Search

Artificial water bodies in Central Asia offer unique environments in which to study plankton diversity influenced by topographic barriers. However, the complexity of these ecosystems and limited comprehensive studies in the region challenge our understanding. In this study, we systematically investigated the water environment parameters and phytoplankton community structure by surveying 14 artificial waters on the southern side of the Altai Mountains and the northern and southern sides of the Tianshan Mountains in the Xinjiang region. The survey covered physical and nutrient indicators, and the results showed noticeable spatial differences between waters in different regions. The temperature, dissolved oxygen, total nitrogen, and total phosphorus of artificial water in the southern Altai Mountains vary greatly. In contrast, the waters in the northern Tianshan Mountains have more consistent physical indicators. The results of phytoplankton identification showed that the phytoplankton communities in different regions are somewhat different, with diatom species being the dominant taxon. The cluster analysis and the non-metric multidimensional scaling (NMDS) results also confirmed the variability of the phytoplankton communities in the areas. The variance partitioning analysis (VPA) results showed that climatic and environmental factors can explain some of the variability of the observed data. Nevertheless, the residual values indicated the presence of other unmeasured factors or the influence of stochasticity. This study provides a scientific basis for regional water resource management and environmental protection.

Schizothoracinae species are the largest group of Cypriniformes that readily adapt to the natural conditions of the Qinghai-Tibet Plateau. This group has habitat characteristics and distribution patterns centered on the Qinghai-Tibet Plateau. To study the evolution of three Schizothoracinae species in Northwest China, the evolutionary characteristics of these species were explored based on differences in otolith morphology and skeletal morphology. From 2020 to 2022, 138 samples (63 Aspiorhynchus laticeps, 35 Diptychus maculatus and 40 Schizothorax pseudaksaiensis) were collected from the Tarim River and Ili River, 6 basic morphological parameters of otoliths were measured and converted into 6 morphological factors and 7 morphological indices. A total of 77 Fourier transform coefficients of each otolith were selected The first three principal components accounted for 92.834% of the total variation in 13 otolith morphological indices of the three Schizothoracinae species, and the overall discrimination rate was 94.20%. According to the principal component analysis of 77 Fourier harmonic values of otoliths, the first 20 principal components explained 97.233% of the total variation, and the overall discrimination rate was 100%. The results of the cluster analysis directly reflected the relationships between related species. The differences in the bone morphology of the three Schizothoracinae species were particularly reflected in the number of whiskers, pharyngeal teeth and vertebrae, and there were also significant differences in the shapes of the sphenotic (SP), pterotic (PTE), preoperculum (PO), branchiostegal ray (BRA) and basibranchial (BB) bones. Their unique morphological and skeletal characteristics are closely related to geological changes and water system evolutionary trends. This study contributes to the understanding of species identification and the evolutionary status of plateau fishes, provides a reference for further evolutionary classification and for assessing the evolutionary mechanisms of plateau fishes, and provides a scientific basis for phylogeny and germplasm resource protection.

The concept of production stability in hot strip rolling encapsulates the ability of a production line to consistently maintain its output levels and uphold the quality of its products, thus embodying the steady and uninterrupted nature of the production yield. This scholarly paper focuses on the paramount looper equipment in the finishing rolling area, utilizing it as a case study to investigate approaches for identifying the origins of instabilities, specifically when faced with inadequate looper performance. Initially, the paper establishes the equipment process accuracy evaluation (EPAE) model for the looper, grounded in the precision of the looper’s operational process, to accurately depict the looper’s functioning state. Subsequently, it delves into the interplay between the EPAE metrics and overall production stability, advocating for the use of EPAE scores as direct indicators of production stability. The study further introduces a novel algorithm designed to trace the root causes of issues, categorizing them into material, equipment, and control factors, thereby facilitating on-site fault rectification. Finally, the practicality and effectiveness of this methodology are substantiated through its application on the 2250 hot rolling equipment production line. This paper provides a new approach for fault tracing in the hot rolling process.

In this study, we investigated how changes in salinity affect biodiversity and function in 11 typical water bodies in the Altai region. The salinity of the freshwater bodies ranged from 0 to 5, the brackish water salinities ranged from 5 to 20, and the hypersaline environments had salinities > 20. We identified 11 orders, 34 families, and 55 genera in 3061 benthic samples and classified them into 10 traits and 32 categories. Subsequently, we conducted Mantel tests and canonical correlation analysis (CCA) and calculated biodiversity and functional diversity indices for each sampling site. The results indicated that biodiversity and the proportion of functional traits were greater in freshwater environments than in saline environments and decreased gradually with increasing salinity. Noticeable shifts in species distribution were observed in high-salinity environments and were accompanied by specific functional traits such as swimming ability, smaller body sizes, and air-breathing adaptations. The diversity indices revealed that the species were more evenly distributed in high-diversity environments under the influence of salinity. In contrast, in high-salinity environments, only a few species dominated. The results suggested that increasing salinity accelerated the evolution of benthic communities, leading to reduced species diversity and functional homogenization. We recommend enhancing the monitoring of saline water resources and implementing sustainable water resource management to mitigate the impact of salinity stress on aquatic communities in response to climate-induced soil and water salinization.

In swarm-robotics foraging, the purpose of task allocation is to adjust the number of active foraging robots dynamically based on the task demands and changing environment. It is a difficult challenge to generate self-organized foraging behavior in which each robot can adapt to environmental changes. To complete the foraging task efficiently, this paper presents a novel self-organized task allocation strategy known as the dynamic response threshold model (DRTM). To adjust the behavior of the active foraging robots, the proposed DRTM newly introduces the traffic flow density, which can be used to evaluate the robot density. Firstly, the traffic flow density and the amount of obstacle avoidance are used to adjust the threshold which determines the tendency of a robot to respond to a stimulus in the environment. Then, each individual robot uses the threshold and external stimulus to calculate the foraging probability that determines whether or not to go foraging. This paper completes the simulation and physical experiments, respectively, and the performance of the proposed method is evaluated using three commonly used performance indexes: the average deviation of food, the energy efficiency, and the number of obstacle avoidance events. The experimental results show that the DRTM is superior to and more efficient than the adaptive response threshold model (ARTM) in all three indexes.

Drone object detection faces numerous challenges such as dense clusters with overlapping, scale diversity, and long-tail distributions. Utilizing tiling inference through uniform sliding window is an effective way of enlarging tiny objects and meanwhile efficient for real-world applications. However, merely partitioning input images may result in heavy truncation and an unexpected performance drop in large objects. Therefore, in this work, we strive to develop an improved tiling detection framework with both competitive performance and high efficiency. First, we formulate the tiling inference and training pipeline with a mixed data strategy. To avoid truncation and handle objects at all scales, we simultaneously perform global detection on the original image and local detection on corresponding sub-patches, employing appropriate patch settings. Correspondingly, the training data includes both original images and the patches generated by random online anchor-cropping, which can ensure the effectiveness of patches and enrich the image scenarios. Furthermore, a scale filtering mechanism is applied to assign objects at diverse scales to global and local detection tasks to keep the scale invariance of a detector and obtain optimal fused predictions. As most of the additional operations are performed in parallel, the tiling inference remains highly efficient. Additionally, we devise two augmentations customized for tiling detection to effectively increase valid annotations, which can generate more challenging drone scenarios and simulate the practical cluster with overlapping, especially for rare categories. Comprehensive experiments on both public drone benchmarks and our customized real-world images demonstrate that, in comparison to other drone detection frameworks, the proposed tiling framework can significantly improve the performance of general detectors in drone scenarios with lower additional computational costs.

The potential of the Internet of Body (IoB) to support healthcare systems in the future lies in its ability to enable proactive wellness screening through the early detection and prevention of diseases. One promising technology for facilitating IoB applications is near-field inter-body coupling communication (NF-IBCC), which features lower power consumption and higher data security when compared to conventional radio frequency (RF) communication. However, designing efficient transceivers requires a profound understanding of the channel characteristics of NF-IBCC, which remain unclear due to significant differences in the magnitude and passband characteristics of existing research. In response to this problem, this paper clarifies the physical mechanisms of the differences in the magnitude and passband characteristics of NF-IBCC channel characteristics in existing research work through the core parameters that determine the gain of the NF-IBCC system. The core parameters of NF-IBCC are extracted through the combination of transfer functions, finite element simulations, and physical experiments. The core parameters include the inter-body coupling capacitance (CH), the load impedance (ZL), and the capacitance (Cair), coupled by two floating transceiver grounds. The results illustrate that CH, and particularly Cair, primarily determine the gain magnitude. Moreover, ZL mainly determines the passband characteristics of the NF-IBCC system gain. Based on these findings, we propose a simplified equivalent circuit model containing only core parameters, which can accurately capture the gain characteristics of the NF-IBCC system and help to concisely describe the channel characteristics of the system. This work lays a theoretical foundation for developing efficient and reliable NF-IBCC systems that can support IoB for early disease detection and prevention in healthcare applications. The potential benefits of IoB and NF-IBCC technology can, thus, be fully realized by developing optimized transceiver designs based on a comprehensive understanding of the channel characteristics.

To investigate the effects of different raising environments on the flesh quality, the study set up three groups of silver carp (Hypophthalmichthys molitrix), that is, pond-farmed; short-term stocked; and ranched, grown in a natural water ranch. This study compared the differences in muscle proximate composition and amino acid composition among three groups. The results showed that there was no difference between the ranched and the stocked groups in content of crude protein, ash, total amino acids (TAA), essential amino acids (EAA), and umami-flavored amino acids (UAA), with both groups being significantly higher than the farmed group. This shows that, in terms of flesh quality, the stocked group was closer to the ranched group and better than the farmed group after being stocked in natural water for 30 days. The results suggest that the flesh quality of farmed fish was improved by short-term stocking in natural water. To elucidate the reasons of flesh quality change in the stocked group, this study compared the food composition and intestinal digestive enzyme activity in three groups, demonstrating that the ranched and stocked groups had similar food composition, with their detritus proportion lower than that of the farmed group, consuming easily digestible phytoplankton diatoms rich in amino acids and fatty acids. No significant difference was seen between the ranched group and the stocked group, for which amylase, lipase, and trypsin activities were lower than that of the farmed group. It is hypothesized that differences in environmental and food composition resulted in lower digestive enzyme activity in the ranched group and the stocked group. In summary, the short-term stocking of farmed fish in a natural water ranch can effectively improve the nutrient content, quality and flavor, and promote value of fish products.

Emerging evidence suggests that inhalation of particulate matter (PM) can have direct adverse effects on liver function. Early life is a time of particular vulnerability to the effects of air pollution. On that basis, we tested whether in utero exposure to residential PM has an impact on the developing liver. Pregnant mice (C57BL/6J) were intranasally administered 100 µg of PM sampled from residential roof spaces (~5 mg/kg) on gestational days 13.5, 15.5, and 17.5. The pups were euthanized at two weeks of age, and liver tissue was collected to analyse hepatic metabolism (glycogen storage and lipid level), cellular responses (oxidative stress, inflammation, and fibrosis), and genotoxicity using a range of biochemical assays, histological staining, ELISA, and qPCR. We did not observe pronounced effects of environmentally sampled PM on the developing liver when examining hepatic metabolism and cellular response. However, we did find evidence of liver genomic DNA damage in response to in utero exposure to PM. This effect varied depending on the PM sample. These data suggest that in utero exposure to real-world PM during mid-late pregnancy has limited impacts on post-natal liver development.

Grey wolf optimization (GWO) is a meta-heuristic algorithm inspired by the hierarchy and hunting behavior of grey wolves. GWO has the superiorities of simpler concept and fewer adjustment parameters, and has been widely used in different fields. However, there are some disadvantages in avoiding prematurity and falling into local optimum. This paper presents an improved grey wolf optimization (IGWO) to ameliorate these drawbacks. Firstly, a modified position update mechanism for pursuing high quality solutions is developed. By designing an ameliorative position update formula, a proper balance between the exploration and exploitation is achieved. Moreover, the leadership hierarchy is strengthened by proposing adaptive weights of α, β and δ. Then, a dynamic local optimum escape strategy is proposed to reinforce the ability of the algorithm to escape from the local stagnations. Finally, some individuals are repositioned with the aid of the positions of the leaders. These individuals are pulled to new positions near the leaders, helping to accelerate the convergence of the algorithm. To verify the effectiveness of IGWO, a series of contrast experiments are conducted. On the one hand, IGWO is compared with some state-of-the-art GWO variants and several promising meta-heuristic algorithms on 20 benchmark functions. Experimental results indicate that IGWO performs better than other competitors. On the other hand, the applicability of IGWO is verified by a robot global path planning problem, and simulation results demonstrate that IGWO can plan shorter and safer paths. Therefore, IGWO is successfully applied to the path planning as a new method.

Although the performance of unmanned aerial vehicle (UAV) tracking has benefited from the successful application of discriminative correlation filters (DCF) and convolutional neural networks (CNNs), UAV tracking under occlusion and deformation remains a challenge. The main dilemma is that challenging scenes, such as occlusion or deformation, are very complex and changeable, making it difficult to obtain training data covering all situations, resulting in trained networks that may be confused by new contexts that differ from historical information. Data-driven strategies are the main direction of current solutions, but gathering large-scale datasets with object instances under various occlusion and deformation conditions is difficult and lacks diversity. This paper proposes an attention-based mask generation network (AMGN) for UAV-specific tracking, which combines the attention mechanism and adversarial learning to improve the tracker’s ability to handle occlusion and deformation. After the base CNN extracts the deep features of the candidate region, a series of masks are determined by the spatial attention module and sent to the generator, and the generator discards some features according to these masks to simulate the occlusion and deformation of the object, producing more hard positive samples. The discriminator seeks to distinguish these hard positive samples while guiding mask generation. Such adversarial learning can effectively complement occluded and deformable positive samples in the feature space, allowing to capture more robust features to distinguish objects from backgrounds. Comparative experiments show that our AMGN-based tracker achieves the highest area under curve (AUC) of 0.490 and 0.349, and the highest precision scores of 0.742 and 0.662, on the UAV123 tracking benchmark with partial and full occlusion attributes, respectively. It also achieves the highest AUC of 0.555 and the highest precision score of 0.797 on the DTB70 tracking benchmark with the deformation attribute. On the UAVDT tracking benchmark with the large occlusion attribute, it achieves the highest AUC of 0.407 and the highest precision score of 0.582.

We report a tomographic absorption spectroscopy (TAS) study of water vapor transport in a laminar jet issuing into the ambient. The jet was generated using compressed dry air that was straightened by a honeycomb and a smooth contraction nozzle. A TAS scheme using the water vapor in the ambient as absorbing species and the absorption line near 1368.598 nm was proposed to study the H2O transport in the laminar jet with an inverse concentration gradient. One-dimensional tomography was conducted at various heights above the nozzle, and the results were validated by the predictions from computational fluid dynamics (CFD) simulations. Particularly, the variations in the concentration gradient in the shear layer at different heights were captured. The 2D distribution of water concentration in the dry laminar jet was obtained experimentally. The present study shows that TAS has great potential in the research of mass transfer and scalar field of gaseous flows.

Tailored properties hot forming of 38MnB5Nb by partition cooling can be configured on-demand. A gradient distribution microstructural characteristic can be generated by undertaking an appropriate cooling-tempering process for the regions with different properties requirements before forming. A unified viscoplastic constitutive model coupled with the primary cooling temperature and related material constants is established based on genetic algorithm. Meanwhile, the use of the mixture of jet air and dry ice particles to cool the partition region is essential to achieve different primary cooling temperatures. In this paper, the inverse heat conduction problem is solved to obtain the relationship between the interfacial heat transfer coefficient and different cooling conditions in the partition cooling process. The U-shaped part is taken as an example to simulate the change of temperature, stress-strain, thickness, and spring-back in the process of partition cooling and tailored hot forming properties. The results show that the gradient microstructural characteristic formed by partition cooling has a great influence on the stress field distribution. The maximum stress of 345 MPa can be reached after complete pressure holding in the partition slow cooling tailored properties of the hot forming process. The maximum stress can reach 743 MPa in the partition fast cooling tailored properties of the hot forming process due to the relatively high deformation resistance of the tempered martensite at the bottom center. The maximum residual stress in the two processes after spring-back drops to 305 MPa and 545 MPa, respectively. The spring-back is small under the two processes, with a maximum spring back angle of no more than 1°.

To balance the diagonal gait of a quadruped robot, a dynamic balance control method is presented to improve the stability of the quadruped robot by adjusting its foot position. We set up a trunk-based coordinate system and a hip-based local coordinate system for the quadruped robot, established the kinematics equation of the robot, and designed a reasonable initial diagonal gait through the spring inverted pendulum model. The current trunk posture of the quadruped robot is obtained by collecting the data of its pitch and roll angle, and the foot position is predicted according to the current posture and initial gait of the quadruped robot. To reduce the impact of one leg landing on the ground and increase the stability of the quadruped robot, we adjust the landing point of the robot according to the landing time difference between the diagonal legs. The proposed method can adjust the body in such scenarios as planar walking and lateral impact resistance. It can reduce the disturbance during the robot motion and make the robot move smoothly. The validity of this method is verified by simulation experiments.

To improve the tumor-targeting efficacy of photodynamic therapy, biotin was conjugated with chlorin e6 to develop a new tumor-targeting photosensitizer, Ce6-biotin. The Ce6-biotin had good water solubility and low aggregation. The singlet-oxygen generation rate of Ce6-biotin was slightly increased compared to Ce6. Flow cytometry and confocal laser scanning microscopy results confirmed Ce6-biotin had higher binding affinity toward biotin-receptor-positive HeLa human cervical carcinoma cells than its precursor, Ce6. Due to the BR-targeting ability of Ce6-biotin, it exhibited stronger cytotoxicity to HeLa cells upon laser irradiation. The IC50 against HeLa cells of Ce6-biotin and Ce6 were 1.28 µM and 2.31 µM, respectively. Furthermore, both Ce6-biotin and Ce6 showed minimal dark toxicity. The selectively enhanced therapeutic efficacy and low dark toxicity suggest that Ce6-biotin is a promising PS for BR-positive-tumor-targeting photodynamic therapy.

Collaborative control of a dual-arm robot refers to collision avoidance and working together to accomplish a task. To prevent the collision of two arms, the control strategy of a robot arm needs to avoid competition and to cooperate with the other one during motion planning. In this paper, a dual-arm deep deterministic policy gradient (DADDPG) algorithm is proposed based on deep reinforcement learning of multi-agent cooperation. Firstly, the construction method of a replay buffer in a hindsight experience replay algorithm is introduced. The modeling and training method of the multi-agent deep deterministic policy gradient algorithm is explained. Secondly, a control strategy is assigned to each robotic arm. The arms share their observations and actions. The dual-arm robot is trained based on a mechanism of “rewarding cooperation and punishing competition”. Finally, the effectiveness of the algorithm is verified in the Reach, Push, and Pick up simulation environment built in this study. The experiment results show that the robot trained by the DADDPG algorithm can achieve cooperative tasks. The algorithm can make the robots explore the action space autonomously and reduce the level of competition with each other. The collaborative robots have better adaptability to coordination tasks.

In view of difficulty in application of optical flow based human action recognition due to large amount of calculation, a human action recognition algorithm I3D-shufflenet model is proposed combining the advantages of I3D neural network and lightweight model shufflenet. The 5 × 5 convolution kernel of I3D is replaced by a double 3 × 3 convolution kernels, which reduces the amount of calculations. The shuffle layer is adopted to achieve feature exchange. The recognition and classification of human action is performed based on trained I3D-shufflenet model. The experimental results show that the shuffle layer improves the composition of features in each channel which can promote the utilization of useful information. The Histogram of Oriented Gradients (HOG) spatial-temporal features of the object are extracted for training, which can significantly improve the ability of human action expression and reduce the calculation of feature extraction. The I3D-shufflenet is testified on the UCF101 dataset, and compared with other models. The final result shows that the I3D-shufflenet has higher accuracy than the original I3D with an accuracy of 96.4%.

Landslide hazards affect the security of human life and property. Mapping the spatial distribution of landslide hazard risk is critical for decision-makers to implement disaster prevention measures. This study aimed to predict and zone landslide hazard risk, using Guixi County in eastern Jiangxi, China, as an example. An integrated dataset composed of 21 geo-information layers, including lithology, rainfall, altitude, slope, distances to faults, roads and rivers, and thickness of the weathering crust, was used to achieve the aim. Non-digital layers were digitized and assigned weights based on their landslide propensity. Landslide locations and non-risk zones (flat areas) were both vectorized as polygons and randomly divided into two groups to create a training set (70%) and a validation set (30%). Using this training set, the Random Forests (RF) algorithm, which is known for its accurate prediction, was applied to the integrated dataset for risk modeling. The results were assessed against the validation set. Overall accuracy of 91.23% and Kappa Coefficient of 0.82 were obtained. The calculated probability for each pixel was consequently graded into different zones for risk mapping. Hence, we conclude that landslide risk zoning using the RF algorithm can serve as a pertinent reference for local government in their disaster prevention and early warning measures.

Recently, the information analysis technology of underwater has developed rapidly, which is beneficial to underwater resource exploration, underwater aquaculture, etc. Dangerous and laborious manual work is replaced by deep learning-based computer vision technology, which has gradually become the mainstream. The binocular cameras based visual analysis method can not only collect seabed images but also construct the 3D scene information. The parallax of the binocular image was used to calculate the depth information of the underwater object. A binocular camera based refined analysis method for underwater creature body length estimation was constructed. A fully convolutional network (FCN) was used to segment the corresponding underwater object in the image to obtain the object position. A fish’s body direction estimation algorithm is proposed according to the segmentation image. The semi-global block matching (SGBM) algorithm was used to calculate the depth of the object region and estimate the object body length according to the left and right views of the object. The algorithm has certain advantages in time and accuracy for interest object analysis by the combination of FCN and SGBM. Experiment results show that this method effectively reduces unnecessary information, improves efficiency and accuracy compared to the original SGBM algorithm.

Rare earth elements (REEs) are widely used in various industries. The open-pit mining and chemical extraction of REEs in the weathered crust in southern Jiangxi, China, since the 1970s have provoked severe damages to the environment. After 2010, different restorations have been implemented by various enterprises, which seem to have a spatial variability in both management techniques and efficiency from one mine to another. A number of vegetation indices, e.g., normalized difference vegetation index (NDVI), soil-adjusted vegetation index (SAVI), enhanced vegetation index (EVI) and atmospherically resistant vegetation index (ARVI), can be used for this kind of monitoring and assessment but lack sensitivity to subtle differences. For this reason, the main objective of this study was to explore the possibility to develop new, mining-tailored remote sensing indicators to monitor the impacts of REE mining on the environment and to assess the effectiveness of its related restoration using multitemporal Landsat data from 1988 to 2019. The new indicators, termed mining and restoration assessment indicators (MRAIs), were developed based on the strong contrast of spectral reflectance, albedo, land surface temperature (LST) and tasseled cap brightness (TCB) of REE mines between mining and postmining restoration management. These indicators were tested against vegetation indices such as NDVI, EVI, SAVI and generalized difference vegetation index (GDVI), and found to be more sensitive. Of similar sensitivity to each other, one of the new indicators was employed to conduct the restoration assessment of the mined areas. Six typically managed mines with different restoration degrees and management approaches were selected as hotspots for a comparative analysis to highlight their temporal trajectories using the selected MRAI. The results show that REE mining had experienced a rapid expansion in 1988–2010 with a total mined area of about 66.29 km2 in the observed counties. With implementation of the post-2010 restoration measures, an improvement of varying degrees in vegetation cover in most mines was distinguished and quantified. Hence, this study with the newly developed indicators provides a relevant approach for assessing the sustainable exploitation and management of REE resources in the study area.

The accurate prediction of airplane engine failure can provide a reasonable decision basis for airplane engine maintenance, effectively reducing maintenance costs and reducing the incidence of failure. According to the characteristics of the monitoring data of airplane engine sensors, this work proposed a remaining useful life (RUL) prediction model based on principal component analysis and bidirectional long short-term memory. Principal component analysis is used for feature extraction to remove useless information and noise. After this, bidirectional long short-term memory is used to learn the relationship between the state monitoring data and remaining useful life. This work includes data preprocessing, the construction of a hybrid model, the use of the NASA’s Commercial Aerodynamic System Simulation (C-MAPSS) data set for training and testing, and the comparison of results with those of support vector regression, long short-term memory and bidirectional long short-term memory models. The hybrid model shows better prediction accuracy and performance, which can provide a basis for formulating a reasonable airplane engine health management plan.

Deep learning based intelligent fault diagnosis methods have become a research hotspot in the fields of fault diagnosis and the health management of rolling bearings in recent years. To effectively identify incipient faults in rotating machinery, this paper proposes a novel hybrid intelligent fault diagnosis framework based on a convolutional neural network and support vector machine (SVM). First, an improved one-dimensional convolutional neural network (1DCNN) was adopted to extract fault features, and the state information and intrinsic properties of the raw vibration signals were mined. Second, the extracted features were used to train the SVM, which was applied to classify the fault category. The proposed hybrid framework combined the excellent classification performance of the SVM for small samples and the strong feature-learning ability of CNN network. In order to tune the parameters of the SVM, an improved novel particle swarm optimization algorithm (INPSO) which combined the Tent map and Lévy flight strategy was proposed. Numerical experimental results indicated that the proposed PSO variant had a better performance in searching accuracy and convergence speed. At last, multiple groups of rolling bearing fault diagnosis experiments were carried out and experimental results showed that, with the proposed 1DCNN-INPSO-SVM model, the hybrid framework was capable of diagnosing with high precision for rolling bearings and superior to some traditional fault diagnosis methods.

The convolutional neural network (CNN) has been widely used in image recognition field due to its good performance. This paper proposes a facial expression recognition method based on the CNN model. Regarding the complexity of the hierarchic structure of the CNN model, the activation function is its core, because the nonlinear ability of the activation function really makes the deep neural network have authentic artificial intelligence. Among common activation functions, the ReLu function is one of the best of them, but it also has some shortcomings. Since the derivative of the ReLu function is always zero when the input value is negative, it is likely to appear as the phenomenon of neuronal necrosis. In order to solve the above problem, the influence of the activation function in the CNN model is studied in this paper. According to the design principle of the activation function in CNN model, a new piecewise activation function is proposed. Five common activation functions (i.e., sigmoid, tanh, ReLu, leaky ReLus and softplus−ReLu, plus the new activation function) have been analysed and compared in facial expression recognition tasks based on the Keras framework. The Experimental results on two public facial expression databases (i.e., JAFFE and FER2013) show that the convolutional neural network based on the improved activation function has a better performance than most-of-the-art activation functions.

Recharging implantable electronics from the outside of the human body is very important for applications such as implantable biosensors and other implantable electronics. In this paper, a recharging method for implantable biosensors based on a wearable incoherent light source has been proposed and simulated. Firstly, we develop a model of the incoherent light source and a multi-layer model of skin tissue. Secondly, the recharging processes of the proposed method have been simulated and tested experimentally, whereby some important conclusions have been reached. Our results indicate that the proposed method will offer a convenient, safe and low-cost recharging method for implantable biosensors, which should promote the application of implantable electronics.

In recent years, with the development of artificial intelligence and human−computer interaction, more attention has been paid to the recognition and analysis of facial expressions. Despite much great success, there are a lot of unsatisfying problems, because facial expressions are subtle and complex. Hence, facial expression recognition is still a challenging problem. In most papers, the entire face image is often chosen as the input information. In our daily life, people can perceive other’s current emotions only by several facial components (such as eye, mouth and nose), and other areas of the face (such as hair, skin tone, ears, etc.) play a smaller role in determining one’s emotion. If the entire face image is used as the only input information, the system will produce some unnecessary information and miss some important information in the process of feature extraction. To solve the above problem, this paper proposes a method that combines multiple sub-regions and the entire face image by weighting, which can capture more important feature information that is conducive to improving the recognition accuracy. Our proposed method was evaluated based on four well-known publicly available facial expression databases: JAFFE, CK+, FER2013 and SFEW. The new method showed better performance than most state-of-the-art methods.

To solve the illumination sensitivity problems of mobile ground equipment, an enhanced visual SLAM algorithm based on the sparse direct method was proposed in this paper. Firstly, the vignette and response functions of the input sequences were optimized based on the photometric formation of the camera. Secondly, the Shi−Tomasi corners of the input sequence were tracked, and optimization equations were established using the pixel tracking of sparse direct visual odometry (VO). Thirdly, the Levenberg−Marquardt (L−M) method was applied to solve the joint optimization equation, and the photometric calibration parameters in the VO were updated to realize the real-time dynamic compensation of the exposure of the input sequences, which reduced the effects of the light variations on SLAM’s (simultaneous localization and mapping) accuracy and robustness. Finally, a Shi−Tomasi corner filtered strategy was designed to reduce the computational complexity of the proposed algorithm, and the loop closure detection was realized based on the oriented FAST and rotated BRIEF (ORB) features. The proposed algorithm was tested using TUM, KITTI, EuRoC, and an actual environment, and the experimental results show that the positioning and mapping performance of the proposed algorithm is promising.

Implantable devices have important applications in biomedical sensor networks used for biomedical monitoring, diagnosis and treatment, etc. In this paper, an implant intra-body communication (IBC) method based on capacitive coupling has been proposed, and the modeling and characterization of this kind of IBC has been investigated. Firstly, the transfer function of the implant IBC based on capacitive coupling was derived. Secondly, the corresponding parameters of the transfer function are discussed. Finally, both measurements and simulations based on the proposed transfer function were carried out, while some important conclusions have been achieved, which indicate that the achieved transfer function and conclusions are able to help to achieve an implant communication method with the highly desirable characteristics of low power consumption, high data rate, high transmission quality, etc.

The signal transmission technology based on the human body medium offers significant advantages in Body Sensor Networks (BSNs) used for healthcare and the other related fields. In previous works we have proposed a novel signal transmission method based on the human body medium using a Mach-Zehnder electro-optical (EO) sensor. In this paper, we present a signal transmission system based on the proposed method, which consists of a transmitter, a Mach-Zehnder EO sensor and a corresponding receiving circuit. Meanwhile, in order to verify the frequency response properties and determine the suitable parameters of the developed system, in-vivo measurements have been implemented under conditions of different carrier frequencies, baseband frequencies and signal transmission paths. Results indicate that the proposed system will help to achieve reliable and high speed signal transmission of BSN based on the human body medium.

Simulation based on the finite-element (FE) method plays an important role in the investigation of intra-body communication (IBC). In this paper, a finite-element model of the whole body model used for the IBC simulation is proposed and verified, while the FE simulation of the galvanic coupling IBC with different signal transmission paths has been achieved. Firstly, a novel finite-element method for modeling the whole human body is proposed, and a FE model of the whole human body used for IBC simulation was developed. Secondly, the simulations of the galvanic coupling IBC with the different signal transmission paths were implemented. Finally, the feasibility of the proposed method was verified by using in vivo measurements within the frequency range of 10 kHz–5 MHz, whereby some important conclusions were deduced. Our results indicate that the proposed method will offer significant advantages in the investigation of the galvanic coupling intra-body communication.

Artificial bee colony (ABC) algorithm, a novel category of bionic intelligent optimization algorithm, was achieved for solving complex nonlinear optimization problems. Previous studies have shown that ABC algorithm is competitive to other biological-inspired optimization algorithms, but there still exist several insufficiencies due to the inefficient solution search equation (SSE), which does well in exploration but poorly in exploitation. To improve accuracy of the solutions, this paper proposes a modified ABC algorithm based on the self-learning mechanism (SLABC) with five SSEs as the candidate operator pool; among them, one is good at exploration and two of them are good at exploitation; another SSE intends to balance exploration and exploitation; moreover, the last SSE with Lévy flight step-size which can generate smaller step-size with high frequency and bigger step-size occasionally not only can balance exploration and exploitation but also possesses the ability to escape from the local optimum. This paper proposes a simple self-learning mechanism, wherein the SSE is selected according to the previous success ratio in generating promising solutions at each iteration. Experiments on a set of 9 benchmark functions are carried out with the purpose of evaluating the performance of the proposed method. The experimental results illustrated that the SLABC algorithm achieves significant improvement compared with other competitive algorithms.

The decision tree algorithm is a core technology in data classification mining, and ID3 (Iterative Dichotomiser 3) algorithm is a famous one, which has achieved good results in the field of classification mining. Nevertheless, there exist some disadvantages of ID3 such as attributes biasing multi-values, high complexity, large scales, etc. In this paper, an improved ID3 algorithm is proposed that combines the simplified information entropy based on different weights with coordination degree in rough set theory. The traditional ID3 algorithm and the proposed one are fairly compared by using three common data samples as well as the decision tree classifiers. It is shown that the proposed algorithm has a better performance in the running time and tree structure, but not in accuracy than the ID3 algorithm, for the first two sample sets, which are small. For the third sample set that is large, the proposed algorithm improves the ID3 algorithm for all of the running time, tree structure and accuracy. The experimental results show that the proposed algorithm is effective and viable.

A method of recharging implantable biosensors based on solar radiation is proposed. Firstly, the models of the proposed method are developed. Secondly, the recharging processes based on solar radiation are simulated using Monte Carlo (MC) method and the energy distributions of sunlight within the different layers of human skin have been achieved and discussed. Finally, the simulation results are verified experimentally, which indicates that the proposed method will contribute to achieve a low-cost, convenient and safe method for recharging implantable biosensors.