Search

Detecting and recognizing pests are paramount for ensuring the healthy growth of crops, maintaining ecological balance, and enhancing food production. With the advancement of artificial intelligence technologies, traditional pest detection and recognition algorithms based on manually selected pest features have gradually been substituted by deep learning-based algorithms. In this review paper, we first introduce the primary neural network architectures and evaluation metrics in the field of pest detection and pest recognition. Subsequently, we summarize widely used public datasets for pest detection and recognition. Following this, we present various pest detection and recognition algorithms proposed in recent years, providing detailed descriptions of each algorithm and their respective performance metrics. Finally, we outline the challenges that current deep learning-based pest detection and recognition algorithms encounter and propose future research directions for related algorithms. [ABSTRACT FROM AUTHOR]

Background: Lumbar disc herniation is a common degenerative lumbar disease with an increasing incidence. Percutaneous endoscopic lumbar discectomy can treat lumbar disc herniation safely and effectively with a minimally invasive procedure. However, the learning curve of this technology is steep, which means that initial learners are often not sufficiently proficient in endoscopic operations, which can easily lead to iatrogenic damage. At present, the application of computer deep learning technology to clinical diagnosis, treatment, and surgical navigation has achieved satisfactory results. Purpose: The objective of our team is to develop a multi-element identification system for the visual field of endoscopic spine surgery using deep learning algorithms and to evaluate the feasibility of this system. Method: We established an image database by collecting surgical videos of 48 patients diagnosed with lumbar disc herniation, which was labeled by two spinal surgeons. We selected 6000 images of the visual field of percutaneous endoscopic spine surgery (including various tissue structures and surgical instruments), divided into the training data, validation data, and test data according to 2:1:2. We developed convolutional neural network models based on instance segmentation—Solov2, CondInst, Mask R-CNN and Yolact, and set the four network model backbone as ResNet101 and ResNet50 respectively. Mean average precision (mAP) and frames per second (FPS) were used to measure the performance of each model for classification, localization and recognition in real time, and AP (average) is used to evaluate how easily an element is detected by neural networks based on computer deep learning. Result: Comprehensively comparing mAP and FSP of each model for bounding box test and segmentation task for the test set of images, we found that Solov2 (ResNet101) (mAP = 73.5%, FPS = 28.9), Mask R-CNN (ResNet101) (mAP = 72.8%, FPS = 28.5) models are the most stable, with higher precision and faster image processing speed. Combining the average precision of the elements in the bounding box test and segmentation tasks in each network, the AP(average) was highest for tool 3 (bbox-0.85, segm-0.89) and lowest for tool 5 (bbox-0.63, segm-0.72) in the instrumentation, whereas in the anatomical tissue elements, the fibrosus annulus (bbox-0.68, segm-0.69) and ligamentum flavum (bbox-0.65, segm-0.62) had higher AP(average),while extra-dural fat (bbox-0.42, segm-0.44) was lowest. Conclusion: Our team has developed a multi-element identification system for the visual field of percutaneous endoscopic spine surgery adapted to the interlaminar and foraminal approaches, which can identify and track anatomical tissue (nerve, ligamentum flavum, nucleus pulposus, etc.) and surgical instruments (endoscopic forceps, an high-speed diamond burr, etc.), which can be used in the future as a virtual educational tool or applied to the intraoperative real-time assistance system for spinal endoscopic operation. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) in deep learning have input pixel limitations, which leads to lost information regarding microcalcification when mammography images are compressed. Segmenting images into patches retains the original resolution when inputting them into the CNN and allows for identifying the location of calcification. This study aimed to develop a mammographic calcification detection method using deep learning by classifying the presence of calcification in the breast. Using publicly available data, 212 mammograms from 81 women were segmented into 224 × 224-pixel patches, producing 15,049 patches. These were visually classified for calcification and divided into five subsets for training and evaluation using fivefold cross-validation, ensuring image consistency. ResNet18, ResNet50, and ResNet101 were used for training, each of which created a two-class calcification classifier. The ResNet18 classifier achieved an overall accuracy of 96.0%, mammogram accuracy of 95.8%, an area under the curve (AUC) of 0.96, and a processing time of 0.07 s. The results of ResNet50 indicated 96.4% overall accuracy, 96.3% mammogram accuracy, an AUC of 0.96, and a processing time of 0.14 s. The results of ResNet101 indicated 96.3% overall accuracy, 96.1% mammogram accuracy, an AUC of 0.96, and a processing time of 0.20 s. This developed method offers quick, accurate calcification classification and efficient visualization of calcification locations. [ABSTRACT FROM AUTHOR]

Automatic modulation recognition is a critical challenge in the field of cognitive radio. In the process of communication, radio signals are modulated in various modes and are interfered by the complex electromagnetic environment. To cope with these problems and avoid manual selection of complex expert features, we propose a multi-level feature extraction algorithm based on deep learning to adequately exploit the hidden feature information of modulated signals. Our algorithm integrates the correlation between the channels of radio signals with convolutional neural networks and Bidirectional Long Short-term Memory (Bi-LSTM), and adopts the appropriate skip connection, which avoids the loss of valid information and achieves the complementarity between spatial and temporal features. In our model, the one-dimensional convolutional layer is specially utilized to enrich the feature representation of each sample point of in-phase and quadrature (I/Q) signals and emphasize the mutual influence of I channel (in-phase signal) and Q channel (quadrature signal). In addition, the label smoothing technique is used to improve the generalization ability of the model. Our proposed method is also of certain significance for other signal processing methods based on deep learning. Experiment results demonstrate that our algorithm outperforms the popular algorithms and is of higher robustness. Specifically, the proposed method improves the recognition accuracy, reaching 92.68% at high signal-to-noise ratio (SNR). In particular, it also reduces the difficulty of recognition for multiple quadrature amplitude modulation (MQAM) signals and significantly improves the recognition accuracy for 16QAM and 64QAM. [ABSTRACT FROM AUTHOR]

The multi-angle polarimetric (MAP) satellite measurements provide abundant information concerning aerosol optical/microphysical properties. In this study, we present a robust and flexible aerosol retrieval algorithm for MAP measurements based on physics-informed deep learning (PDL) method. Different from optimized inversion that needs iterative Radiative Transfer (RT) calculations of all the unknowns, the PDL method can model the whole MAP observations with each retrieved aerosol parameter separately with the pre-training of RT simulations. Furthermore, the training of PDL can make full use of the prior information from ground-based aerosol inversions and satellite surface products, and provides an effective constraint to avoid unphysical values. To examine performance of PDL algorithm, we retrieve aerosols over eastern China from POLDER-3 measurements during 2007–2009. Comparison with AERONET products shows high correlations (R > 0.91) for both POLDER-3 PDL Aerosol Optical Depth (AOD) and fine AOD. Despite lower correlations caused by a small portion of poor retrievals, PDL coarse AOD and Single Scattering Albdeo (SSA) is very consistent with AERONET results. Also, PDL retrievals perform well as the best estimates of optimized methods such as GRASP (Generalized Retrieval of Aerosol and Surface Properties). With an outstanding performance in accuracy and efficiency, the flexible PDL algorithm exhibits great potential for operational retrieval of MAP satellite measurements. • A robust aerosol algorithm is developed for MAP satellite observation. • The training of PDL method can make full use of existing priori information. • POLDER-3 PDL retrievals over eastern China have a good performance. [ABSTRACT FROM AUTHOR]

With users being exposed to the growing volume of online information, the recommendation system aiming at mining the important or interesting information is becoming a modern research topic. One approach of recommendation is to integrate the graph neural network with deep learning algorithms. However, some of them are not tailored for bipartite graphs, which is a unique type of heterogeneous graph having two entity types. Others, though customized, neglect the importance of implicit relation and content information. In this paper, we propose the attentive implicit relation recommendation incorporating content information (AIRC) framework that is designed for bipartite graphs based on the GC–MC algorithm. First, through reconstructing the bipartite graphs, we obtain the implicit relation graphs. Then we analyze the content information of users and items with a CNN process, so that each user and item has its feature-tailored embeddings. Besides, we expand the GC–MC algorithms by adding a graph attention mechanism layer, which handles the implicit relation graph by highlighting important features and neighbors. Therefore, our framework takes into consideration both the implicit relation and content information. Finally, we test our framework on Movielens dataset and the results show that our framework performs better than other state-of-art recommendation algorithms. [ABSTRACT FROM AUTHOR]

Large neural networks usually perform well for executing machine learning tasks. However, models that achieve state-of-the-art performance involve arbitrarily large number of parameters and therefore their training is very expensive. It is thus desired to implement methods with small per-iteration costs, fast convergence rates, and reduced tuning. This paper proposes a multivariate adaptive gradient descent method that meets the above attributes. The proposed method updates every element of the model parameters separately in a computationally efficient manner using an adaptive vector-form learning rate, resulting in low per-iteration cost. The adaptive learning rate computes the absolute difference of current and previous model parameters over the difference in subgradients of current and previous state estimates. In the deterministic setting, we show that the cost function value converges at a linear rate for smooth and strongly convex cost functions. Whereas in both the deterministic and stochastic setting, we show that the gradient converges in expectation at the order of O (1 / k) for a non-convex cost function with Lipschitz continuous gradient. In addition, we show that after T iterates, the cost function of the last iterate scales as O (log (T) / T) for non-smooth strongly convex cost functions. Effectiveness of the proposed method is validated on convex functions, smooth non-convex function, non-smooth convex function, and four image classification data sets, whilst showing that its execution requires hardly any tuning unlike existing popular optimizers that entail relatively large tuning efforts. Our empirical results show that our proposed algorithm provides the best overall performance when comparing it to tuned state-of-the-art optimizers. [ABSTRACT FROM AUTHOR]

Current deep learning methods for single hyperspectral image super-resolution are non-blind ones, which adopt the simplistic bicubic degradation model. These models have poor generalization performance and cannot handle unknown degradation. Additionally, blind super-resolution methods for RGB images neglect rich spectral information in hyperspectral images, which causes spectral distortion in results. To address these issues, we consider the degeneration estimation and propose a single hyperspectral image blind super-resolution algorithm. Specifically, we first use a blur kernel estimation network and a deblurring network to obtain the image without blur. We change the receptive field by exchanging spatial channel information when estimating the kernel, thereby obtaining blurry information at different scales. In addition, to reduce the errors introduced by kernel mismatch and the relevant information among bands ignored by the group convolution, we fuse the spatial information of the blurred image to compensate for the errors and then utilize the spatial and spectral information of other bands to guide the feature extraction of the current band. Finally, we integrate the feature information from different branches in a global fusion network to improve spatial and spectral information fidelity further. Extensive experiments on synthetic and real-world hyperspectral datasets unequivocally demonstrate that our approach outperforms other state-of-the-art approaches in terms of both quantitative and qualitative evaluations. Our code is publicly available at https://github.com/YoungP2001/DBSR. • A novel blind super-resolution algorithm for the single hyperspectral image is proposed for the first time, effectively addressing the issue of unknown degradation in hyperspectral images. • We propose a blur kernel estimation module and a deblurring module to obtain the clean hyperspectral image without blur. • We design the branch and fusion module to exploit the spatial-spectral information from both the local and global perspectives to further remove degradation. • Experimental results validate that the proposed method has superior performance and better generalization capability. [ABSTRACT FROM AUTHOR]