view faces and various types of face images are used to train the models. The experimental results have demonstrated that the proposed model outperforms most existing methods on benchmark datasets such as the Labeled Faces in the Wild (LFW) and YouTube Face (YTF) datasets without multi-view (accuracy is 99.38% and 94.30%, respectively) and the CNBC/FERET datasets with multi-view (accuracy is 94.69%).

This paper proposes a novel multivariate performance diagnostic approach for the Oracle database systems to detect performance degradation and crashes during database operations and maintenance. It was based on three technologies: image encoding, image concatenation, and deep convolutional network. Instantaneous variation and magnitude information of the time series were acquired by Heatmap and Recurrence Plot (RP) from databases. Moreover, the Heatmap and RP were concatenated in order to fully extract complementary information. Finally, the concatenated images of Heatmap and RP were used to train the VGG16 model for database performance diagnosis. The quantitative analysis demonstrated a good increment of accuracy in Heatmap and RP based on the same deep learning networks compared with other image encodings of Gramian Angular Difference Field (GADF), Gramian Angular Summation Fields (GASF), and Markov Transition Fields (MTF). Meanwhile, concatenated images of Heatmap and RP can improve the accuracy by 1% compared to single Heatmap input. The result of the trained model applied to multivariate database diagnosis shows an accuracy of 95.3%. Thus, our method can more effectively and accurately diagnose the performance of the Oracle database systems.

The cost of software testing is a significant aspect of the software development life cycle, typically accounting for half of the total software production cost. Due to the large number of tests, it is impractical to perform a complete test of a system under test. Combinatorial testing is employed to identify errors that arise from the interaction among subsystems, with covering arrays being the most crucial type of combinatorial testing. Covering arrays consider parameter combinations using the t-way strategy. The goal is to reduce the number of test cases while ensuring adequate coverage. Fewer test cases result in greater efficiency, and less time spent generating the test suite leads to more effective testing. Various solutions have been proposed, with metaheuristic algorithms playing a vital role. Furthermore, solutions have been developed to automatically generate parameters and their corresponding values by utilizing a model of the system under test. In this paper, our objective is to employ model-based solutions for the automatic generation of a covering array. Specifically, we integrate the GROOVE model checker with a combination of Biogeography-Based Optimization (BBO) and Genetic Algorithm (GA) to enhance the efficiency and accuracy of the test suite generation. The GROOVE model checker extracts parameters and their values, which are then optimized by the BBO and GA algorithms to generate a minimal and effective test suite. The evaluation results show that our proposed solution outperforms existing algorithms, achieving higher efficiency and accuracy in test generation. This research highlights the novel integration of GROOVE with BBO and GA, contributing to the advancement of combinatorial testing techniques.

Frequency-modulated continuous-wave (FMCW) light detection and ranging (LiDAR) has become increasingly significant for long-distance ranging fields. However, the beat signal is vulnerable to noise interference during detection, resulting in a low signal-to-noise ratio (SNR) and inaccurate ranging results. Although traditional methods have improved accuracy through various denoising and spectral analysis algorithms, they often struggle to maintain robust performance in long-range scenarios under low-SNR conditions. To address this challenge, this paper proposes the HOIGL, a hybrid frequency estimation algorithm which integrates Orthogonal Matching Pursuit (OMP) for initial value guidance and Gray Wolf Optimization (GWO) for local search. Specifically, by leveraging the frequency-domain sparsity of the signal, OMP performs piecewise sparse representation to yield a coarse initial frequency, within which GWO conducts a refined continuous local search to overcome dictionary discretization bias based on a custom fitness function. Monte Carlo simulations in MATLAB demonstrate that the proposed algorithm achieves an RMSE of 2.63 m compared to over 84.34 m for other methods at −20 dB SNR, while maintaining a low and stable processing time of around 0.498 s. Finally, fiber-optic-link experimental results verify the performance of HOIGL for hundred-meter-scale range detection.

Today most commercial DNA sequencing systems' signal detection was based on CCD or PMT. The CCD based system needs cooled CCD, whose cost is high and the sensitivity is relatively low. The PMT based system using mechanical scanning to realize multi-channel detection, whose stability is relatively low and the working noise is high. In this paper, a novel multi-channel DNA sequencing system was presented, which was based on single PMT confocal fluorescence detection and optical scanning adopting an f-theta lens. Capillary electrophoresis experiments were executed in the system for DNA marker pBR322/Hae III. The system's limit of detection was evaluated to be 1.1841times10-11 mol/L (dsDNA with Thiazole Orange). Its working noise is much lower compared with that based on mechanical scanning one, and the stability and detecting sensitivity is high. The system is expected to be applied to both capillary array and microchip electrophoresis detection based on laser-induced fluorescence.

We demonstrate a nonlinear Mach-Zehnder interferometer (MZI) designed for direct characterization of infrared (IR) optical vortices. By interfering an IR signal vortex with a dynamically phase-modulated reference beam, the MZI maps IR vortex modes into visible second-harmonic generation (SHG) interference patterns. Distinct from linear interferometers, the nonlinear characteristic of our MZI provides an inherent contrast enhancement, where the quadratic intensity response effectively sharpens the petal structures to improve fringe visibility significantly. These petal-like interference patterns allow for the simultaneous retrieval of the topological charge (TC) magnitude and sign, which are determined directly from the number of petals and rotation direction, respectively. By leveraging the high sensitivity of standard visible-light CMOS sensors, our scheme provides an efficient platform for IR vortex metrology and OAM-based optical communications.