Convolution Method Research Articles

Field cabbage detection and positioning system based on improved YOLOv8n

BackgroundPesticide efficacy directly affects crop yield and quality, making targeted spraying a more environmentally friendly and effective method of pesticide application. Common targeted cabbage spraying methods often involve object detection networks. However, complex natural and lighting conditions pose challenges in the accurate detection and positioning of cabbage.ResultsIn this study, a cabbage detection algorithm based on the YOLOv8n neural network (YOLOv8-cabbage) combined with a positioning system constructed using a Realsense depth camera is proposed. Initially, four of the currently available high-performance object detection models were compared, and YOLOv8n was selected as the transfer learning model for field cabbage detection. Data augmentation and expansion methods were applied to extensively train the model, a large kernel convolution method was proposed to improve the bottleneck section, the Swin transformer module was combined with the convolutional neural network (CNN) to expand the perceptual field of feature extraction and improve edge detection effectiveness, and a nonlocal attention mechanism was added to enhance feature extraction. Ablation experiments were conducted on the same dataset under the same experimental conditions, and the improved model increased the mean average precision (mAP) from 88.8% to 93.9%. Subsequently, depth maps and colour maps were aligned pixelwise to obtain the three-dimensional coordinates of the cabbages via coordinate system conversion. The positioning error of the three-dimensional coordinate cabbage identification and positioning system was (11.2 mm, 10.225 mm, 25.3 mm), which meets the usage requirements.ConclusionsWe have achieved accurate cabbage positioning. The object detection system proposed here can detect cabbage in real time in complex field environments, providing technical support for targeted spraying applications and positioning.

Vision transformer-based robust learning for cloth-changing person re-identification

The domain of Cloth-Changing Person Re-identification has garnered substantial attention recently owing to its pivotal role in security applications. The essence of Cloth-Changing Person Re-identification lies in acquiring information unaffected by clothing variations, such as gait and silhouette. Most studies focus on the Convolutional Neural Network models. However, main drawback of Convolutional Neural Network is the limitation of receptive field. Methods based on Convolutional Neural Network primarily focus on modeling local information, making it complex to extract the discriminative part of multiple spatial contexts. Therefore, we proposed a Vision Transformer-based Cloth-Changing Person Re-identification framework called TransRL-ReID. Specifically, we encoded an image as a sequence of patches and constructed a Vision Transformer-based framework. In addition, a module named DropAll was designed to reduce local bias by adaptive adjustment of attention weights for each patch. We conducted extensive experiments on the real-world benchmark PRCC dataset. TransRL-ReID achieves 66.7% on Rank-1 and 60.0% on mean Average Precision, outperforming previous Convolutional Neural Network-based methods. After visual analysis of the results, we found that TransReID could extract information unrelated to clothing, such as gait and silhouette, and paid less attention to clothing information. DropAll improves the model’s ability to fit pedestrian distributions.

Internet street view image fusion method using convolutional neural network

The use of image fusion technology in the area of information processing is continuing to advance in depth thanks to ongoing hardware advancements and related research. An enhanced convolutional neural network approach is developed to fuse visible and infrared images, and image pre-processing is carried out utilising an image alignment method with edge detection in order to gain more accurate and trustworthy image information. The performance of the fast wavelet decomposition, convolutional neural network, and modified convolutional neural network techniques is compared and examined using four objective assessment criteria. The experimental findings demonstrated that the picture alignment was successful with an offset error of fewer than 3 pixels in the horizontal direction and an angle error of less than 0.3∘ in both directions. The revised convolutional neural network method increased the information entropy, mean gradient, standard deviation, and edge detection information by an average of 46.13%, 39.40%, 19.91%, and 3.72%. The runtime of the modified approach was lowered by 19.42% when compared to the convolutional neural network method, which enhanced the algorithm’s performance and boosted the effectiveness of picture fusion. The image fusion accuracy reached 98.61%, indicating that the method has better fusion performance and is of practical value for improving image fusion quality.

Multi kernel cross sparse graph attention convolutional neural network for brain magnetic resonance imaging super-resolution

High-resolution Magnetic Resonance Imaging (MRI) is pivotal in both diagnosing and treating brain tumors, assisting physicians in diagnosis and treatment by displaying anatomical structures. Utilizing convolutional neural network-based super-resolution methods enables the efficient acquisition of high-resolution MRI images.However, Convolutional neural networks are limited by their kernel size, which restricts their ability to capture a wider field of view, potentially leading to feature omission and difficulties in establishing global and local feature relationships. To overcome these shortcomings, We have designed a novel network architecture that highlights three main modules: (i) Multiple Convolutional Feature (MCF)extraction module, which diversifies convolution operations for extracting image features, achieving comprehensive feature representation. (ii) Multiple Groupss of Cross-Iterative Feature(MGCIF) modules, promoting inter-channel feature interactions and emphasizing crucial features needed for subsequent learning. (iii) A Graph Neural Network Module based on a sparse attention mechanism, capable of connecting distant pixel features and identifying influential neighboring pixels for target pixel inpainting. To evaluate the accuracy of our proposed network, we conducted tests on four datasets, comprising two sets of brain tumor data and two sets of healthy head MRI data, all of which underwent varying degrees of degradation. We conducted experiments using nineteen super-resolution (SR) models. Our experiments were carried out on four datasets, and the results demonstrate that our method outperforms the current leading-edge methods. In the four datasets, our model showed improvements in Peak Signal-to-Noise Ratio (PSNR) scores compared to the second-place model,with increase of 1.16 %,1.08 %,0.19 % and 0.53 % for ×2,and 2.26 %,1.67 %,0.13 % and 0.45 % for × 4,respectively.

An Improved Unbounded-DP Algorithm for the Unbounded Knapsack Problem with Bounded Coefficients

Benchmark instances for the unbounded knapsack problem are typically generated according to specific criteria within a given constant range R, and these instances can be referred to as the unbounded knapsack problem with bounded coefficients (UKPB). In order to increase the difficulty of solving these instances, the knapsack capacity C is usually set to a very large value. While current efficient algorithms primarily center on the Fast Fourier Transform (FFT) and (min,+)-convolution method, there is a simpler method worth considering. In this paper, based on the basic Unbounded-DP algorithm, we utilize a recent branch and bound (B&B) result and basic theory of linear Diophantine equation, and propose an improved Unbounded-DP algorithm with time complexity of O(R4) and space complexity of O(R3). Additionally, the algorithm can also solve the All-capacities unbounded knapsack problem within the complexity O(R4+C). In particular, the proof techniques required by the algorithm are primarily covered in the first-year mathematics curriculum, which is convenient for subsequent researchers to grasp.

Similarity-based Graph Convolution Collaborative Recommendation Approach

With the rapid and iterative development of science and technology, a large amount of information exceeds the range that can be accepted, processed, or effectively utilized by an individual or a system, and recommendation algorithms can, to a certain extent, solve such problems, but traditional recommendation algorithms do not have a good solution to the problems related to data sparsity and recommendation accuracy. A similarity-based graph convolutional neural collaborative recommendation method (GCSCF) is proposed. The similarity algorithm based on the attributes of the item is used to find the item with the highest similarity and has not interacted with the current user, and this item is set to interact with the current user. The relevant interaction information of the user and the item is converted into relative feature vectors; the feature vectors are propagated using a graph convolutional neural network to aggregate the localized information, and the weight coefficients based on the item ratings are normalized to reduce the noise caused by the information aggregation. Comparative experiments are conducted on two public datasets, MovieLens-1M and Movielens-100K, with five baseline models on the set, and using Recall, Normalized Discounted Cumulative Gain (NDCG), and Precision as the evaluation metrics, and the results of the experiments show that the performance of the proposed social recommendation model better than other models.

Brain-computer interfaces inspired spiking neural network model for depression stage identification

BackgroundDepression is a global mental disorder, and traditional diagnostic methods mainly rely on scales and subjective evaluations by doctors, which cannot effectively identify symptoms and even carry the risk of misdiagnosis. Brain-Computer Interfaces inspired deep learning-assisted diagnosis based on physiological signals holds promise for improving traditional methods lacking physiological basis and leads next generation neuro-technologies. However, traditional deep learning methods rely on immense computational power and mostly involve end-to-end network learning. These learning methods also lack physiological interpretability, limiting their clinical application in assisted diagnosis. MethodologyA brain-like learning model for diagnosing depression using electroencephalogram (EEG) is proposed. The study collects EEG data using 128-channel electrodes, producing a 128×128 brain adjacency matrix. Given the assumption of undirected connectivity, the upper half of the 128×128 matrix is chosen in order to minimise the input parameter size, producing 8,128-dimensional data. After eliminating 28 components derived from irrelevant or reference electrodes, a 90×90 matrix is produced, which can be used as an input for a single-channel brain-computer interface image. ResultAt the functional level, a spiking neural network is constructed to classify individuals with depression and healthy individuals, achieving an accuracy exceeding 97.5 %. Comparison with existing methodsCompared to deep convolutional methods, the spiking method reduces energy consumption. ConclusionAt the structural level, complex networks are utilized to establish spatial topology of brain connections and analyse their graph features, identifying potential abnormal brain functional connections in individuals with depression.

An Improved Ningxia Desert Herbaceous Plant Classification Algorithm Based on YOLOv8.

Wild desert grasslands are characterized by diverse habitats, uneven plant distribution, similarities among plant class, and the presence of plant shadows. However, the existing models for detecting plant species in desert grasslands exhibit low precision, require a large number of parameters, and incur high computational cost, rendering them unsuitable for deployment in plant recognition scenarios within these environments. To address these challenges, this paper proposes a lightweight and fast plant species detection system, termed YOLOv8s-KDT, tailored for complex desert grassland environments. Firstly, the model introduces a dynamic convolutional KernelWarehouse method to reduce the dimensionality of convolutional kernels and increase their number, thus achieving a better balance between parameter efficiency and representation ability. Secondly, the model incorporates triplet attention into its feature extraction network, effectively capturing the relationship between channel and spatial position and enhancing the model's feature extraction capabilities. Finally, the introduction of a dynamic detection head tackles the issue related to target detection head and attention non-uniformity, thus improving the representation of the target detection head while reducing computational cost. The experimental results demonstrate that the upgraded YOLOv8s-KDT model can rapidly and effectively identify desert grassland plants. Compared to the original model, FLOPs decreased by 50.8%, accuracy improved by 4.5%, and mAP increased by 5.6%. Currently, the YOLOv8s-KDT model is deployed in the mobile plant identification APP of Ningxia desert grassland and the fixed-point ecological information observation platform. It facilitates the investigation of desert grassland vegetation distribution across the entire Ningxia region as well as long-term observation and tracking of plant ecological information in specific areas, such as Dashuikeng, Huangji Field, and Hongsibu in Ningxia.

Enhancing the seismic response of faults by using a deep learning‐based method

AbstractThe accuracy of fault interpretation is generally influenced by the quality of seismic images. Because of the blurring effect of the migration process, faults with small throws may not be clearly imaged in seismic images, which will impose limitations on the fault detection. To address this issue, we propose a deep learning‐based method to enhance faults in poststack seismic images. We generate abundant training samples by convolving the three‐dimensional point‐spread functions with the noisy reflectivity models. The corresponding labels are synthesized using the one‐dimensional seismic wavelet convolution method, simulating conditions with perfect illumination. To train the network for optimal performance, we investigate the impact of different loss functions. Ultimately, we employ a mixed loss function combining structural similarity index measure and gradient difference loss, since the gradient difference loss focuses more on geological edge information, and the structural similarity index measure possesses excellent image perceptual capability and optimization property. Results from one synthetic seismic image and three real seismic data demonstrate that our proposed method can effectively restore the sharpness of fault surfaces, particularly for faults with small displacements. Compared to the structural smoothing method, the network we trained achieves optimal fault enhancement. Furthermore, coherence‐based fault images indicate that seismic images enhanced using our method can improve the accuracy of fault interpretation and yield more continuous fault maps.

An optimized framework for metal ion analysis in automobile industrial sewage

This research paper presents an optimized approach for analyzing metal ions in automobile industrial sewage by integrating Dove Swarm Optimization (DSO) and a Recurrent Neural Network (RNN), termed DSbRNM. The DSbRNM approach is designed to detect and predict the concentration of metal ions in sewage samples. DSO is utilized to select the most relevant features, optimizing the feature set for the RNN. This optimization allows the RNN to perform classification with high accuracy, predicting metal ion concentrations effectively. The effectiveness of the DSbRNM approach was validated by analyzing real industrial sewage samples and comparing the results with those obtained using machine learning (ML) based convolutional methods. The results demonstrate that DSbRNM provides more accurate and reliable predictions of metal ion ranges. Furthermore, DSbRNM outperformed convolutional methods in terms of accuracy, recall, precision, and F1 score. The DSbRNM approach offers a rapid and effective solution for analyzing metal ions in automobile industrial sewage, enhancing the efficiency and effectiveness of wastewater treatment processes.

LGC-DBP: the method of DNA-binding protein identification based on PSSM and deep learning.

The recognition of DNA Binding Proteins (DBPs) plays a crucial role in understanding biological functions such as replication, transcription, and repair. Although current sequence-based methods have shown some effectiveness, they often fail to fully utilize the potential of deep learning in capturing complex patterns. This study introduces a novel model, LGC-DBP, which integrates Long Short-Term Memory (LSTM), Gated Inception Convolution, and Improved Channel Attention mechanisms to enhance the prediction of DBPs. Initially, the model transforms protein sequences into Position Specific Scoring Matrices (PSSM), then processed through our deep learning framework. Within this framework, Gated Inception Convolution merges the concepts of gating units with the advantages of Graph Convolutional Network (GCN) and Dilated Convolution, significantly surpassing traditional convolution methods. The Improved Channel Attention mechanism substantially enhances the model's responsiveness and accuracy by shifting from a single input to three inputs and integrating three sigmoid functions along with an additional layer output. These innovative combinations have significantly improved model performance, enabling LGC-DBP to recognize and interpret the complex relationships within DBP features more accurately. The evaluation results show that LGC-DBP achieves an accuracy of 88.26% and a Matthews correlation coefficient of 0.701, both surpassing existing methods. These achievements demonstrate the model's strong capability in integrating and analyzing multi-dimensional data and mark a significant advancement over traditional methods by capturing deeper, nonlinear interactions within the data.

Leveraging optimal UAV-lidar features for two CNN approaches to delineate mangrove tree crowns

Effective individual tree crown delineation plays a critical role for assessing mangrove quality and health. However, mangrove tree crowns often form large, interconnected clusters in dense coverage areas, making it difficult to separate them individually. Moreover, many mangrove trees have multiple large branches that result in irregular tree shapes and create internal gaps inside their crowns. Unmanned Aerial Vehicle (UAV) lidar data can potentially overcome these challenges, but a comprehensive assessment of UAV-lidar-derived features is still missing, as well as how to best use them for dense mangrove forests. In this study, we set forth two objectives: (1) to derive optimal features for mangrove individual tree crown delineation through an exclusive examination of all the UAV-lidar features; (2) to develop effective methods that can best incorporate these optimal UAV-lidar features. To achieve the first objective, we extracted 224 features from UAV-lidar data based on three groups of attributes: height, intensity, and point density. Seven spatial scales ranging from 0.2 to 0.5 m were tested in this process. For the second objective, we applied two state-of-the-art Convolutional Neural Networks: Mask Region-based Convolutional Network method (Mask R–CNN) and Ultralytics You Only Look Once version 8 (YOLOv8). At last, the derived three optimal features are: canopy height model at 0.20 m, coefficient of point cloud height variation at 0.25 m, and ground point percentage at 0.25 m. Comparing our methods with traditional methods that only use canopy height model, we found that integrating Convolutional Neural Networks and the optimal UAV-lidar features improved the accuracy by more than 13%. Mask R–CNN was better for dense mangroves, while YOLOv8 was excellent for sparse and short mangroves. The derived optimal UAV-lidar features further enhanced the detection of short trees, densely clumped trees and trees with irregular shapes. To conclude, we developed three novel features based on UAV-lidar data that are especially suitable for individual tree crown delineation in dense mangrove forests. Using these features, we demonstrated that Convolutional Neural Networks can achieve high performance. We hope that our methods will facilitate various mangrove forest studies that rely on accurate individual tree crown delineation.

Small target tea bud detection based on improved YOLOv5 in complex background.

Tea bud detection is the first step in the precise picking of famous teas. Accurate and fast tea bud detection is crucial for achieving intelligent tea bud picking. However, existing detection methods still exhibit limitations in both detection accuracy and speed due to the intricate background of tea buds and their small size. This study uses YOLOv5 as the initial network and utilizes attention mechanism to obtain more detailed information about tea buds, reducing false detections and missed detections caused by different sizes of tea buds; The addition of Spatial Pyramid Pooling Fast (SPPF) in front of the head to better utilize the attention module's ability to fuse information; Introducing the lightweight convolutional method Group Shuffle Convolution (GSConv) to ensure model efficiency without compromising accuracy; The Mean-Positional-Distance Intersection over Union (MPDIoU) can effectively accelerate model convergence and reduce the training time of the model. The experimental results demonstrate that our proposed method achieves precision (P), recall rate (R) and mean average precision (mAP) of 93.38%, 89.68%, and 95.73%, respectively. Compared with the baseline network, our proposed model's P, R, and mAP have been improved by 3.26%, 11.43%, and 7.68%, respectively. Meanwhile, comparative analyses with other deep learning methods using the same dataset underscore the efficacy of our approach in terms of P, R, mAP, and model size. This method can accurately detect the tea bud area and provide theoretical research and technical support for subsequent tea picking.

Face recognition for smart door security access with convolutional neural network method

Face recognition for smart door security access with convolutional neural network method

Image Classification of Traditional Indonesian Cakes Using Convolutional Neural Network (CNN)

Indonesia is one of the countries famous for its traditional culinary. Traditional cakes in Indonesia are traditional snacks typical of the archipelago's culture which have a variety of textures, shapes, colors that vary and some are similar so that there are still many people who do not know the name of the cake from the many types of traditional Indonesian cakes. The problem can be solved by creating a traditional cake image recognition system that can be programmed and trained to classify various types of traditional Indonesian cakes. The Convolutional Neural Network method with the AlexNet architecture model is used in this research to predict various kinds of traditional Indonesian cakes. The dataset used in this research is 1846 datasets with 8 classes of cake images. This study trained the AlexNet model with several optimizers, namely, Adam optimizer, SGD, and RMSprop. The best parameters from the model testing results are at batchsize 16, epoch 50, learning rate 0.01 for SGD optimizer and learning rate 0.001 for Adam and RMSprop optimizers. Each optimizer tested produces different accuracy, precision, recall, and f1_score values. The highest test results that have been carried out on the image dataset of typical Indonesian traditional cakes are obtained by the Adam optimizer with an accuracy value of 79%.

Estimating receptive fields of simple and complex cells in early visual cortex: A convolutional neural network model with parameterized rectification.

Neurons in the primary visual cortex respond selectively to simple features of visual stimuli, such as orientation and spatial frequency. Simple cells, which have phase-sensitive responses, can be modeled by a single receptive field filter in a linear-nonlinear model. However, it is challenging to analyze phase-invariant complex cells, which require more elaborate models having a combination of nonlinear subunits. Estimating parameters of these models is made additionally more difficult by cortical neurons' trial-to-trial response variability. We develop a simple convolutional neural network method to estimate receptive field models for both simple and complex visual cortex cells from their responses to natural images. The model consists of a spatiotemporal filter, a parameterized rectifier unit (PReLU), and a two-dimensional Gaussian "map" of the receptive field envelope. A single model parameter determines the simple vs. complex nature of the receptive field, capturing complex cell responses as a summation of homogeneous subunits, and collapsing to a linear-nonlinear model for simple type cells. The convolutional method predicts simple and complex cell responses to natural image stimuli as well as grating tuning curves. The fitted models yield a continuum of values for the PReLU parameter across the sampled neurons, showing that the simple/complex nature of cells can vary in a continuous manner. We demonstrate that complex-like cells respond less reliably than simple-like cells. However, compensation for this unreliability with noise ceiling analysis reveals predictive performance for complex cells proportionately closer to that for simple cells. Most spatial receptive field structures are well fit by Gabor functions, whose parameters confirm well-known properties of cat A17/18 receptive fields.

Identification of Rice Plant Diseases Using Convolutional Neural Network Method

Identification of Rice Plant Diseases Using Convolutional Neural Network Method

A Convolutional Neural Network-Based Quantization Method for Block Compressed Sensing of Images.

Block compressed sensing (BCS) is a promising method for resource-constrained image/video coding applications. However, the quantization of BCS measurements has posed a challenge, leading to significant quantization errors and encoding redundancy. In this paper, we propose a quantization method for BCS measurements using convolutional neural networks (CNN). The quantization process maps measurements to quantized data that follow a uniform distribution based on the measurements' distribution, which aims to maximize the amount of information carried by the quantized data. The dequantization process restores the quantized data to data that conform to the measurements' distribution. The restored data are then modified by the correlation information of the measurements drawn from the quantized data, with the goal of minimizing the quantization errors. The proposed method uses CNNs to construct quantization and dequantization processes, and the networks are trained jointly. The distribution parameters of each block are used as side information, which is quantized with 1 bit by the same method. Extensive experiments on four public datasets showed that, compared with uniform quantization and entropy coding, the proposed method can improve the PSNR by an average of 0.48 dB without using entropy coding when the compression bit rate is 0.1 bpp.

Enhancing Safety and Workover Efficiency Through Real-Time Scale-Adaptive Video Detection of Critical Objects at the Wellsite

Summary The wellsite serves as the fundamental unit in the development of oil and gas fields, functioning as a hub for the production activities, with workover operations being a critical means to ensure production continuity. In addition, it plays a crucial role in environmental protection, preventing oil and gas leakage and pollution. Various pieces of mechanical equipment deployed at the wellsite are essential for tasks such as oil and gas extraction and well repair operations, holding a pivotal position in oil- and gasfield development. Consequently, intelligent wellsite implementation necessitates a primary focus on monitoring mechanical equipment, with video emerging as a vital form of multisource information at the wellsite. While existing research on wellsite video monitoring predominantly addresses system and data transmission issues, it falls short in addressing the challenges of real-time assessment and early warning in intelligent wellsite operations. This study introduces a method for identifying critical targets at the wellsite based on a scale-adaptive network. The model employs a multiscale fusion network to extract different image features and semantic features at various scales, facilitating their fusion. The processing of wellsite video images occurs in multiple stages, outputting predicted box locations and category information, enabling the localization and recognition of critical objects at the wellsite. Unlike traditional deep convolutional object detection methods, this model incorporates a parameter-free attention mechanism, enhancing the accurate feature learning of small targets during the extraction process and addressing the issue of multiscale imbalance. The experimental results validate the robust performance of the method, surpassing the latest one-stage object detection models and mainstream loss function methods. Comparative experiments demonstrate a 9.22% improvement in mean average precision (mAP) compared with YOLOv8, establishing the proposed model as a top performer in loss function optimization experiments. Furthermore, we propose a video security detection model whose results, combined with the recognition model, are applicable for video detection in wellsite scenarios. The model exhibits strong integration capabilities for scene area division and behavior regulation monitoring. In addition, the model provides valuable insights for analyzing equipment operating status, aligning with the practical needs of oil fields.

Photonic envelope convolver based on time-domain convolution method

A photonic approach of temporal convolver is proposed and experimentally demonstrated. Different from traditional schemes, the photonic envelope convolution can be achieved by time-domain convolution method, which includes three steps of time-domain Fourier transform, multiplication and inverse Fourier transform. The feasibility of the system is verified by theoretical analysis and simulation. The proposed temporal convolution is experimentally evaluated, in which three temporal convolution results between two rectangular signals, between a rectangular signal and a sawtooth signal, and between two sawtooth signals are successfully obtained, which agree with the theoretical analysis well. Because the time-domain Fourier transform and multiplication can be easily implemented through dispersion mediums and modulation devices respectively, the proposed system has advantages of simple configuration, easy operation, reconfigurability and cost-effectiveness. It provides a new access to achieving convolution operation.