Vehicle State Estimation Combining Physics-Informed Neural Network and Unscented Kalman Filtering on Manifolds.

This paper proposes a novel vehicle state estimation (VSE) method that combines a physics-informed neural network (PINN) and an unscented Kalman filter on manifolds (UKF-M). This VSE aimed to achieve inertial measurement unit (IMU) calibration and provide comprehensive information on the vehicle's dynamic state. The proposed method leverages a PINN to eliminate IMU drift by constraining the loss function with ordinary differential equations (ODEs). Then, the UKF-M is used to estimate the 3D attitude, velocity, and position of the vehicle more accurately using a six-degrees-of-freedom vehicle model. Experimental results demonstrate that the proposed PINN method can learn from multiple sensors and reduce the impact of sensor biases by constraining the ODEs without affecting the sensor characteristics. Compared to the UKF-M algorithm alone, our VSE can better estimate vehicle states. The proposed method has the potential to automatically reduce the impact of sensor drift during vehicle operation, making it more suitable for real-world applications.

A sustainable and economic strategy to reduce risk antibiotic resistance genes during poultry manure bioconversion by black soldier fly Hermetia illucens larvae: Larval density adjustment.

Black soldier fly (Hermetia illucens) larvae (BSFL) are common insects that are known for bioconversion of organic waste into a sustainable utilization resource. However, a strategy to increase antibiotic resistance gene (ARG) elimination in sustainable and economic ways through BSFL is lacking. In the present study, different larval densities were employed to assess the mcr-1 and tetX elimination abilities, and potential mechanisms were investigated. The application and economic value of each larval density were also analyzed. The results showed that the 100 larvae cultured in 100 g of manure group had the best density because the comprehensive disadvantage evaluation ratio was the lowest (14.97%, good bioconversion manure quality, low ARG deposition risk and reasonable larvae input cost). Further investigation showed that mcr-1 could be significantly decreased by BSFL bioconversion (4.42 ×107 copies/g reduced to 4.79 ×106-2.14 ×105 copies/g)(P＜0.05); however, mcr-1 was increasingly deposited in the larval gut with increasing larval density. The tetX abundance was stabilized by BSFL bioconversion, except that the abundance at the lowest larval density increased (1.22 ×1010 copies/g increase, 34-fold). Escherichia was the host of mcr-1 and tetX in all samples, especially in fresh manure; Alcaligenes was the host of tetX in bioconversion manure; and the abundance of Alcaligenes was highly correlated with the pH of bioconversion manure. The pH of bioconversion manure was extremely correlated with the density of larvae. Klebsiella and Providencia were both hosts of tetX in the BSF larval gut, and Providencia was also the host of mcr-1 in the BSF larval gut. The density of larvae influenced the bioconversion manure quality and caused the ARG host abundance to change to control the abundance of ARGs, suggesting that larval density adjustment was a useful strategy to manage the ARG risk during BSFL manure bioconversion.

The relationship between culturable doxycycline-resistant bacterial communities and antibiotic resistance gene hosts in pig farm wastewater treatment plants.

Pig farm wastewater treatment plants (WWTPs) are an important repository for resistant bacterial communities (RBCs) and antibiotic resistance genes (ARGs). However, the relationship between RBCs and ARG hosts has not been well characterized. In this study, water samples from influent and effluent from five pig farm WWTPs were collected. Gradient concentrations of doxycycline (DOX) were used to screen the culturable RBCs. The abundance of 21 subtypes of ARGs and the bacterial community were investigated. This study detected a large number of culturable DOX-RBCs and ARGs in the influent and effluent of pig farm WWTPs. The abundances of ARGs and RBCs in all effluent samples was significantly lower than that in the influent samples (P < 0.05), which indicated that the WWTPs can effectively remove most ARGs and RBCs in pig farm wastewater. The main potential culturable RBCs in pig farm wastewater were the dominant bacteria Proteobacteria, Actinobacteria, Pseudomonas, and Rheinheimera. However, most of the ARGs were mainly present in Bacteroidetes, Actinobacteria, Corynebacteriaceae, Macellibacteroides, Acinetobacter, and Enterobacteriaceae, which are considered potential ARG hosts. The results presented here showed that there were obvious differences between the species of culturable DOX-RBCs and ARG hosts in the pig farm WWTPs, which may be due to various environmental factors. This highlights the urgent need for further research on the relationship between RBCs and ARG hosts.

Lyophobic slippery surfaces on smooth/hierarchical structured substrates and investigations of their dynamic liquid repellency.

Slippery surfaces were prepared by infusing lubricant into smooth or hierarchical-structured superhydrophobic surfaces (SHS) to compare different surface-free energies. The surfaces obtained showed good repellency towards liquids with various values of surface tension/molecular polarity/viscosity, including hexane, tetradecane, water, ethylene glycol and viscous engine oil. The lyophobicity could be realized on a relatively smooth surface, indicating that the first principle of preparing a lyophobic slippery surface is to perform a low surface-free energy modification. The dynamic liquid repellency was also studied: the sliding speeds of different liquids on lubricant infused SHS showed a negative correlation to their kinematic viscosity values, and a higher surface roughness was favorable for dynamic wettability, whereas for the smooth slippery surface, the travelling speeds showed randomness.

Vehicle Detection by Fusing Part Model Learning and Semantic Scene Information for Complex Urban Surveillance.

Visual-based vehicle detection has been studied extensively, however there are great challenges in certain settings. To solve this problem, this paper proposes a probabilistic framework combining a scene model with a pattern recognition method for vehicle detection by a stationary camera. A semisupervised viewpoint inference method is proposed in which five viewpoints are defined. For a specific monitoring scene, the vehicle motion pattern corresponding to road structures is obtained by using trajectory clustering through an offline procedure. Then, the possible vehicle location and the probability distribution around the viewpoint in a fixed location are calculated. For each viewpoint, the vehicle model described by a deformable part model (DPM) and a conditional random field (CRF) is learned. Scores of root and parts and their spatial configuration generated by the DPM are used to learn the CRF model. The occlusion states of vehicles are defined based on the visibility of their parts and considered as latent variables in the CRF. In the online procedure, the output of the CRF, which is considered as an adjusted vehicle detection result compared with the DPM, is combined with the probability of the apparent viewpoint in a location to give the final vehicle detection result. Quantitative experiments under a variety of traffic conditions have been contrasted to test our method. The experimental results illustrate that our method performs well and is able to deal with various vehicle viewpoints and shapes effectively. In particular, our approach performs well in complex traffic conditions with vehicle occlusion.

Kernel Sparse Representation with Hybrid Regularization for On-Road Traffic Sensor Data Imputation.

The problem of missing values (MVs) in traffic sensor data analysis is universal in current intelligent transportation systems because of various reasons, such as sensor malfunction, transmission failure, etc. Accurate imputation of MVs is the foundation of subsequent data analysis tasks since most analysis algorithms need complete data as input. In this work, a novel MVs imputation approach termed as kernel sparse representation with elastic net regularization (KSR-EN) is developed for reconstructing MVs to facilitate analysis with traffic sensor data. The idea is to represent each sample as a linear combination of other samples due to inherent spatiotemporal correlation, as well as periodicity of daily traffic flow. To discover few yet correlated samples and make full use of the valuable information, a combination of l1-norm and l2-norm is employed to penalize the combination coefficients. Moreover, the linear representation among samples is extended to nonlinear representation by mapping input data space into high-dimensional feature space, which further enhances the recovery performance of our proposed approach. An efficient iterative algorithm is developed for solving KSR-EN model. The proposed method is verified on both an artificially simulated dataset and a public road network traffic sensor data. The results demonstrate the effectiveness of the proposed approach in terms of MVs imputation.

A Vehicle Recognition Algorithm Based on Deep Transfer Learning with a Multiple Feature Subspace Distribution.

Vehicle detection is a key component of environmental sensing systems for Intelligent Vehicles (IVs). The traditional shallow model and offline learning-based vehicle detection method are not able to satisfy the real-world challenges of environmental complexity and scene dynamics. Focusing on these problems, this work proposes a vehicle detection algorithm based on a multiple feature subspace distribution deep model with online transfer learning. Based on the multiple feature subspace distribution hypothesis, a deep model is established in which multiple Restricted Boltzmann Machines (RBMs) construct the lower layers and a Deep Belief Network (DBN) composes the superstructure. For this deep model, an unsupervised feature extraction method is applied, which is based on sparse constraints. Then, a transfer learning method with online sample generation is proposed based on the deep model. Finally, the entire classifier is retrained online with supervised learning. The experiment is actuated using the KITTI road image datasets. The performance of the proposed method is compared with many state-of-the-art methods and it is demonstrated that the proposed deep transfer learning-based algorithm outperformed existing state-of-the-art methods.

Estimation of Longitudinal Force and Sideslip Angle for Intelligent Four-Wheel Independent Drive Electric Vehicles by Observer Iteration and Information Fusion.

Exact estimation of longitudinal force and sideslip angle is important for lateral stability and path-following control of four-wheel independent driven electric vehicle. This paper presents an effective method for longitudinal force and sideslip angle estimation by observer iteration and information fusion for four-wheel independent drive electric vehicles. The electric driving wheel model is introduced into the vehicle modeling process and used for longitudinal force estimation, the longitudinal force reconstruction equation is obtained via model decoupling, the a Luenberger observer and high-order sliding mode observer are united for longitudinal force observer design, and the Kalman filter is applied to restrain the influence of noise. Via the estimated longitudinal force, an estimation strategy is then proposed based on observer iteration and information fusion, in which the Luenberger observer is applied to achieve the transcendental estimation utilizing less sensor measurements, the extended Kalman filter is used for a posteriori estimation with higher accuracy, and a fuzzy weight controller is used to enhance the adaptive ability of observer system. Simulations and experiments are carried out, and the effectiveness of proposed estimation method is verified.

A vehicle detection algorithm based on deep belief network.

Vision based vehicle detection is a critical technology that plays an important role in not only vehicle active safety but also road video surveillance application. Traditional shallow model based vehicle detection algorithm still cannot meet the requirement of accurate vehicle detection in these applications. In this work, a novel deep learning based vehicle detection algorithm with 2D deep belief network (2D-DBN) is proposed. In the algorithm, the proposed 2D-DBN architecture uses second-order planes instead of first-order vector as input and uses bilinear projection for retaining discriminative information so as to determine the size of the deep architecture which enhances the success rate of vehicle detection. On-road experimental results demonstrate that the algorithm performs better than state-of-the-art vehicle detection algorithm in testing data sets.

MixedFusion: An Efficient Multimodal Data Fusion Framework for 3-D Object Detection and Tracking.

The performance of environmental perception is critical for the safe driving of intelligent connected vehicles (ICVs). Currently, the most prevalent technical solutions are based on multimodal data fusion to achieve a comprehensive perception of the surrounding environment. However, existing fusion perception methods suffer from issues such as low sensor data utilization and unreasonable fusion strategies, which severely limit their performance in adverse weather conditions. To address these issues, this article proposes a novel multimodal data fusion framework called MixedFusion. In this framework, we introduce two innovative fusion strategies for the data characteristics of each sensor: high-level semantic guidance (HLSG) and multipriority matching (MPM). It not only realizes the efficient utilization of the multimodal data but also further realizes the complementary fusion between the multimodal data. We perform extensive experiments on the nuScenes and K-radar datasets. The experimental results demonstrate that the fusion framework proposed in this article significantly improves the performance of 3-D object detection and tracking in severe weather conditions.

DSC-based RBF neural network control for nonlinear time-delay systems with time-varying full state constraints.

The presented control scheme in this paper aims at stabilizing uncertain time-delayed systems requiring all states to change within the preset time-varying constraints. The controller design framework is based on the backstepping method, drastically simplified by the dynamic surface control technique. Meanwhile, the radius basis function neural networks are utilized to deal with the unknown items. To prevent all state variables from violating time-varying predefined regions, we employ the time-varying barrier Lyapunov functions during the backstepping procedure. Moreover, appropriate Lyapunov-Krasovskii functionals are used to cancel the influence of the time-delay terms on the system's stability. Under the presented control laws and Lyapunov analysis, it is proven that constraints on all state variables are not breached, good tracking performance of desired output is achieved, and all signals in the closed-loop systems are bounded. The effectiveness of our control scheme is confirmed by a simulation example.

Transmission of tetracycline resistance genes and microbiomes from manure-borne black soldier fly larvae frass to rhizosphere soil and pakchoi endophytes.

Manure treatment with black soldier fly larvae (BSFL) and BSFL frass application in crop land is a sustainable strategy; however, whether residual antibiotic resistance genes (ARGs) and their transmission risk are related to the manure BSFL treatment process is still unknown. In this paper, the effect of BSFL addition density on residual tetracycline resistance genes (TRGs) and transmission from frass to pakchoi was determined. The results showed that BSFL frass can provide sufficient nutrients for growth, improve the economic value of pakchoi, and reduce the risk of transmission of TRGs in chicken manure regardless of BSFL density. The potential hosts of the TRGs we detected were found in BSFL frass (Oblitimonas and Tissierella), rhizosphere soil (Mortierella and Fermentimonas), and pakchoi endophytes (Roseomonas). The present study concluded that BSFL frass produced by adding 100 BSFL per 100 g of chicken manure has the advantages of high value and low risk. These findings will provide important strategic guidance for animal manure disposal and theoretical support for preventing the transmission of TRGs in BSFL applications.

DLnet With Training Task Conversion Stream for Precise Semantic Segmentation in Actual Traffic Scene.

Many successful semantic segmentation models trained on certain datasets experience a performance gap when they are applied to the actual scene images, expressing weak robustness of these models in the actual scene. The training task conversion (TTC) and domain adaption field have been originally proposed to solve the performance gap problem. Unfortunately, many existing models for TTC and domain adaptation have defects, and even if the TTC is completed, the performance is far from the original task model. Thus, how to maintain excellent performance while completing TTC is the main challenge. In order to address this challenge, a deep learning model named DLnet is proposed for TTC from the existing image dataset-based training task to the actual scene image-based training task. The proposed network, named the DLnet, contains three main innovations. The proposed network is verified by experiments. The experimental results show that the proposed DLnet not only can achieve state-of-the-art quantitative performance on four popular datasets but also can obtain outstanding qualitative performance in four actual urban scenes, which demonstrates the robustness and performance of the proposed DLnet. In addition, although the proposed DLnet cannot achieve outstanding performance in real time, it can still achieve a moderate performance in real time, which is within an acceptable range.

Torsional oscillation-considered mode transition coordinated control for a power-split PHEV based on action dependent heuristic dynamic programming.

The mode transition process (MTP) from electric mode to hybrid electric mode (EM-to-HM) will cause the deterioration in occupant comfort of PHEV, to tickle this issue, a torsional oscillation-considered mode transition coordinated control strategy and a novel general evaluation index for MTP are developed in this research, the quality of mode transition and transient torsional oscillation of gears (TTOGs) during MTP are taken into consideration comprehensively. An action dependent heuristic dynamic programming algorithm which takes the vehicle jerk, friction loss and TTOGs as evaluation index is used to optimize the pressure curve of clutch oil and the compensation torque of motor in the entire EM-to-HM process. Finally, the simulation results and hardware-in-the-loop tests show that vehicle jerk and TTOGs are suppressed, and the driving comfort can be improved accordingly.

Multi-Target Pan-Class Intrinsic Relevance Driven Model for Improving Semantic Segmentation in Autonomous Driving.

At present, most semantic segmentation models rely on the excellent feature extraction capabilities of a deep learning network structure. Although these models can achieve excellent performance on multiple datasets, ways of refining the target main body segmentation and overcoming the performance limitation of deep learning networks are still a research focus. We discovered a pan-class intrinsic relevance phenomenon among targets that can link the targets cross-class. This cross-class strategy is different from the latest semantic segmentation model via context where targets are divided into an intra-class and inter-class. This paper proposes a model for refining the target main body segmentation using multi-target pan-class intrinsic relevance. The main contributions of the proposed model can be summarized as follows: a) The multi-target pan-class intrinsic relevance prior knowledge establishment (RPK-Est) module builds the prior knowledge of the intrinsic relevance to lay the foundation for the following extraction of the pan-class intrinsic relevance feature. b) The multi-target pan-class intrinsic relevance feature extraction (RF-Ext) module is designed to extract the pan-class intrinsic relevance feature based on the proposed multi-target node graph and graph convolution network. c) The multi-target pan-class intrinsic relevance feature integration (RF-Int) module is proposed to integrate the intrinsic relevance features and semantic features by a generative adversarial learning strategy at the gradient level, which can make intrinsic relevance features play a role in semantic segmentation. The proposed model achieved outstanding performance in semantic segmentation testing on four authoritative datasets compared to other state-of-the-art models.

Bacillus coagulans R11 consumption influenced the abundances of cecum antibiotic resistance genes in lead-exposed laying hens.

Bacillus coagulans is regarded as a clean, safe and helpful probiotic additive in the production of livestock and poultry breeds. Some studies have also shown that Bacillus coagulans can adsorb heavy metals in water, even in the gut of animals. However, whether Bacillus coagulans feeding influences antibiotic resistance gene (ARG) abundance in the gut of lead-exposed laying hens is unknown. To better apply such probiotics in the breeding industry, the present study employed Bacillus coagulans R11 and laying hens in model experiments to test ARG changes in the cecum of laying hens under lead exposure and B. coagulans R11 feeding. The results showed that there was the trend for ARG abundance decreasing in feeding B. coagulans R11 without lead exposure to laying hens in the cecum; however, feeding B. coagulans R11 to laying hens exposed to lead obviously increased the abundances of aminoglycoside and chloramphenicol ARGs. Further experiment found that hydroquinone, dodecanedioic acid, gibberellin A14, alpha-solanine, jasmonic acid and chitin were involved in the abundances of ARGs in the cecum, in addition the abundances of these compounds were also significantly enhanced by lead exposure or combination effects of lead and B. coagulans R11. As a result, the ARG hazards increased with feeding B. coagulans R11 to laying hens exposed to lead, and the key compounds which influenced by the combination effects of lead and B. coagulans R11 might influence the ARGs abundance.

Occurrence of microplastic in livestock and poultry manure in South China.

Microplastic (MP) contamination in soil has attracted much attention, and increasing evidence suggests that MPs can accumulate in agricultural soils through fertilization by compost. In addition, the most common raw materials for composting are livestock and poultry manure wastes. Because the presence of MPs may threaten the safe utilization of fertilizers composted by livestock and poultry wastes during crop planting, it is necessary to understand the contamination risk of MPs present in livestock and poultry manure. In this study, the distribution of MPs in 19 livestock and poultry farms with 3 different species was investigated by using FTIR microscopy. A total of 115 items manure MPs and 18 items feed MPs were identified as PP and PE types dominated by colorful fragments and fibers. Furthermore, after comparing the compositions of plastic products used in the feeding process, we proposed two transport pathways for MP pollution in manure and one potential transport pathway in feeds. Our result proved that the application of swine and poultry manure directly could be a new route of MPs in agricultural soil, furthermore, the presence of MPs could threaten the safety of resource utilization in agricultural soil by using swine and poultry manure for manure potentially. Not, only that, our study also provided a reference for the remediation of MP-contaminated soil.

A novel method for extraction of polypropylene microplastics in swine manure.

With the development of modern industry and agriculture, plentiful microplastics (MPs) were produced as a result of the abuse of plastic. The widespread presence of MPs in soils has caused coastal ecological environment pollution. Previous research has shown that fertilizer is one pathway for the entry of MPs into agricultural soils. Meanwhile, livestock manure is a major fertilizer for crops, and the application of livestock manure compost creates a potential pathway for MPs to enter soils. Thus, MPs may exist in livestock manure from the process of livestock breeding and ultimately contaminate agricultural soils. Based on the increasing attention to MP pollution, manure-born MPs will attract more interest in the future. Thus, the present study compares the extraction effects of centrifugation with fractional distillation, and an improved method is introduced to extract polypropylene (PP) from different types of swine manure. The numbers of particles and fibers were determined using a camera (MS60) connected to a stereomicroscope (Mshot MZ62), and the results showed that the recovery rate of plastic particles in swine manure based on different added numbers ranged from 71.43% ± 8.36 to 96.67% ± 3.33 with the centrifugation method, and only 31.11% ± 10.56 to 43.33% ± 12.56 using fractional distilling. The recovery rate for fibers was generally higher than for particles, especially using centrifugation, and ranged from 95.67% ± 1.58 to 100% ± 0, while the rate of fiber recovery using fractional distillation ranged from 39.44% ± 10.66 to 39.44 ± 10.66. The results of recovery rates using the two methods show that the effect of extraction by centrifugation is superior to the method of fractional distillation, with a recovery rate of approximately 100% for fibers and 90% for particles. The recovery number of microplastics evaluated with a line regression model was acceptable. Graphical abstract.

A Novel Saliency Detection Algorithm Based On Adversarial Learning Model.

The traditional salient object detection models can be divided into several classes based on the low-level features of images and contrast between the pixels. This paper proposes an adversarial learning model (ALM) that includes the generative model and discriminative model. The ALM uses the original image as an input of the generative model to extract the high-level features and forms an initial salient map. Then, the discriminative model is utilized to compare differences in the features between the initial salient map and the ground truth, and the obtained differences are sent to the convolutional layers of the generative model to adjust the parameters for the generative model updating. Due to the serial-iterative adjustment, the salient map of the generative model becomes more similar to the ground truth. Lastly, the ALM forms the salient map fused with the super-pixels by enhancing the color and texture features, so the final salient map is obtained. The ALM is not limited to the color and texture features; on the contrary, it fuses multiple features and achieves good results in the salient target extraction. The experimental results show that ALM performs better than the other ten state-of-the-art models on three different datasets. Thus, the proposed ALM is widely applicable to the salient target extraction.

Effect of eight-section brocade on bone mineral density in middle age and elderly people: Protocol for a systematic review and meta-analysis of randomised controlled trials.

BACKGROUND: Physical therapy have an important role in preventing and managing osteoporosis (OP). A number of randomized controlled studies have indicated that eight-section brocade (ESB) could increase bone mass and alleviate pain, particularly in older women. However, there is no systematic review evaluating safety and efficacy of ESB. METHODS: Relevant studies involving eight-section brocade in middle-aged and elderly individuals with osteoporosis were systematically identified from electronic databases, including EMBASE, PubMed, the Cochrane Library Chinese National Knowledge Infrastructure, Chinese Science and Technology Periodicals Database, Chinese BioMedical Database, and Wanfang Data. Inclusion criteria are randomised controlled trials of eight-section brocade that examine function and bone metabolism in middle-aged and elderly individuals with OP. The primary outcome measures will be bone mineral density (BMD), balance capacity, pain score, and adverse event including fracture during exercise. Review Manager (Revman Version 5.3) software will be used for data synthesis, sensitivity analysis, meta regression, subgroup analysis, and risk of bias assessment. A funnel plot will be developed to evaluate reporting bias and Begg and Egger tests will be used to assess funnel plot symmetries. We will use the Grading of Recommendations Assessment, Development and Evaluation system to assess the quality of evidence. RESULTS: This paper will systematically review the existing evidence, assessing the safety and effect of eight-section brocade in middle-aged and elderly individuals with OP. CONCLUSION: The results of this review may help to establish a better approach to prevention of osteoporosis and osteoporotic fractures in high-risk groups and to provide reliableevidence for its further application. ETHICS AND DISSEMINATION: Our aim is to publish this systematic review in a peer-reviewed journal. Our findings will provide information about the safety of ESB exercises and their effect on BMD of middle-aged and elderly individuals. This review will not require ethical approval as there are no issues about participant privacy.