Search

Stress wave technology is very suitable for detecting internal defects of standing trees, logs, and wood and has gradually become the mainstream technology in this research field. Usually, 12 sensors are positioned equidistantly around the cross-section of tree trunks in order to obtain enough stress wave signals. However, the arrangement of sensors is time-consuming and laborious, and maintaining the accuracy of stress wave imaging under sparse signals is a challenging problem. In this paper, a novel stress wave hybrid imaging method based on compressive sensing and elliptic interpolation is proposed. The spatial structure of the defective area is reconstructed by using the advantages of compressive sensing in sparse signal representation and solution of stress waves, and the healthy area is reconstructed by using the elliptic space interpolation method. Then, feature points are selected and mixed for imaging. The comparative experimental results show that the overall imaging accuracy of the proposed method reaches 89.7%, and the high-quality imaging effect can be guaranteed when the number of sensors is reduced to 10, 8, or even 6.

Stress wave tomography technology uses instruments to collect stress wave velocity data via sensors, visualizes those velocity data, and reconstructs an image of internal defects using estimated velocity distribution. This technology can be used to detect the size, position, and shape of internal defects in hardwood, and it has increasingly attracted the attention of researchers. In order to obtain enough stress wave signals, 12 sensors are usually equidistantly positioned around the cross-section of trunks like a clock. Although this strategy is reasonable and convenient, it is obviously not the optimal signal acquisition strategy for all defects. In this paper, a novel sensor position’s optimization method for high-quality stress wave tomography is proposed. The relationship between the shape of defects and the planar distribution of sensors is established by taking the ray penetration ratio and degree of equidistant distribution of sensors as indicators. Through the construction of the fitness function and optimization conditions, the optimal strategy for the planar distribution of sensors was determined using the Genetic Algorithm. Seven samples containing simulated defects and real tree trunks were used to test the proposed algorithm, and the comparison results show that the image of internal defects in hardwood can be reconstructed with high accuracy after optimizing the sensor positions.

The study of comorbidity can provide new insights into the pathogenesis of the disease and has important economic significance in the clinical evaluation of treatment difficulty, medical expenses, length of stay, and prognosis of the disease. In this paper, we propose a disease association prediction model DapBCH, which constructs a cross-species biological network and applies heterogeneous graph embedding to predict disease association. First, we combine the human disease–gene network, mouse gene–phenotype network, human–mouse homologous gene network, and human protein–protein interaction network to reconstruct a heterogeneous biological network. Second, we apply heterogeneous graph embedding based on meta-path aggregation to generate the feature vector of disease nodes. Finally, we employ link prediction to obtain the similarity of disease pairs. The experimental results indicate that our model is highly competitive in predicting the disease association and is promising for finding potential disease associations.

The CRISPR/Cas9 system has significantly advanced the field of gene editing, yet its clinical application is constrained by the considerable challenge of off-target effects. Although numerous deep learning models for off-target prediction have been proposed, most struggle to effectively extract the nuanced features of guide RNA (gRNA) and DNA sequence pairs and to mitigate information loss during data transmission within the model. To address these limitations, we introduce a novel Hybrid Neural Network (HNN) model that employs a parallelized network structure to fully extract pertinent features from different positions and types of bases in the sequence to minimize information loss. Notably, this study marks the first application of word embedding techniques to extract information from sequence pairs that contain insertions and deletions (Indels). Comprehensive evaluation across diverse datasets indicates that our proposed model outperforms existing state-of-the-art prediction methods in off-target prediction. The datasets and source codes supporting this study can be found at https://github.com/Yang-k955/CRISPR-HW.

With the development of sensor technology and point cloud generation techniques, there has been an increasing amount of high-quality forest RGB point cloud data. However, popular clustering-based point cloud segmentation methods are usually only suitable for pure forest scenes and not ideal for scenes with multiple ground features or complex terrain. Therefore, this study proposes a single-tree point cloud extraction method that combines deep semantic segmentation and clustering. This method first uses a deep semantic segmentation network, Improved-RandLA-Net, which is developed based on RandLA-Net, to extract point clouds of specified tree species by adding an attention chain to improve the model’s ability to extract channel and spatial features. Subsequently, clustering is employed to extract single-tree point clouds from the segmented point clouds. The feasibility of the proposed method was verified in the Gingko site, the Lin’an Pecan site, and a Fraxinus excelsior site in a conference center. Finally, semantic segmentation was performed on three sample areas using pre- and postimproved RandLA-Net. The experiments demonstrate that Improved-RandLA-Net had significant improvements in Accuracy, Precision, Recall, and F1 score. At the same time, based on the semantic segmentation results of Improved-RandLA-Net, single-tree point clouds of three sample areas were extracted, and the final single-tree recognition rates for each sample area were 89.80%, 75.00%, and 95.39%, respectively. The results demonstrate that our proposed method can effectively extract single-tree point clouds in complex scenes.

Timely and accurate identification of tea tree pests is critical for effective tea tree pest control. We collected image data sets of eight common tea tree pests to accurately represent the true appearance of various aspects of tea tree pests. The dataset contains 782 images, each containing 1~5 different pest species randomly distributed. Based on this dataset, a tea garden pest detection and recognition model was designed using the Yolov7-tiny network target detection algorithm, which incorporates deformable convolution, the Biformer dynamic attention mechanism, a non-maximal suppression algorithm module, and a new implicit decoupling head. Ablation experiments were conducted to compare the performance of the models, and the new model achieved an average accuracy of 93.23%. To ensure the validity of the model, it was compared to seven common detection models, including Efficientdet, Faster Rcnn, Retinanet, DetNet, Yolov5s, YoloR, and Yolov6. Additionally, feature visualization of the images was performed. The results demonstrated that the Improved Yolov7-tiny model developed was able to better capture the characteristics of tea tree pests. The pest detection model proposed has promising application prospects and has the potential to reduce the time and economic cost of pest control in tea plantations.

Compared to English, Chinese named entity recognition has lower performance due to the greater ambiguity in entity boundaries in Chinese text, making boundary prediction more difficult. While traditional models have attempted to enhance the definition of Chinese entity boundaries by incorporating external features such as lexicons or glyphs, they have rarely disentangled the entity boundary prediction problem for separate study. In order to leverage entity boundary information, the named entity recognition task has been decomposed into two subtasks: boundary annotation and type annotation, and a multi-task learning network (MTL-BERT) has been proposed that combines a bidirectional encoder (BERT) model. This network performs joint encoding and specific decoding of the subtasks, enhancing the model’s feature extraction abilities by reinforcing the feature associations between subtasks. Multiple sets of experiments conducted on Weibo NER, MSRA, and OntoNote4.0 public datasets show that the F1 values of MTL-BERT reach 73.8%, 96.5%, and 86.7%, respectively, effectively improving the performance and efficiency of Chinese named entity recognition tasks.

In order to effectively solve the current security problems encountered by smart wireless terminals in the digital twin biological network, to ensure the stable and efficient operation of the wireless communication network. This research aims to reduce the interference attack in the communication network, an interference source location scheme based on Mobile Tracker in the communication process of the Internet of Things (IoT) is designed. Firstly, this paper improves Attribute-Based Encryption (ABE) to meet the security and overhead requirements of digital twin networking communication. The access control policy is used to encrypt a random key, and the symmetric encryption scheme is used to hide the key. In addition, in the proposed interference source location technology, the influence of observation noise is reduced based on the principle of unscented Kalman filter, and the estimated interference source location is modified by the interference source motion model. In order to further evaluate the performance of the method proposed as the interference source, this paper simulates the jamming attack scenario. The Root Mean Square Error (RMSE) value of the proposed algorithm is 0.245 ​m, which is better than the ErrMin algorithm (0.313 ​m), and the number of observation nodes of the proposed algorithm is less than half of the ErrMin algorithm. To sum up, satisfactory results can be achieved by taking the Jamming Signal Strength (JSS) information as the observation value and estimating the location of the interference source and other state information based on the untracked Kalman filter algorithm. This research has significant value for the secure communication of the digital twins in the IoT.

Accurately detecting and identifying granary pests is important in effectively controlling damage to a granary, ensuring food security scientifically and efficiently. In this paper, multi-scale images of seven common granary pests were collected. The dataset had 5231 images acquired with DSLR-shot, microscope, cell phone and online crawler. Each image contains different species of granary pests in a different background. In this paper, we designed a multi-scale granary pest recognition model, using the YOLOv5 (You Look Only Once version 5) object detection algorithm incorporating bidirectional feature pyramid network (BiFPN) with distance intersection over union, non-maximum suppression (DIOU_NMS) and efficient channel attention (ECA) modules. In addition, we compared the performance of the different models established with Efficientdet, Faster rcnn, Retinanet, SSD, YOLOx, YOLOv3, YOLOv4 and YOLOv5s, and we designed improved YOLOv5s on this dataset. The results show that the average accuracy of the model we designed for seven common pests reached 98.2%, which is the most accurate model among those identified in this paper. For further detecting the robustness of the proposed model, ablation analysis was conducted. Furthermore, the results show that the average accuracy of models established using the YOLOv5s network model combined with the attention mechanism was 96.9%. When replacing the model of PANet with BiFPN, the average accuracy reached 97.2%. At the same time, feature visualization was analyzed. The results show that the proposed model is good for capturing features of pests. The results of the model have good practical significance for the recognition of multi-scale granary pests.

Hyperspectral imaging (HSI) emerges as a non-destructive and rapid analytical tool for assessing food quality, safety, and authenticity. This work aims to investigate the potential of combining the spectral and spatial features of HSI data with the aid of deep learning approach for the pixel-wise classification of food products. We applied two strategies for extracting spatial-spectral features: (1) directly applying three-dimensional convolution neural network (3-D CNN) model; (2) first performing principal component analysis (PCA) and then developing 2-D CNN model from the first few PCs. These two methods were compared in terms of efficiency and accuracy, exemplified through two case studies, i.e., classification of four sweet products and differentiation between white stripe (“myocommata”) and red muscle (“myotome”) pixels on salmon fillets. Results showed that combining spectral-spatial features significantly enhanced the overall accuracy for sweet dataset, compared to partial least square discriminant analysis (PLSDA) and support vector machine (SVM). Results also demonstrated that spectral pre-processing techniques prior to CNN model development can enhance the classification performance. This work will open the door for more research in the area of practical applications in food industry.

Air-coupled ultrasound has shown excellent sensitivity and specificity for the nondestructive imaging of wood-based material. However, it is time-consuming, due to the high scanning density limited by the Nyquist law. This study investigated the feasibility of applying compressed sensing techniques to air-coupled ultrasound imaging, aiming to reduce the number of scanning lines and then accelerate the imaging. Firstly, an undersampled scanning strategy specified by a random binary matrix was proposed to address the limitation of the compressed sensing framework. The undersampled scanning can be easily implemented, while only minor modification was required for the existing imaging system. Then, discrete cosine transform was selected experimentally as the representation basis. Finally, orthogonal matching pursuit algorithm was utilized to reconstruct the wood images. Experiments on three real air-coupled ultrasound images indicated the potential of the present method to accelerate air-coupled ultrasound imaging of wood. The same quality of ACU images can be obtained with scanning time cut in half.

This paper presents a new methodology for detecting the longitudinal location of the hidden hole in a log using impact-echo testing. The hole and the end surface of the log produced two different amplitude peaks in the frequency spectrum after a mechanical tap on the top of the log. The ratio of the two frequencies was used to estimate the longitudinal position of the hole. The major advantage of this method is that it avoids measuring the travel velocity of the stress wave, which is sensitive to many factors and then poses a formidable challenge to the realization of inspection. Experimental studies were carried out using Pine logs with mechanically drilled holes and a Cinnamomum camphora log with natural hole. The results indicated that the estimated positions were in good agreement with the actual position of the hole. The impact-echo testing can be applied to detect the longitudinal position of the internal hole in log.

In this paper, a novel stress wave tomography method, using spatial interpolation and velocity compensation, is proposed for the detection of internal defects in wood, based on the measured time of flight data and the assumption that stress waves propagate in straight lines in the cross-sectional area of wood. First, an improved ellipse-based spatial interpolation method is proposed, which could be used to estimate the velocity value of a grid cell by the elliptic affected zones corresponding to the nearby velocity rays. Second, because of the anisotropic property of wood, a velocity compensation method was applied to obtain more accurate input data for spatial interpolation. Then, the internal graph of the cross-section of a wood trunk could be reconstructed by the proposed algorithm. Four wood samples, with different defects, were used to test the proposed tomography method in the experiment. The results showed that the proposed method performed well and was able to resist signal interference caused by the density variation of the defective area.

Stress wave velocity has been traditionally regarded as an indicator of the extent of damage inside wood. This paper aimed to detect internal decay of urban trees through reconstructing tomographic image of the cross section of a tree trunk. A grid model covering the cross section area of a tree trunk was defined with some assumptions. Stress wave data were processed beforehand to obtain the propagation velocity and the coordinate values. An image reconstruction algorithm for detecting internal decay was proposed based on an interpolation method, which estimated the velocity values of unknown grid points by utilizing the values of the surrounding points. To test the effectiveness of this method, Cinnamomum camphora tree samples were selected and tested using a stress wave tool. The area, positions, and extent of decay in the representative samples were displayed in tomographic images constructed by the interpolation method, and the results demonstrate the performance of the method.

In order to detect the size and shape of defects inside wood, an image reconstruction method based on segmented propagation rays of stress waves is proposed. The method uses sensors to obtain the stress wave velocity data by hanging around the timber equally, visualizes those data, and reconstructs the image of internal defects with the visualized propagation rays. The basis of the algorithm is precisely segmenting the rays to benefit the spatial interpolation. First, a ray segmentation algorithm using the elliptical neighborhood technique is proposed, which can be used to segment the rays and estimate the velocity values of segmented rays by the nearby original rays using elliptical zones. Second, a spatial interpolation algorithm utilizing a segmented ellipse according to the segmented rays is also proposed, which can be used to estimate the velocity value of a grid cell by the segmented ellipses corresponding to the nearby segmented rays. Then, the image of the internal defect inside the wood is reconstructed. Both simulation and experimental data were used to evaluate the proposed method, and the area and shape of the imaging results were analyzed. The comparison results show that the proposed method can produce high quality reconstructions with clear edges and high accuracy.

Stress wave based techniques have been developed for evaluating the quality of the wooden materials nondestructively. However the existing techniques have some shortcomings due to the significant variation of the wood properties and are now in need of updating. There are also stress wave based instruments which have been widely used for nondestructive testing of wood. But most of them are inflexible and unsuitable for the tentative studies. This paper proposed and implemented a wood nondestructive testing platform based on NI virtual instrument. Three wood nondestructive testing methods, including peak time interval measurement, cross-correlation, and spectrum analysis, were also tested on this platform with serious decay sample, early decay sample, and defect-free sample. The results show that new methods can be verified easily and the researches of wood nondestructive testing will be accelerated with the designed platform.

A mobile agent routing algorithm (MARA) is presented in this paper, and then based on the dual-channel communication model, the two-layer network combination optimization strategy is also proposed. Since this strategy deals with the collision between packets and the multicast suppression in channel competitive process well, the blocking probability of network and the error rate of packet transmission can be cut down by utilizing this strategy. Furthermore, a restore rule for the failure optimal route is presented too. By using this rule, the optimal route can restore quickly in the local of fail nodes and most of the information of original optimal route can be reserved. Compared with other existing algorithms like ant colony optimization-based dynamic energy-efficient mobile agent routing algorithm (ADEEMA) and mobile agent-based wireless sensor network (MAWSN), simulation results show that MARA performs better in improving the success rate of packet transmission and cutting down the delay of communication. The success rate of packet transmission is improved 15%. Simultaneously, this algorithm can keep the ant agents away from the nodes with less residual energy in searching for the optimal route. This way can make the energy of each nodes on the optimal route overall decline and hence improve the lifetime of network.