A novel dynamic inverse control method based on a dynamical neural network (DNN) is proposed for the trajectory tracking control of a flexible air-breathing hypersonic vehicle (FAHV). Firstly, considering that the accurate model of FAHV is difficult to obtain, the FAHV is regarded as a completely unknown system, and a DNN is designed to identify its nonlinear model. On the basis of Lyapunov’s second law, the weight vectors of the DNN are adaptively updated. Then, a dynamic inverse controller is designed based on the identification model, which avoids the transformation of the nonlinear model of FAHV, thereby simplifying the controller design process. The simulation results verify that the DNN can identify FAHV accurately, and velocity and altitude can track the given reference signal accurately with the proposed dynamic inverse control method. Compared with the back-stepping control method, the proposed method has better tracking accuracy, and the amplitude of the initial control law is smaller. Full article

The known amplitude-sensitive eddy-current method for measuring the thickness of non-conductive coatings on conductive non-magnetic base metals does not satisfy the accuracy requirements. A primary consideration is the significant influence of a change in the specific electrical conductivity of the base metals on results of measurements. In this study, we developed a technique for measuring the thickness of non-conductive coatings on non-magnetic conductive base metals by using the eddy-current amplitude-phase method and implemented algorithms to process obtained information. Our method considered the influence of the specific electrical conductivity of the base metals by forming a two-dimensional graduation characteristic of the thickness gauge by using several base metals with different specific electrical conductivity. The algorithm for point-in-polygon determination was applied, which allowed us to measure the thickness of the coatings and the specific electrical conductivity of the base metals as independent values. The equipment necessary to construct the two-dimensional graduation characteristic and the algorithm for calculation of the thickness are described in detail. Full article

Eliminating the magnetic interference of the carrier platform is an important technical link and plays a vital role in aeromagnetic survey. The traditional compensation method is based on the Tolles–Lawson (T-L) model and establishes the linear relationship between the aircraft interference magnetic field and the aircraft attitude. The compensation coefficients are solved by designing the calibration flight. At present, almost all aeromagnetic systems use the fluxgate magnetometer fixed to the aircraft to realize the attitude measurement of the flight platform. However, the fluxgate magnetometer has problems, such as non-orthogonal error, zero drift error, and linearity error limited by the production process, and the fluxgate magnetometer is also very susceptible to external magnetic interference as a magnetic sensor. These lead to the aircraft attitude calculated by the fluxgate magnetometer being inaccurate, thus reducing the compensation effect. In this article, we analyze the influence of the fluxgate magnetometer noise on compensation and propose a new conjunctive compensation method based on inertial navigation systems (INS) and fluxgate magnetometer information to improve the compensation effect. The flight experiment data show that the proposed method can significantly improve the quality of aeromagnetic data. Compared with the traditional compensation method only based on fluxgate magnetometer information, the improved ratio is increased by 30–60%, and it is a real-time compensation method. It shows that the proposed method has a remarkable compensation effect for aeromagnetic interference. Full article

In this work, deep learning (DL)-based transmit antenna selection (TAS) strategies are employed to enhance the average bit error rate (ABER) and energy efficiency (EE) performance of a spectrally efficient fully generalized spatial modulation (FGSM) scheme. The Euclidean distance-based antenna selection (EDAS), a frequently employed TAS technique, has a high search complexity but offers optimal ABER performance. To address TAS with minimal complexity, we present DL-based approaches that reframe the traditional TAS problem as a classification learning problem. To reduce the energy consumption and latency of the system, we presented three DL architectures in this study, namely a feed-forward neural network (FNN), a recurrent neural network (RNN), and a 1D convolutional neural network (CNN). The proposed system can efficiently process and make predictions based on the new data with minimal latency, as DL-based modeling is a one-time procedure. In addition, the performance of the proposed DL strategies is compared to two other popular machine learning methods: support vector machine (SVM) and K-nearest neighbor (KNN). While comparing DL architectures with SVM on the same dataset, it is seen that the proposed FNN architecture offers a ~3.15% accuracy boost. The proposed FNN architecture achieves an improved signal-to-noise ratio (SNR) gain of ~2.2 dB over FGSM without TAS (FGSM-WTAS). All proposed DL techniques outperform FGSM-WTAS. Full article

Stone columns have been extensively advocated as a traditional approach to increase the undrained bearing capacity and reduce the settlement of footings sitting on cohesive ground. However, due to the complex interaction between the soil and the stone columns, there currently needs to be a commonly acknowledged approach that can be used to precisely predict the undrained bearing capacity of the system. For this reason, the bearing capacity of a sandy bed reinforced with geogrid and sitting above a collection of geogrid-encased stone columns floating in soft clay was studied in this research. Using a white-box machine learning (ML) technique called Multivariate Polynomial Regression (MPR), this work aims to develop a model for predicting the bearing capacity of the referred foundation system. For this purpose, two hundred and forty-five experimental results were collected from the literature. In addition, the model was compared to two other ML models, namely, a black-box model known as Random Forest (RF) and a white-box ML model called Linear Regression (LR). In terms of R² (coefficient of determination) and RMSE (Root Mean Absolute Error) values, the newly proposed model outperforms the two other referred models and demonstrates robust estimation capabilities. In addition, a parametric analysis was carried out to determine the contribution of each input variable and its relative significance on the output. Full article

To investigate the plastic deformation (PD) response of a liner material during the shaped-charge jet (SCJ) formation process, the state of motion of liner material and the pattern of change in its deformation environment under explosive loading were theoretically analyzed and modeled. The distribution patterns of the characteristic PD parameters (that is, strain, strain rate, temperature, and flow stress) of the jet at any given time were theoretically predicted. The distribution patterns of the characteristic PD parameters of jets formed from two materials, namely, oxygen-free high-thermal-conductivity copper (OFHC-Cu) and molybdenum (Mo), during their formation process were theoretically analyzed. A series of experimental and numerical simulation studies were conducted to examine the accuracy of the theoretical predictions. As per the results, the developed theoretical model is effective in predicting the one-dimensional distribution of the characteristic PD parameters in the direction of jet formation. At any given time, the distribution of the characteristic PD parameters varies considerably between different parts of the jet. There is no significant difference in the distribution of the strain and strain rate between the jets formed from the two materials in the presence of the same warhead structure. A theoretical analysis predicted average temperatures of 804 and 2277.8 K and average flow stresses of 193.1 and 344.3 MPa for the OFHC-Cu and Mo jets, respectively. A hardness analysis of the jet fragments revealed average strengths of 144.32 and 286.66 MPa for the OFHC-Cu and Mo jets during their formation process, respectively. These results differed by 34% and 20% from the corresponding theoretical predictions. Full article

Fringe projection profilometry is one of the most widely used three-dimensional measurement techniques at present, in which phase is the key factor for the accuracy of dimensional measurements. Jumping errors may occur due to improper handling of truncation points in phase unwrapping. Meanwhile, projective dual-frequency grating has the shortcomings of a narrow measurement range and coarse projection fringe due to the requirements of an overlapping grid. To address the above problems, this paper puts forward an improved multi-frequency heterodyne phase unwrapping approach. Firstly, the phase principal values of three frequencies are obtained by the standard four-step phase-shifting approach, and two wrapped phases with lower frequencies are obtained through the dual-frequency heterodyne phase unwrapping approach. Then, the decimal part of the fringe order is again calculated using the dual-frequency heterodyne principle, and the actual value of the current decimal part is calculated from the phase principal values of the grating fringe corresponding to the fringe order. Then, a threshold is set according to the error of the phase principal value itself, and the differences between this threshold and the above calculated and theoretical values are compared. Finally, the absolute phase is corrected by adjusting the number of cycles according to the judgment results. Experiments show that the improved approach can achieve a correction rate of more than 96.8% for the jumping errors that occur in phase unwrapping, and it is also highly resistant to noise in the face of different noises. Furthermore, the approach can measure the three-dimensional morphology of objects with different surface morphologies, indicating the certain universality of the approach. Full article

Acute alcoholic liver injury is an important health problem worldwide. Apples are rich in many nutrients and have a variety of biological activities, including antioxidant, anti-inflammatory, and anti-tumor, and therefore have the potential to be a natural protective agent against acute alcoholic liver injury. This study evaluated the protective effect of apples (Malus pumila Mill) on acute alcoholic liver injury in rats. Male Wistar rats were randomly assigned to four groups: a control group (C), a control group that was fed fresh apples (CA), an ethanol-treated group (E), and an ethanol-treated group that was fed fresh apples (EA). Rats were treated with continuous forced gavage with 40° ethanol (4 mL/kg) for one week to simulate human alcoholism. Liver injury was assessed based on changes in the serum levels of alanine aminotransferase (ALT) and aspartate aminotransferase (AST), as well as histological analysis. The protective effect of apples on alcoholic liver injury was assessed in terms of alcohol metabolism, oxidative stress, inflammation, lipid synthesis, and tissue fibrosis. The results showed that apple consumption protected against alcoholic liver injury, as indicated by the decreased serum ALT and AST levels, reduced liver lipid peroxidation, and improved liver histopathology. Moreover, apple consumption increased antioxidant enzyme activity and reduced inflammatory cytokine levels in the liver. These findings suggest that apple consumption may have a protective effect against acute ethanol-induced liver injury in rats, possibly through its antioxidant and anti-inflammatory properties. Full article

We perform a stochastic sensitivity analysis of the experimental setup of a mock circulatory loop for in vitro hemodynamics analysis in the ascending thoracic aorta at a patient-specific level. The novelty of the work is that, for the first time, we provide a systematic sensitivity analysis of the effect of the inflow conditions, viz. the stroke volume, the cardiac cycle period, and the spatial distribution of the velocity in in-vitro experiments in a circulatory mock loop. We considered three different patient-specific geometries of the ascending thoracic aorta, viz. a healthy geometry, an aortic aneurysm, and a coarctation of the aorta. Three-dimensional-printed phantoms are inserted in a mock circulatory loop, and velocity and pressure measurements are carried out for the different setup conditions. The stochastic approach, performed using the generalized polynomial chaos, allows us to obtain continuous and accurate response surfaces in the parameter space, limiting the number of experiments. The main contributions of this work are that (i) the flow rate and pressure waveforms are mostly affected by the cardiac cycle period and the stroke volume, (ii) the impact of the spatial distribution of the inlet velocity profile is negligible, and (iii), from a practical viewpoint, this analysis confirms that in experiments it is also important to replicate the patient-specific inflow waveform, while the length of the pipe connecting the pump and the phantom of the aorta can be varied to comply with particular requirements as, for instance, those implied by the use of MRI in experiments. Full article

Deep neural networks have achieved remarkable performance in various fields such as image recognition and natural language processing. However, recent research has revealed that even a small imperceptible perturbation can confound well-trained neural network models and yield incorrect answers. Such adversarial examples are regarded as a key hazard to the application of machine learning techniques to safety-critical systems, such as unmanned vehicle navigation and security systems. In this study, we propose an efficient technique for searching one-pixel attacks in deep neural networks, which are recently reported as an adversarial example. Using exhaustive search, our method can identify one-pixel attacks which existing methods cannot detect. Moreover, the method can adjust exhaustiveness to reduce the search space dramatically. However, it still identifies most attacks. We present our experiment using the MNIST data set to demonstrate that our adjustable search method efficiently identifies one-pixel attacks in well-trained deep neural networks, including convolutional layers. Full article

Deep learning effectively identifies and predicts modes but faces performance reduction under few-shot learning conditions. In this paper, a time series prediction framework for small samples is proposed, including a data augmentation algorithm, time series trend decomposition, multi-model prediction, and error-based fusion. First, data samples are augmented by retaining and extracting time series features. Second, the expanded data are decomposed based on data trends, and then, multiple deep models are used for prediction. Third, the models’ predictive outputs are combined with an error estimate from the intersection of covariances. Finally, the method is verified using natural systems and classic small-scale simulation datasets. The results show that the proposed method can improve the prediction accuracy of small sample sets with data augmentation and multi-model fusion. Full article

Scalable lab-scale photobioreactors are needed for the exploration of new and improved photoautotrophic bioprocesses. Microbioreactor systems in which parallel bioreactors operate automatically are frequently employed to increase the speed of strain selection as well as the bioprocess-based exploration of heterotrophic fermentation processes. To enable the photoautotrophic operation of a commercially available parallel microbioreactor system with 48 stirred-tank bioreactors, LED illumination modules were designed to allow for individual light supply (400–700 nm) for each of the parallel bioreactors automated by a liquid handling station that performs both individual pH control and OD₇₅₀ detection. The illumination modules enable dynamic variation of the incident light intensities of up to 1800 µmol m⁻² s⁻¹. Automated liquid level detection and volume control of each individual mL-scale gassed photobioreactor has to be established to compensate for evaporation because of the long process times of several days up to weeks. Photoautotrophic batch processes with Microchloropsis salina that employ either varying constant incident light intensities or day and night dynamics resulted in a standard deviation of OD₇₅₀ of up to a maximum of 10%, with the exception of high-photoinhibiting incident light intensities. The established photoautotrophic microbioreactor system enables the automated investigation of microalgae processes in up to 48 parallel stirred photobioreactors and is thus a new tool that enables efficient characterization and development of photoautotrophic processes with microalgae. Full article

Most existing approaches to image classification neglect the concept of semantics, resulting in two major shortcomings. Firstly, categories are treated as independent even when they have a strong semantic overlap. Secondly, the features used to classify images into different categories can be the same. It has been demonstrated that the integration of ontologies and semantic relationships greatly improves image classification accuracy. In this study, a hybrid ontological bagging algorithm and an ensemble technique of convolutional neural network (CNN) models have been developed to improve forest image classification accuracy. The ontological bagging approach learns discriminative weak attributes over multiple learning instances, and the bagging concept is adopted to minimize the error propagation of the classifiers. An ensemble of ResNet50, VGG16, and Xception models is used to generate a set of features for the classifiers trained through an ontology to perform the image classification process. To the authors’ best knowledge, there are no publicly available datasets for forest-type images; hence, the images used in this study were obtained from the internet. Obtained images were put into eight categories, namely: orchards, bare land, grassland, woodland, sea, buildings, shrubs, and logged forest. Each category comprised 100 images for training and 19 images for testing; thus, in total, the dataset contained 800 images for training and 152 images for testing. Our ensemble deep learning approach with an ontology model was successfully used to classify forest images into their respective categories. The classification was based on the semantic relationship between image categories. The experimental results show that our proposed model with ontology outperformed other baseline classifiers without ontology with 96% accuracy and the lowest root-mean-square error (RMSE) of 0.532 compared to 88.8%, 86.2%, 81.6%, 64.5%, and 63.8% accuracy and 1.048, 1.094, 1.530, 1.678, and 2.090 RMSE for support-vector machines, random forest, k-nearest neighbours, Gaussian naive Bayes, and decision trees, respectively. Full article

The Industrial Internet of Things (IIoT) accelerates smart manufacturing and boosts production efficiency through heterogeneous industrial equipment, intelligent sensors, and actuators. The Industrial Internet of Things is transforming from a traditional factory model to a new manufacturing mode, which allows cross-domain data-sharing among multiple system departments to enable smart manufacturing. A complete industrial product comes from the combined efforts of many different departments. Therefore, secure and reliable cross-domain access control has become the key to ensuring the security of cross-domain communication and resource-sharing. Traditional centralized access control schemes are prone to single-point failure problems. Recently, many researchers have integrated blockchain technology into access control models. However, most blockchain-based approaches use a single-chain structure, which has weak data management capability and scalability, while ensuring system security, and low access control efficiency, making it difficult to meet the needs of multi-domain cooperation in IIoT scenarios. Therefore, this paper proposes a decentralized cross-domain access model based on a master–slave chain with high scalability. Moreover, the model ensures the security and reliability of the master chain through a reputation-based node selection mechanism. Access control efficiency is improved by a grouping strategy retrieval method in the access control process. The experimental benchmarks of the proposed scheme use various performance metrics to highlight its applicability in the IIoT environment. The results show an 82% improvement in the throughput for the master–slave chain structure over the single-chain structure. There is also an improvement in the throughput and latency compared to the results of other studies. Full article

South African agriculture accounts for 62% of the national water demand. Almost 45% of the water is wasted. Therefore, irrigation systems need to improve their water-use efficiency (WUE). However, the WUE of smallholder irrigation schemes in the country, including Agri-Parks, is not precisely known. A study was performed at four Agri-Parks (Rooiwal, Soshanguve, Tarlton, and Westonaria) in Gauteng province to assess the condition and performance of the irrigation systems, as part of a project that aimed to develop a WUE model for smallholder irrigation systems. The Agri-Parks were equipped with efficient irrigation systems in forms of drip and microjets. The assessments were performed at the system component level in February–March 2021. A Condition Assessment Model (CAM), developed by ARC-NRE/AE, was used for the condition assessment. Enumerators observed the system components visually and assigned conditions, which they uploaded into the model to generate condition indices (CIs). Water conveyance efficiency (CE) and distribution uniformity (DU) were assessed on delivery and infield systems, respectively. The CI values ranged 4–6, implying significant deterioration had occurred. The CE was 61–78%, while the DU was 60–95%. The infield system CI correlated positively with the DU, suggesting the CI could predict the DU in drip systems, which was encouraging for the proposed WUE model. However, further research covering a longer period and more Agri-Parks is recommended. Full article