Deep Information Research Articles

Tea Bud Detection Model in a Real Picking Environment Based on an Improved YOLOv5

The detection of tea bud targets is the foundation of automated picking of premium tea. This article proposes a high-performance tea bud detection model to address issues such as complex environments, small target tea buds, and blurry device focus in tea bud detection. During the spring tea-picking stage, we collect tea bud images from mountainous tea gardens and annotate them. YOLOv5 tea is an improvement based on YOLOv5, which uses the efficient Simplified Spatial Pyramid Pooling Fast (SimSPPF) in the backbone for easy deployment on tea bud-picking equipment. The neck network adopts the Bidirectional Feature Pyramid Network (BiFPN) structure. It fully integrates deep and shallow feature information, achieving the effect of fusing features at different scales and improving the detection accuracy of focused fuzzy tea buds. It replaces the independent CBS convolution module in traditional neck networks with Omni-Dimensional Dynamic Convolution (ODConv), processing different weights from spatial size, input channel, output channel, and convolution kernel to improve the detection of small targets and occluded tea buds. The experimental results show that the improved model has improved precision, recall, and mean average precision by 4.4%, 2.3%, and 3.2%, respectively, compared to the initial model, and the inference speed of the model has also been improved. This study has theoretical and practical significance for tea bud harvesting in complex environments.

A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection

Remote sensing object detection (RSOD) plays a crucial role in resource utilization, geological disaster risk assessment and urban planning. Deep learning-based object-detection algorithms have proven effective in remote sensing image studies. However, accurate detection of objects with small size, dense distribution and complex object arrangement remains a significant challenge in the remote sensing field. To address this, a refined and efficient object-detection algorithm (RE-YOLO) has been proposed in this paper for remote sensing images. Initially, a refined and efficient module (REM) was designed to balance computational complexity and feature-extraction capabilities, which serves as a key component of the RE_CSP block. RE_CSP block efficiently extracts multi-scale information, overcoming challenges posed by complex backgrounds. Moreover, the spatial extracted attention module (SEAM) has been proposed in the bottleneck of backbone to promote representative feature learning and enhance the semantic information capture. In addition, a three-branch path aggregation network (TBPAN) has been constructed as the neck network, which facilitates comprehensive fusion of shallow positional information and deep semantic information across different channels, enabling the network with a robust ability to capture contextual information. Extensive experiments conducted on two large-scale remote sensing datasets, DOTA-v1.0 and SCERL, demonstrate that the proposed RE-YOLO outperforms state-of-the-art other object-detection approaches and exhibits a significant improvement in generalization ability.

Unsupervised PolSAR Image Classification Based on Superpixel Pseudo-Labels and a Similarity-Matching Network

Supervised polarimetric synthetic aperture radar (PolSAR) image classification demands a large amount of precisely labeled data. However, such data are difficult to obtain. Therefore, many unsupervised methods have been proposed for unsupervised PolSAR image classification. The classification maps of unsupervised methods contain many high-confidence samples. These samples, which are often ignored, can be used as supervisory information to improve classification performance on PolSAR images. This study proposes a new unsupervised PolSAR image classification framework. The framework combines high-confidence superpixel pseudo-labeled samples and semi-supervised classification methods. The experiments indicated that this framework could achieve higher-level effectiveness in unsupervised PolSAR image classification. First, superpixel segmentation was performed on PolSAR images, and the geometric centers of the superpixels were generated. Second, the classification maps of rotation-domain deep mutual information (RDDMI), an unsupervised PolSAR image classification method, were used as the pseudo-labels of the central points of the superpixels. Finally, the unlabeled samples and the high-confidence pseudo-labeled samples were used to train an excellent semi-supervised method, similarity matching (SimMatch). Experiments on three real PolSAR datasets illustrated that, compared with the excellent RDDMI, the accuracy of the proposed method was increased by 1.70%, 0.99%, and 0.8%. The proposed framework provides significant performance improvements and is an efficient method for improving unsupervised PolSAR image classification.

A novel automated neural network architecture search method of air target intent recognition

Modern air battlefield operations are characterized by flexibility and change, and the battlefield evolves rapidly and intricately. However, traditional air target intent recognition methods, which mainly rely on manually designed neural network models, find it difficult to maintain sustained and excellent performance in such a complex and changing environment. To address the problem of the adaptability of neural network models in complex environments, we propose a lightweight Transformer model (TransATIR) with a strong adaptive adjustment capability, based on the characteristics of air target intent recognition and the neural network architecture search technique. After conducting extensive experiments, it has been proved that TransATIR can efficiently extract the deep feature information from battlefield situation data by utilizing the neural architecture search algorithm, in order to quickly and accurately identify the real intention of the target. The experimental results indicate that TransATIR significantly improves recognition accuracy compared to the existing state-of-the-art methods, and also effectively reduces the computational complexity of the model.

Reconstruction of blood flow velocity with deep learning information fusion from spectral ct projections and vessel geometry

In this work, we investigate a new deep learning reconstruction method of blood flow velocity within deformed vessels from contrast enhanced X-ray projections and vessel geometry. The principle of the method is to perform linear or nonlinear dimension reductions on the Radon projections and on the mesh of the vessel. These low dimensional projections are then fused to obtain the velocity field in the vessel. The accuracy of the reconstruction method is proved using various neural network architectures with realistic unsteady blood flows. The approach leverages the vessel geometry information and outperforms the simple PCA-net.

Identification of apple watercore based on ConvNeXt and Vis/NIR spectra

This paper proposes a method for discriminating between normal apples and watercore apples using visible/near-infrared spectroscopy technology, which combines Gramian Angular Fields (GAF) encoding technology and the ConvNeXt deep learning network. The existing feature extraction methods for visible/near-infrared spectroscopy data do not perform deeper information mining on the extracted features, which results in the quality of the established model being entirely determined by the extracted features. Additionally, the process of building a visible/near-infrared spectroscopy data classification model is complex and time-consuming, and the accuracy of the established model is not high. To address these issues, the experimental visible/near-infrared spectroscopy data of apples was first transformed into two-dimensional images using Gramian Angular Summation Fields (GASF) and Gramian Angular Difference Fields (GADF) with sizes of 64, 128, 256, and 512. These images were then input into the ConvNeXt network, and the performance of different encoding methods and sizes was compared. The results showed that, under the conditions provided in this paper, the GADF encoding method with a size of 256 achieved the highest classification accuracy of 98.48%. Next, ResNet, EfficientNet, and RegNet deep learning networks were selected to classify the encoded images under the same conditions. The results above indicate that the apple variety discrimination method based on GAF encoding technology and ConvNeXt network combined with visible/near-infrared spectroscopy technology can achieve deep information mining of visible/near-infrared spectroscopy data and provide a relatively simple method for establishing qualitative classification models of visible/near-infrared spectroscopy. This method has a relatively excellent discrimination effect between normal apples and watercore apples.

Traffic flow parameter estimation for complex environments based on improved YOLOv8

Estimation of traffic flow parameters based on computer vision is still a very popular challenge. In particular, the detection problems such as occlusion, small targets, luminance variations, and lighting jitter, etc., are caused by dense traffic scenes and complex weather conditions. Previous studies about detecting and tracking methods focused on daytime and nighttime or single weather condition, but the performance of this model will decline dramatically due to complex conditions. In this paper, a framework for estimating traffic flow parameters in complex environments is presented, in which Ghost-YOLOv8 vehicle detection model is proposed. GhostConv is used to replace part of Conv and a new C2fGhost module is designed to replace part of C2f, reducing the number of parameters and improving the detection performance of the model; The global attention mechanism module is added to the neck network, which strengthens the semantic and location information in the features and improves the model’s ability of feature fusion; In view of the loss of semantic information caused by different scales in detecting small targets, a small target detection layer is added to enhance a combination of deep and shallow semantic information; The GIoU bounding loss function is used instead of the original loss function, which improves the performance of the network’s bounding box regression. Then, combining DeepSORT tracking algorithm and virtual line counting method, the proposed framework estimates traffic flow parameters, including volume, speed, and density in complex environments. The experimental results show that compared with the original model in the UA-DETRAC dataset, the improved YOLOv8 model’s the accuracy is increased by 1.4%, and the parameter number and model size are reduced by 0.229G and 0.2MB respectively. In addition, the framework has good robustness, reaching 97.56% accuracy when estimating average traffic flow parameters. It is sufficient to overcome complex weather conditions and effectively help control traffic for intelligent transportation systems and traffic management to provide good data support. In conclusion, it shows that the model can reduce the number and size of model parameters and improve the detection precision as well as meeting the requirements of edge computing devices and having better real-time performance, so it has practical application value.

A Survey of Deep Learning-Based Information Cascade Prediction

Online social media have significantly boosted the creation and transmission of information, accelerating the dissemination and interaction of vast amounts of data, thereby making the prediction of information cascades increasingly important. In recent years, deep learning has been extensively applied in the domain of information cascade prediction. This paper primarily classifies, organizes, and summarizes the current research status and classic algorithms of information cascade prediction methods based on deep learning. According to the different focuses on characterizing information cascade features, studies on deep learning-based information cascade prediction are classified from two perspectives, i.e., prediction targets and prediction methods. Each category is explained in detail, along with its principles, advantages, and disadvantages, and the commonly used datasets and evaluation metrics in this field are introduced. Additionally, this paper explores the role of symmetry in the structural patterns of information diffusion networks, analyzing how symmetry impacts the pathways and efficiency of information dissemination. Finally, this paper summarizes the potential future research directions and development trends in this domain.

Single-Channel Sleep EEG Classification Method Based on LSTM and Hidden Markov Model

Background: The single-channel sleep EEG has the advantages of convenient collection, high-cost performance, and easy daily use, and it has been widely used in the classification of sleep stages. Methods: This paper proposes a single-channel sleep EEG classification method based on long short-term memory and a hidden Markov model (LSTM-HMM). First, the single-channel EEG is decomposed using wavelet transform (WT), and multi-domain features are extracted from the component signals to characterize the EEG characteristics fully. Considering the temporal nature of sleep stage changes, this paper uses a multi-step time series as the input for the model. After that, the multi-step time series features are input into the LSTM. Finally, the HMM improves the classification results, and the final prediction results are obtained. Results: A complete experiment was conducted on the Sleep-EDFx dataset. The results show that the proposed method can extract deep information from EEG and make full use of the sleep stage transition rule. The proposed method shows the best performance in single-channel sleep EEG classification; the accuracy, macro average F1 score, and kappa are 82.71%, 0.75, and 0.76, respectively. Conclusions: The proposed method can realize single-channel sleep EEG classification and provide a reference for other EEG classifications.

MRI-Driven Alzheimer’s Disease Diagnosis Using Deep Network Fusion and Optimal Selection of Feature

Alzheimer’s disease (AD) is a degenerative neurological condition characterized by cognitive decline, memory loss, and reduced everyday function, which eventually causes dementia. Symptoms develop years after the disease begins, making early detection difficult. While AD remains incurable, timely detection and prompt treatment can substantially slow its progression. This study presented a framework for automated AD detection using brain MRIs. Firstly, the deep network information (i.e., features) were extracted using various deep-learning networks. The information extracted from the best deep networks (EfficientNet-b0 and MobileNet-v2) were merged using the canonical correlation approach (CCA). The CCA-based fused features resulted in an enhanced classification performance of 94.7% with a large feature vector size (i.e., 2532). To remove the redundant features from the CCA-based fused feature vector, the binary-enhanced WOA was utilized for optimal feature selection, which yielded an average accuracy of 98.12 ± 0.52 (mean ± standard deviation) with only 953 features. The results were compared with other optimal feature selection techniques, showing that the binary-enhanced WOA results are statistically significant (p < 0.01). The ablation study was also performed to show the significance of each step of the proposed methodology. Furthermore, the comparison shows the superiority and high classification performance of the proposed automated AD detection approach, suggesting that the hybrid approach may help doctors with dementia detection and staging.

SPFDNet: Water Extraction Method Based on Spatial Partition and Feature Decoupling

Extracting water information from remote-sensing images is of great research significance for applications such as water resource protection and flood monitoring. Current water extraction methods aggregated richer multi-level features to enhance the output results. In fact, there is a difference in the requirements for the water body and the water boundary. Indiscriminate multi-feature fusion can lead to perturbation and competition of information between these two types of features during the optimization. Consequently, models cannot accurately locate the internal vacancies within the water body with the external boundary. Therefore, this paper proposes a water feature extraction network with spatial partitioning and feature decoupling. To ensure that the water features are extracted with deep semantic features and stable spatial information before decoupling, we first design a chunked multi-scale feature aggregation module (CMFAM) to construct a context path for obtaining deep semantic information. Then, an information interaction module (IIM) is designed to exchange information between two spatial paths with two fixed resolution intervals and the two paths through. During decoding, a feature decoupling module (FDM) is developed to utilize internal flow prediction to acquire the main body features, and erasing techniques are employed to obtain boundary features. Therefore, the deep features of the water body and the detailed boundary information are supplemented, strengthening the decoupled body and boundary features. Furthermore, the integrated expansion recoupling module (IERM) module is designed for the recoupling stage. The IERM expands the water body and boundary features using expansion and adaptively compensates the transition region between the water body and boundary through information guidance. Finally, multi-level constraints are combined to realize the supervision of the decoupled features. Thus, the water body and boundaries can be extracted more accurately. A comparative validation analysis is conducted on the public datasets, including the gaofen image dataset (GID) and the gaofen2020 challenge dataset (GF2020). By comparing with seven SOTAs, the results show that the proposed method achieves the best results, with IOUs of 91.22 and 78.93, especially in the localization of water bodies and boundaries. By applying the proposed method in different scenarios, the results show the stable capability of the proposed method for extracting water with various shapes and areas.

A lightweight Mini-YOLOv5s algorithm for small target crack detection in tunnels

ABSTRACT The automatic detection and identification of tunnel cracks is very important for safe driving and tunnel maintenance. In order to accelerate the application of automated detection and reduce the deployment cost of target detection algorithm on edge devices, this paper adopts non-destructive testing and proposes a lightweight Mini-YOLOv5s algorithm for small target crack detection in tunnels, which mainly includes DP-C3 module, GDConv module, ECA-C3 module, CARAFE lightweight upsampling operator and loss function IGIoU. Among them, the DP-C3 module uses PConv to reduce the computational complexity of the model, and uses dilated convolution to enrich the receptive field to improve the information loss. The GDConv module improves the feature extraction capability of deep information. The feature fusion of small crack target information is realised by using ECA-C3 module and CARAFE lightweight up-sampling operator. A new loss function IGIoU is used to pay more attention to the contact degree of the boundary frame, so as to minimise the loss and improve the detection accuracy. Experiments show that the detection accuracy of Mini-YOLOv5s on self-made tunnel crack dataset reaches 91%, which compensates for the information loss, while the number of model parameters and GFLOPs are reduced by 35.4% and 30.4% respectively.

Kernel Density Estimation for the Interpretation of Seismic Big Data in Tectonics Using QGIS: The Türkiye–Syria Earthquakes (2023)

Numerous studies have utilized remote sensing techniques to analyze seismic data in active areas. Point density techniques, widely used in remote sensing, examine the spatial distribution of point clouds related to specific variables. Applying these techniques to complex tectonic settings, such as the East Anatolian Fault Zone, helps identify major active fractures using both surface and deep information. This study employed kernel density estimation (KDE) to compare two distinct point-cloud populations from the seismic event along the Türkiye–Syria border on 6 February 2023, providing insights into the main active orientations supporting the Global Tectonics framework. This study considered two populations of seismic foci point clouds containing over 40,000 events, recorded by the Turkish Disaster and Emergency Management Authority (AFAD) and Kandilli Observatory and Earthquake Research Institute (KOERI). These populations were divided into two datasets: crude and relocated-filtered. Kernel density analysis demonstrated that both datasets yielded similar geological interpretations. The high-density cores of both datasets perfectly matched, exhibiting identical structures consistent with geological knowledge. Areas with a minimal concentration of earthquakes at depth were also identified, separating different crustal strength levels.

Deep spatial-temporal information fusion dynamic graph convolutional network for traffic flow prediction

Abstract Predicting traffic flow is vital for advancing intelligent transportation systems, but achieving precise forecasts remains challenging. To deeply explore the complex and diverse dynamic spatio-temporal correlation of traffic data, this study proposes a multi-information fusion spatio-temporal dynamic graph convolution model for traffic flow prediction. In the model construction, firstly, a dynamic graph generation module is designed to fully capture the complex spatial correlation of the traffic network and model the changing spatio-temporal interaction; secondly, the spatial self-attention mechanism is used to dynamically focus on the spatial relationship between different nodes, and combined with the dynamic graph convolution network to extract the spatial dynamic correlation features of the road network to study deep spatiotemporal information; Finally, existing models rarely consider other traffic information related to traffic flow, and a spatiotemporal information fusion module is designed to enhance the ability of the model to perceive information, thereby improving the performance of traffic flow prediction models. Experiments are conducted on four real traffic datasets using three performance evaluation metrics and 18 baseline models. The results show that the model has higher prediction accuracy.

Aircraft skin defect detection algorithm based on improved YOLOv8

To solve the problem that the traditional aircraft skin defect detection relies on human eye observation, which leads to reduced efficiency due to human eye fatigue and limited individual cognition, an aircraft skin defect detection algorithm based on improved YOLOv8 is proposed. The data enhancement method is improved, and a slice reasoning + mosaic data enhancement method is proposed; the residual block is integrated into the feature extraction network to enhance the network expression ability and improve the accuracy of the model in the aircraft skin defect detection task; the three-branch (Triplet) attention module is applied to improve the feature fusion network to reduce the false detection rate and missed detection rate of small target samples; the structure of the detection head is optimized so that the network can better combine shallow information with deep information. Experimental results show that compared with the latest YOLOv8 algorithm, the improved algorithm improves the mean average precision (mAP) and recall rate (Recall) on the aircraft skin defect dataset by 3.6%and respectively 3.7%; and improves the mean average precision and recall rate on the public dataset VOC2007 by 2.9%and 2.2%.

Temporal-enhanced Radar and Camera Fusion for Object Detection

Recently, object detection methods based on multimodal fusion have gained widespread adoption in autonomous driving, proving to be valuable for detecting objects in dynamic environments. Among them, millimetre wave (mmWave) radar is commonly utilized as an effective complement to cameras, as it is almost unaffected by harsh weather conditions. However, current approaches that fuse mmWave radar and camera often overlook the correlation between the two modalities, failing to fully exploit their complementary features. To address this, we propose a temporal-enhanced radar and camera fusion network to explore the correlation between these two modalities and learn a comprehensive representation for object detection. In our model, a temporal fusion model is introduced to fuse mmWave radar features from different moments, thus mitigating the problem of mmWave radar point-object mismatch due to object movement. Moreover, a new correlation-based fusion strategy using the dedicated mask cross attention is proposed to fuse mmWave radar and vision features more effectively. Finally, we design a gate feature pyramid network that selects shallow texture information based on deep semantic information to obtain more representative features. The experimental results on the nuScenes benchmark demonstrate the effectiveness of our proposed method.

Facial expression recognition based on convolutional network attention mechanism

Aiming at the problems of large number of parameters and weak recognition ability in expression recognition, a method of facial expression recognition based on convolutional network is proposed. An improved residual module is introduced to reduce the number of parameters while enhancing the attention to the expression area; the channel-space attention mechanism is used to realize the weight distribution of different dimensions and positions of the expression area extracted by the network, focusing on the subtle difference feature information in the key points of the expression; the detail module is used to further extract the deep feature information. In order to obtain higher accuracy, a joint loss function is introduced to increase the out-of-class distance and reduce the intra-class distance to improve the accuracy of expression recognition. This paper applies this network to the datasets FER2013 and CK+. The experimental results show that the average recognition rate of this algorithm is respectively and 63.91%，97.98%the number of parameters is 11.34 M. Compared with VGG network, residual network, etc., this model not only improves the recognition rate but also reduces the redundant parameters.

Deep Information Retention Network‐Enabled Data Modeling for Key Quality Indicator Prediction in the Chemical Industry

ABSTRACTDeep learning has attracted widespread attention in data modeling and key quality indicator prediction in the chemical industry. However, traditional deep learning networks usually distort the original data distribution due to the superposition effect of multiple layers of nonlinear activation functions. In this case, multivariate statistical learning techniques present an avenue to reveal the intrinsic relationship of the data by combining the linear trends between input and predictor variables. To comprehensively capture data features from multiple perspectives, this study proposes a deep learning‐based data modeling network called the information retention unit (IRU). This network combines intrinsic attributes to partial least squares (PLS) and autoencoder (AE) modalities, thus engendering an adaptive response to the complex linear and nonlinear data features. Furthermore, multiple IRUs can be stacked to construct a deep information retention network (DIRN), which enhances the robust extraction of deep data features. Finally, the effectiveness of the proposed network is validated through its prediction application on a dataset obtained from a real‐world chemical industrial process. This method combines multivariate statistical learning techniques based on deep learning, providing an innovative and practical solution for data analysis and prediction in the chemical industry.

Vehicle and Pedestrian Detection Based on Improved YOLOv7-Tiny

To improve the detection accuracy of vehicles and pedestrians in traffic scenes using object detection algorithms, this paper presents modifications, compression, and deployment of the single-stage typical algorithm YOLOv7-tiny. In the model improvement section: firstly, to address the problem of small object missed detection, shallower feature layer information is incorporated into the original feature fusion branch, forming a four-scale detection head; secondly, a Multi-Stage Feature Fusion (MSFF) module is proposed to fully integrate shallow, middle, and deep feature information to extract more comprehensive small object information. In the model compression section: the Layer-Adaptive Magnitude-based Pruning (LAMP) algorithm and the Torch-Pruning library are combined, setting different pruning rates for the improved model. In the model deployment section: the V7-tiny-P2-MSFF model, pruned by 45% using LAMP, is deployed on the embedded platform NVIDIA Jetson AGX Xavier. Experimental results show that the improved and pruned model achieves a 12.3% increase in mAP@0.5 compared to the original model, with parameter volume, computation volume, and model size reduced by 76.74%, 7.57%, and 70.94%, respectively. Moreover, the inference speed of a single image for the pruned and quantized model deployed on Xavier is 9.5 ms.

Learning With Board Games: Interplay of Context and Students’ Prior Knowledge

Board games can support engagement, deep information processing and learning outcomes for university students. The instructional context, notably the way an activity is introduced to students, can influence students’ behavior and learning outcomes. Yet, despite its potential important influence on in-game behavior and learning, the impact of the instructional context used to introduce a game-based learning activity has not received much attention. In two studies, we examined how framing a game-based learning activity with a serious or a non-serious context can impact university students’ behavior and learning outcomes. In the first study, 44 graduate students played the same word association game that was either introduced as a game or as a study activity. Results showed that the serious context increased recall as compared to the gaming context. In the second study, involving 87 participants playing the same game, results showed that the gaming context and prior gaming experience also reduced students’ recall. Overall, grouped analysis showed that the gaming context led to poorer learning than the serious context for recognition and recall measures, even when considering prior knowledge, in-game behavior, and prior gaming experience. Theoretical and practical implications for educators are discussed.