Enhanced Feature Extraction 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.

Building Materials Classification Model Based on Text Data Enhancement and Semantic Feature Extraction

In order to accurately extract and match carbon emission factors from the Chinese textual building materials list and construct a precise carbon emission factor database, it is crucial to accurately classify the textual building materials. In this study, a novel classification model based on text data enhancement and semantic feature extraction is proposed and applied for building materials classification. Firstly, the explanatory information on the building materials is collected and normalized to construct the original dataset. Then, the Latent Dirichlet Allocation and statistical-language-model-based hybrid ensemble data enhancement methods are explained in detail, and the semantic features closely related to the carbon emission factor are extracted by constructed composite convolutional networks and the transformed word vectors. Finally, the ensemble classification model is designed, constructed, and applied to match the carbon emission factor from the textual building materials. The experimental results show that the proposed model improves the F1Macro score by 4–12% compared to traditional machine learning and deep learning models.

A Deep Transfer Learning Model for the Fault Diagnosis of Double Roller Bearing Using Scattergram Filter Bank 1

In this study, a deep transfer learning model was developed using ResNet-101 architecture to diagnose double roller bearing defects. Vibration data were collected for three different load scenarios, including conditions without load, and for five different rotational speeds, ranging from 500 to 2500 RPM. Significantly, the speed condition of 2500 RPM has not previously been investigated, therefore offering a potential avenue for future investigations. This study offers a thorough examination of bearing conditions using multidirectional vibration data collected from accelerometers positioned in both vertical and horizontal orientations. In addition to transfer learning using ResNet-101, four additional models (VGG-16, VGG19, ResNet-18, and ResNet-50) were trained. Transfer learning using ResNet-101 consistently achieved the highest accuracy in all scenarios, with accuracy rates ranging from 90.78% to 99%. Scattergram Filter Bank 1 was used as the image input for training as a preprocessing method to enhance feature extraction. Research has effectively applied transfer learning to improve fault diagnosis accuracy, especially in limited data scenarios. This shows the capability of the method to differentiate between normal and faulty bearing conditions using signal-to-image transformation, emphasizing the potential of transfer learning to augment diagnostic performance in scenarios with limited training data.

Semi-Supervised Autoencoder for Chemical Gas Classification with FTIR Spectrum.

Chemical warfare agents pose a serious threat due to their extreme toxicity, necessitating swift the identification of chemical gases and individual responses to the identified threats. Fourier transform infrared (FTIR) spectroscopy offers a method for remote material analysis, particularly in detecting colorless and odorless chemical agents. In this paper, we propose a deep neural network utilizing a semi-supervised autoencoder (SSAE) for the classification of chemical gases based on FTIR spectra. In contrast to traditional methods, the SSAE concurrently trains an autoencoder and a classifier attached to a latent vector of the autoencoder, enhancing feature extraction for classification. The SSAE was evaluated on laboratory-collected FTIR spectra, demonstrating a superior classification performance compared to existing methods. The efficacy of the SSAE lies in its ability to generate denser cluster distributions in latent vectors, thereby enhancing gas classification. This study established a consistent experimental environment for hyperparameter optimization, offering valuable insights into the influence of latent vectors on classification performance.

Swift Detection of XSS Attacks: Enhancing XSS Attack Detection by Leveraging Hybrid Semantic Embeddings and AI Techniques

AbstractCross-Site Scripting (XSS) attacks continue to be a significant threat to web application security, necessitating robust detection mechanisms to safeguard user data and ensure system integrity. In this study, we present a novel approach for detecting XSS attacks that harnesses the combined capabilities of the Universal Sentence Encoder (USE) and Word2Vec embeddings as a feature extractor, aiming to enhance the performance of machine learning and deep learning techniques. By leveraging the semantic understanding of sentences offered by USE and the word-level representations from Word2Vec, we obtain a comprehensive feature representation for XSS attack payloads. Our proposed approach aims to capture both fine-grained word meanings and broader sentence contexts, leading to enhanced feature extraction and improved model performance. We conducted extensive experiments utilizing machine learning and deep learning architectures to evaluate the effectiveness of our approach. The obtained results demonstrate that our combined embeddings approach outperforms traditional methods, achieving superior accuracy, precision, recall, ROC, and F1-score in detecting XSS attacks. This study not only advances XSS attack detection but also highlights the potential of state-of-the-art natural language processing techniques in web security applications. Our findings offer valuable insights for the development of more robust and effective security measures against XSS attacks.

Automated segmentation of liver tumors from computed tomographic scans

The precision of liver tumor segmentation heavily depends on the doctor's expertise, hence it is required to produce an algorithm for automatic liver tumor segmentation to reduce the manual intervention in assessing liver disease identification. We propose a CNN-based UNet architecture designed to segment liver tumors from CT images of size 128×128. In this model, modifications were made to the encoder, decoder, and bridge paths to enhance feature extraction efficiency. The performance of the modified UNet was evaluated against an existing segmentation method using the same CT image size. The comparison focused on the Dice similarity coefficient and accuracy. Our proposed method demonstrated a high Dice similarity coefficient of 75.37 % and an accuracy of 99.75 % on the 3Dircadb dataset. These results indicate that our modified UNet achieved superior segmentation metrics compared to state-of-the-art methods, showcasing its effectiveness in liver tumor segmentation.

Learning to generalize with latent embedding optimization for few- and zero-shot cross domain fault diagnosis

Ensuring the safety and reliability of rotating machinery in modern industrial production and intelligent manufacturing is of paramount importance. While deep learning-based fault diagnosis methods offer promise, the scarcity of fault samples and the variations in distributions between training and test data due to variable working conditions make it difficult for these methods to be applied in industrial scenarios. To surmount these obstacles, we present a novel solution: learning to generalize with latent embedding optimization. Our proposed method, tailored for few-shot and zero-shot cross domain fault diagnosis, shows promise in addressing the industrial fault diagnosis problems under small samples and various working condition. The proposed method builds upon the latent embedding optimization algorithm which capitalizes on the essence of meta-learning, effectively addressing few-shot challenges. Additionally, we harness an efficient pretraining model, enhancing feature extraction and domain adaptation, effectively handling the scarcity of fault data. In tackling the cross domain issue, we introduce an innovative meta-task organization and amplify the episode training strategy within meta-learning. These enhancements empower the model to develop the ability to generalize effectively. The proposed approach is substantiated through comprehensive case studies in bearing and gearbox fault diagnosis. The results demonstrate its exceptional efficacy in both few-shot and zero-shot cross domain fault diagnosis scenarios.

APHS-YOLO: A Lightweight Model for Real-Time Detection and Classification of Stropharia Rugoso-Annulata.

The classification of Stropharia rugoso-annulata is currently reliant on manual sorting, which may be subject to bias. To improve the sorting efficiency, automated sorting equipment could be used instead. However, sorting naked mushrooms in real time remains a challenging task due to the difficulty of accurately identifying, locating and sorting large quantities of them simultaneously. Models must be deployable on resource-limited devices, making it challenging to achieve both a high accuracy and speed. This paper proposes the APHS-YOLO (YOLOv8n integrated with AKConv, CSPPC and HSFPN modules) model, which is lightweight and efficient, for identifying Stropharia rugoso-annulata of different grades and seasons. This study includes a complete dataset of runners of different grades in spring and autumn. To enhance feature extraction and maintain the recognition accuracy, the new multi-module APHS-YOLO uses HSFPNs (High-Level Screening Feature Pyramid Networks) as a thin-neck structure. It combines an improved lightweight PConv (Partial Convolution)-based convolutional module, CSPPC (Integration of Cross-Stage Partial Networks and Partial Convolution), with the Arbitrary Kernel Convolution (AKConv) module. Additionally, to compensate for the accuracy loss due to lightweighting, APHS-YOLO employs a knowledge refinement technique during training. Compared to the original model, the optimized APHS-YOLO model uses 57.8% less memory and 62.5% fewer computational resources. It has an FPS (frames per second) of over 100 and even achieves 0.1% better accuracy metrics than the original model. These research results provide a valuable reference for the development of automatic sorting equipment for forest farmers.

WTBD-YOLOv8: An Improved Method for Wind Turbine Generator Defect Detection

Wind turbine blades are the core components responsible for efficient wind energy conversion and ensuring stability. To address challenges in wind turbine blade damage detection using image processing techniques such as complex image backgrounds, decreased detection performance due to high image resolution, prolonged inference time, and insufficient recognition accuracy, this study introduces an enhanced wind turbine blade damage detection model named WTDB-YOLOv8. Firstly, by incorporating the GhostCBS and DFSB-C2f modules, the aim is to reduce the number of model parameters while enhancing feature extraction capability. Secondly, by integrating the MHSA-C2f module, which incorporates a multi-head self-attention mechanism, the focus on global information is enabled, thereby mitigating irrelevant background interference and reducing the impact of complex backgrounds on damage detection. Lastly, adopting the Mini-BiFPN structure improves the retention of features for small target objects in shallow networks and reinforces the propagation of these features in deep networks, thereby enhancing the detection accuracy of small target damage and reducing false negative rates. Through training and testing on the Wind Turbine Blade Damage Dataset (WTBDD), the WTDB-YOLOv8 model achieves an average precision of 98.3%, representing a 2.2 percentage point improvement over the original YOLOv8 model. Particularly noteworthy is the increase in precision from 93.1% to 97.9% in small target damage detection. Moreover, the total parameter count of the model decreases from 3.22 million in YOLOv8 to 1.99 million, marking a reduction of 38.2%. Therefore, the WTDB-YOLOv8 model not only enhances the detection performance and efficiency of wind turbine blade damage but also significantly reduces the model parameter count, showcasing its practical advantages in engineering applications.

The Fault Diagnosis of Rolling Bearings Is Conducted by Employing a Dual-Branch Convolutional Capsule Neural Network.

Currently, many fault diagnosis methods for rolling bearings based on deep learning are facing two main challenges. Firstly, the deep learning model exhibits poor diagnostic performance and limited generalization ability in the presence of noise signals and varying loads. Secondly, there is incomplete utilization of fault information and inadequate extraction of fault features, leading to the low diagnostic accuracy of the model. To address these problems, this paper proposes an improved dual-branch convolutional capsule neural network for rolling bearing fault diagnosis. This method converts the collected bearing vibration signals into grayscale images to construct a grayscale image dataset. By fully considering the types of bearing faults and damage diameters, the data are labeled using a dual-label format. A multi-scale convolution module is introduced to extract features from the data and maximize feature information extraction. Additionally, a coordinate attention mechanism is incorporated into this module to better extract useful channel features and enhance feature extraction capability. Based on adaptive fusion between fault type (damage diameter) features and labels, a dual-branch convolutional capsule neural network model for rolling bearing fault diagnosis is established. The model was experimentally validated using both Case Western Reserve University's bearing dataset and self-made datasets. The experimental results demonstrate that the fault type branch of the model achieves an accuracy rate of 99.88%, while the damage diameter branch attains an accuracy rate of 99.72%. Both branches exhibit excellent classification performance and display robustness against noise interference and variable working conditions. In comparison with other algorithm models cited in the reference literature, the diagnostic capability of the model proposed in this study surpasses them. Furthermore, the generalization ability of the model is validated using a self-constructed laboratory dataset, yielding an average accuracy rate of 94.25% for both branches.

Maize leaf disease recognition based on improved MSRCR and OSCRNet

Accurate identification of maize pests and diseases plays a crucial role in the growth and yield of maize. The recognition method of maize leaf diseases based on deep learning is currently a research hotspot. In practical applications, it is difficult to ensure a high recognition accuracy due to the impact of environmental factors (such as light intensity, background noise) and insufficient training data. To address this challenge, this paper proposes a maize image recognition method based on image enhancement and OSCRNet. Firstly, a maize leaf image enhancement framework and algorithm based on improved MSRCR were designed to enhance the characteristics of the maize leaf in a complex environment and to solve the problems of high noise and blur of maize images. Subsequently, the OSCRNet maize leaf recognition network model was established, which uses octave convolution with characteristics to accelerate network training and reduce unnecessary redundant spatial information in maize leaf images. Additionally, a self-calibrated convolution with multi-scale features was employed to realize the interactions of different feature information in the maize leaf images, enhance feature extraction, and solve the problems of similarity of maize disease features and easy learning disorders. Concurrently, batch normalization was employed to prevent network overfitting and enhance the robustness of the model. The experimental results showed that the highest identification accuracy of the proposed method for rust, gray leaf disease, northern wilt disease, and healthy maize are 96.67%, 94.86%, 92.81%, and 95.63%, respectively. Our methods were beneficial in solving the problems of slow efficiency, low accuracy and insufficient training data, and also outperformed other comparison models. The proposed method demonstrates strong robustness for maize disease images collected in the natural environment, providing a reference for the intelligent diagnosis of other plant leaf diseases.

ENFformer: Long-short term representation of electric network frequency for digital audio tampering detection

Detecting digital audio tampering is essential for ensuring judicial fairness and societal security. Traditional methods, primarily based on Electric Network Frequency (ENF), have been limited by their reliance on singular, static features, which overlook critical temporal dynamics inherent in ENF data. This results in suboptimal detection accuracy. Addressing these limitations, this paper introduces a novel transformer model, ENFformer, designed for the detection of digital audio tampering by leveraging both short and long-term temporal features of ENF data. Initially, the ENFformer model extracts traditional zero-order and first-order phase features using discrete Fourier transforms (DFT0 and DFT1), along with frequency features obtained through the Hilbert transform. These features are processed using a frame-based algorithm to develop their temporal counterparts. To enhance feature extraction, the model employs a two-layer one-dimensional Convolutional Long Short-Term Memory (ConvLSTM) network to assimilate short-term temporal features, followed by a Bidirectional Long Short-Term Memory (BiLSTM) network for long-term feature integration. A branch attention mechanism then synergizes these long-term features, which are further refined by a transformer module for accurate tampered audio identification. Our empirical evaluations on the Carioca and ENF-EDIT1 databases demonstrate that ENFformer achieves detection accuracies of 97.33% and 93.50% respectively, surpassing existing state-of-the-art methods. These results confirm the effectiveness of our approach, which significantly advances the field of digital audio tampering detection by incorporating a comprehensive analysis of temporal information in ENF features. The source code of this study is publicly available at https://github.com/CCNUZFW/ENFformer.

TSANN-TG: Temporal-Spatial Attention Neural Networks with Task-Specific Graph for EEG Emotion Recognition.

Electroencephalography (EEG)-based emotion recognition is increasingly pivotal in the realm of affective brain-computer interfaces. In this paper, we propose TSANN-TG (temporal-spatial attention neural network with a task-specific graph), a novel neural network architecture tailored for enhancing feature extraction and effectively integrating temporal-spatial features. TSANN-TG comprises three primary components: a node-feature-encoding-and-adjacency-matrices-construction block, a graph-aggregation block, and a graph-feature-fusion-and-classification block. Leveraging the distinct temporal scales of features from EEG signals, TSANN-TG incorporates attention mechanisms for efficient feature extraction. By constructing task-specific adjacency matrices, the graph convolutional network with an attention mechanism captures the dynamic changes in dependency information between EEG channels. Additionally, TSANN-TG emphasizes feature integration at multiple levels, leading to improved performance in emotion-recognition tasks. Our proposed TSANN-TG is applied to both our FTEHD dataset and the publicly available DEAP dataset. Comparative experiments and ablation studies highlight the excellent recognition results achieved. Compared to the baseline algorithms, TSANN-TG demonstrates significant enhancements in accuracy and F1 score on the two benchmark datasets for four types of cognitive tasks. These results underscore the significant potential of the TSANN-TG method to advance EEG-based emotion recognition.

Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification

The early and accurate diagnosis of brain tumors is critical for effective treatment planning, with Magnetic Resonance Imaging (MRI) serving as a key tool in the non-invasive examination of such conditions. Despite the advancements in Computer-Aided Diagnosis (CADx) systems powered by deep learning, the challenge of accurately classifying brain tumors from MRI scans persists due to the high variability of tumor appearances and the subtlety of early-stage manifestations. This work introduces a novel adaptation of the EfficientNetv2 architecture, enhanced with Global Attention Mechanism (GAM) and Efficient Channel Attention (ECA), aimed at overcoming these hurdles. This enhancement not only amplifies the model’s ability to focus on salient features within complex MRI images but also significantly improves the classification accuracy of brain tumors. Our approach distinguishes itself by meticulously integrating attention mechanisms that systematically enhance feature extraction, thereby achieving superior performance in detecting a broad spectrum of brain tumors. Demonstrated through extensive experiments on a large public dataset, our model achieves an exceptional high-test accuracy of 99.76%, setting a new benchmark in MRI-based brain tumor classification. Moreover, the incorporation of Grad-CAM visualization techniques sheds light on the model’s decision-making process, offering transparent and interpretable insights that are invaluable for clinical assessment. By addressing the limitations inherent in previous models, this study not only advances the field of medical imaging analysis but also highlights the pivotal role of attention mechanisms in enhancing the interpretability and accuracy of deep learning models for brain tumor diagnosis. This research sets the stage for advanced CADx systems, enhancing patient care and treatment outcomes.

Load Prediction in Double-Channel Residual Self-Attention Temporal Convolutional Network with Weight Adaptive Updating in Cloud Computing.

When resource demand increases and decreases rapidly, container clusters in the cloud environment need to respond to the number of containers in a timely manner to ensure service quality. Resource load prediction is a prominent challenge issue with the widespread adoption of cloud computing. A novel cloud computing load prediction method has been proposed, the Double-channel residual Self-attention Temporal convolutional Network with Weight adaptive updating (DSTNW), in order to make the response of the container cluster more rapid and accurate. A Double-channel Temporal Convolution Network model (DTN) has been developed to capture long-term sequence dependencies and enhance feature extraction capabilities when the model handles long load sequences. Double-channel dilated causal convolution has been adopted to replace the single-channel dilated causal convolution in the DTN. A residual temporal self-attention mechanism (SM) has been proposed to improve the performance of the network and focus on features with significant contributions from the DTN. DTN and SM jointly constitute a dual-channel residual self-attention temporal convolutional network (DSTN). In addition, by evaluating the accuracy aspects of single and stacked DSTNs, an adaptive weight strategy has been proposed to assign corresponding weights for the single and stacked DSTNs, respectively. The experimental results highlight that the developed method has outstanding prediction performance for cloud computing in comparison with some state-of-the-art methods. The proposed method achieved an average improvement of 24.16% and 30.48% on the Container dataset and Google dataset, respectively.

1D-CNN-based audio tampering detection using ENF signals

The extensive adoption of digital audio recording has revolutionized its application in digital forensics, particularly in civil litigation and criminal prosecution. Electric network frequency (ENF) has emerged as a reliable technique in the field of audio forensics. However, the absence of comprehensive ENF reference datasets limits current ENF-based methods. To address this, this study introduces ATD, a blind audio forensics framework based on a one-dimensional convolutional neural network (1D-CNN) model. ATD can identify phase mutations and waveform discontinuities within the tampered ENF signal, without relying on an ENF reference database. To enhance feature extraction, the framework incorporates characteristics of the fundamental harmonics of ENF signals. In addition, a denoising method termed ENF noise reduction (ENR) based on the variational mode decomposition (VMD) and robust filtering algorithm (RFA) is proposed to reduce the impact of external noise on embedded electric network frequency signals. This study investigates three distinct types of audio tampering—deletion, insertion, and replacement—culminating in the design of binary-class tampering detection scenarios and four-class tampering detection scenarios tailored to these tampering types. ATD achieves a tampering detection accuracy of over 93% in the four-class scenario and exceeds 96% in the binary-class scenario. The effectiveness, efficiency, adaptability, and robustness of ATD in the two and four classification scenarios have been confirmed by extensive experiments.

Vehicle trajectory prediction based on attention optimized with real-scene sampling

Advancements in autonomous vehicles and deep learning have notably improved vehicle trajectory prediction accuracy. However, extracting interaction features in complex driving scenarios, such as vehicle-to-vehicle interactions and lane constraints, presents challenges. Deep learning-based methods struggle to achieve optimal predictive performance under limited computational resources. This study introduces a global attention mechanism to enhance feature extraction from driving scene encodings, focusing the decoder on interactive behaviours and boosting long-term prediction performance. An adaptive scheduled sampling model is employed, using actual driving scenarios probabilistically for training, addressing slow learning of actual driving behaviours and lack of initial feature correction. This method increases attention to actual interactions, reducing reliance on natural scenes and improving model generalizability. On the NGSIM dataset, sampling attention encoder-decoder (SAED) achieves a 1–5 s average displacement error (ADE) of 1.34 m, with 4 s and 5 s final displacement errors (FDEs) of 1.64 and 2.06 m, respectively. Compared to methods based on long short-term memory (LSTM), SAED reduces the model's storage space by 24.68% under the same network layer count. That demonstrates its effectiveness in extracting interactive behaviours in complex scenarios and enhances the accuracy of long-term predictions.

Automatic classification of spinal osteosarcoma and giant cell tumor of bone using optimized DenseNet

ObjectiveThis study aims to explore an optimized deep-learning model for automatically classifying spinal osteosarcoma and giant cell tumors. In particular, it aims to provide a reliable method for distinguishing between these challenging diagnoses in medical imaging. MethodsThis research employs an optimized DenseNet model with a self-attention mechanism to enhance feature extraction capabilities and reduce misclassification in differentiating spinal osteosarcoma and giant cell tumors. The model utilizes multi-scale feature map extraction for improved classification accuracy. The paper delves into the practical use of Gradient-weighted Class Activation Mapping (Grad-CAM) for enhancing medical image classification, specifically focusing on its application in diagnosing spinal osteosarcoma and giant cell tumors. The results demonstrate that the implementation of Grad-CAM visualization techniques has improved the performance of the deep learning model, resulting in an overall accuracy of 85.61%. Visualizations of images for these medical conditions using Grad-CAM, with corresponding class activation maps that indicate the tumor regions where the model focuses during predictions. ResultsThe model achieves an overall accuracy of 80% or higher, with sensitivity exceeding 80% and specificity surpassing 80%. The average area under the curve AUC for spinal osteosarcoma and giant cell tumors is 0.814 and 0.882, respectively. The model significantly supports orthopedics physicians in developing treatment and care plans. ConclusionThe DenseNet-based automatic classification model accurately distinguishes spinal osteosarcoma from giant cell tumors. This study contributes to medical image analysis, providing a valuable tool for clinicians in accurate diagnostic classification. Future efforts will focus on expanding the dataset and refining the algorithm to enhance the model's applicability in diverse clinical settings.

A novel stochastic configuration network with enhanced feature extraction for industrial process modeling

Stochastic configuration networks (SCNs), possessing sound generalization performance and low computational burden, have been extensively investigated in data analysis field. But in practice, it performs poor. This is mainly caused by two aspects: (1) the increment of random hidden nodes with incompact constraints may bring the emergence of redundant nodes, thereby resulting in poor modeling performance, and (2) SCNs have limited feature extraction capabilities. To address these issues, a novel SCN inserting feature layer, termed as FSCN, is presented in this paper. First, the embedded feature layer establishes a connection between the input and hidden layers, thus mapping the input data into a suitable feature space. Second, an inequality constraint based on Greville iterative method is established. It can not only facilitate the construction of high-quality hidden nodes but also guarantee convergence of the built model. Then, the Greville iterative method is also employed for output weight updating. Finally, comparative experiments on a real-valued nonlinear function, four real-world data sets and the modeling of two real industrial processes are conducted and the comparison results with other modeling methods show that FSCN has superior performance in terms of both model accuracy and compactness.

LENet: Lightweight and Effective Detector for Aerial Object

Aerial object detection is crucial in various computer vision tasks, including video monitoring, early warning systems, and visual tracking. While current methods can accurately detect normal-sized objects, they face challenges distinguishing small objects from cluttered backgrounds. Developing methods that can be deployed on edge devices to achieve fast, accurate, and energy-efficient performance is also an urgent challenge. This paper proposes a network for aerial object detection by incorporating an attention mechanism to enhance feature extraction and elevate the accuracy of aerial moving object detection. Additionally, we optimize the channel dimensions of the feature extraction framework, resulting in a reduction in model parameters, acceleration of inference speed, and alleviation of the computational burden. Ulteriorly, we optimize the Spatial Pyramid Pooling (SPP) module to enhance detection accuracy and processing speed. Inspired by the ResNet and RepVGG structures, we design a feature fusion module to combine early-extracted features, improving speed and accuracy. Based on the design mentioned above principles, we develop a neural network method with an impressively small model size of only [Formula: see text][Formula: see text]M. The proposed approach achieves state-of-the-art performance on five benchmark datasets. Besides its superior performance, our method demonstrates excellent throughput on edge computing devices. Experimental results show that even when running on low-performance computing devices, the CPU and GPU temperatures remain below 50∘C and achieve a detection speed of 14.8 frames per second (fps) and power consumption of only 2.9[Formula: see text]W. These findings suggest that a high-accuracy, low-power, low-latency, and low-memory footprint aerial object detection solution is achievable.