Search Results (60)

This study presents a novel approach for classifying Discomycetes species using deep learning and explainable artificial intelligence (XAI) techniques. The EfficientNet-B0 model achieved the highest performance, reaching 97% accuracy, a 97% F1-score, and a 99% AUC, making it the most effective model. MobileNetV3-L followed closely, with 96% accuracy, a 96% F1-score, and a 99% AUC, while ShuffleNet also showed strong results, reaching 95% accuracy and a 95% F1-score. In contrast, the EfficientNet-B4 model exhibited lower performance, achieving 89% accuracy, an 89% F1-score, and a 93% AUC. These results highlight the superior feature extraction and classification capabilities of EfficientNet-B0 and MobileNetV3-L for biological data. Explainable AI (XAI) techniques, including Grad-CAM and Score-CAM, enhanced the interpretability and transparency of model decisions. These methods offered insights into the internal decision-making processes of deep learning models, ensuring reliable classification results. This approach improves traditional taxonomy by advancing data processing and supporting accurate species differentiation. In the future, using larger datasets and more advanced AI models is recommended for biodiversity monitoring, ecosystem modeling, medical imaging, and bioinformatics. Beyond high classification performance, this study offers an ecologically meaningful approach by supporting biodiversity conservation and the accurate identification of fungal species. These findings contribute to developing more precise and reliable biological classification systems, setting new standards for AI-driven research in biological sciences. Full article

This study proposes a grading algorithm for Orah sorting lines based on machine vision and deep learning. The original ShuffleNet V2 network was modified by replacing the ReLU activation function with the Mish activation function to alleviate the neuron death problem. The ECA attention module was incorporated to enhance the extraction of Orah appearance features, and transfer learning was applied to improve model performance. As a result, the ShuffleNet_wogan model was developed. Based on the operational principles of the sorting line, a time-sequential grading algorithm was designed to improve grading accuracy, along with a multi-sampling diameter algorithm for simultaneous Orah diameter measurement. Experimental results show that the ShuffleNet_wogan model achieved an accuracy of 91.12%, a 3.92% improvement compared to the original ShuffleNet V2 network. The average prediction time for processing 10 input images was 51.44 ms. The sorting line achieved a grading speed of 10 Orahs per second, with an appearance grading accuracy of 92.5% and a diameter measurement compliance rate of 98.3%. The proposed algorithm is characterized by high speed and accuracy, enabling efficient Orah sorting. Full article

Paint loss is one of the major forms of deterioration in ancient murals and color paintings, and its detection and segmentation are critical for subsequent restoration efforts. However, existing methods still suffer from issues such as incomplete segmentation, patch noise, and missed detections during paint loss extraction, limiting the automation of paint loss detection and restoration. To tackle these challenges, this paper proposes PLDS-YOLO, an improved model based on YOLOv8s-seg, specifically designed for the detection and segmentation of paint loss in ancient murals and color paintings. First, the PA-FPN network is optimized by integrating residual connections to enhance the fusion of shallow high-resolution features with deep semantic features, thereby improving the accuracy of edge extraction in deteriorated areas. Second, a dual-backbone network combining CSPDarkNet and ShuffleNet V2 is introduced to improve multi-scale feature extraction and enhance the discrimination of deteriorated areas. Third, SPD-Conv replaces traditional pooling layers, utilizing space-to-depth transformation to improve the model’s ability to perceive deteriorated areas of varying sizes. Experimental results on a self-constructed dataset demonstrate that PLDS-YOLO achieves a segmentation accuracy of 86.2%, outperforming existing methods in segmentation completeness, multi-scale deterioration detection, and small target recognition. Moreover, the model maintains a favorable balance between computational complexity and inference speed, providing reliable technical support for intelligent paint loss monitoring and digital restoration. Full article

In subway tunnel construction, current hand–eye integrated drilling robots use a camera mounted on the drilling arm for image acquisition. However, dust interference and long-distance operation cause a decline in image quality, affecting the stability and accuracy of the visual recognition system. Additionally, the computational complexity of high-precision detection models limits deployment on resource-constrained edge devices, such as industrial controllers. To address these challenges, this paper proposes a dual-arm tunnel drilling robot system with hand–eye separation, utilizing the first-frame localization and follower tracking method. The vision arm (“eye”) provides real-time position data to the drilling arm (“hand”), ensuring accurate and efficient operation. The study employs an RFBNet model for initial frame localization, replacing the original VGG16 backbone with ShuffleNet V2. This reduces model parameters by 30% (135.5 MB vs. 146.3 MB) through channel splitting and depthwise separable convolutions to reduce computational complexity. Additionally, the GIoU loss function is introduced to replace the traditional IoU, further optimizing bounding box regression through the calculation of the minimum enclosing box. This resolves the gradient vanishing problem in traditional IoU and improves average precision (AP) by 3.3% (from 0.91 to 0.94). For continuous tracking, a SiamRPN-based algorithm combined with Kalman filtering and PID control ensures robustness against occlusions and nonlinear disturbances, increasing the success rate by 1.6% (0.639 vs. 0.629). Experimental results show that this approach significantly improves tracking accuracy and operational stability, achieving 31 FPS inference speed on edge devices and providing a deployable solution for tunnel construction’s safety and efficiency needs. Full article

For reducing the parameters and computational complexity of networks while improving the classification accuracy of hyperspectral remote sensing images (HRSIs), a dynamic split pointwise convolution (DSPC) strategy is presented, and a lightweight convolutional neural network (CNN), i.e., CSM-DSPCss-Ghost, is proposed based on DSPC. A channel switching module (CSM) and a dynamic split pointwise convolution Ghost (DSPC-Ghost) module are presented by combining the presented DSPC with channel shuffling and the Ghost strategy, respectively. CSM replaces the first expansion pointwise convolution in the MobileNetV2 bottleneck module to reduce the parameter number and relieve the increasing channel correlation caused by the original channel expansion pointwise convolution. DSPC-Ghost replaces the second pointwise convolution in the MobileNetV2 bottleneck module, which can further reduce the number of parameters based on DSPC and extract the depth spectral and spatial features of HRSIs successively. Finally, the CSM-DSPCss-Ghost bottleneck module is presented by introducing a squeeze excitation module and a spatial attention module after the CSM and the depthwise convolution, respectively. The presented CSM-DSPCss-Ghost network consists of seven successive CSM-DSPCss-Ghost bottleneck modules. Experiments on four measured HRSIs show that, compared with 2D CNN, 3D CNN, MobileNetV2, ShuffleNet, GhostNet, and Xception, CSM-DSPCss-Ghost can significantly improve classification accuracy and running speed while reducing the number of parameters. Full article

Facial expression recognition (FER) is essential for discerning human emotions and is applied extensively in big data analytics, healthcare, security, and user experience enhancement. This study presents a comprehensive evaluation of ten state-of-the-art deep learning models—VGG16, VGG19, ResNet50, ResNet101, DenseNet, GoogLeNet V1, MobileNet V1, EfficientNet V2, ShuffleNet V2, and RepVGG—on the task of facial expression recognition using the FER2013 dataset. Key performance metrics, including test accuracy, training time, and weight file size, were analyzed to assess the learning efficiency, generalization capabilities, and architectural innovations of each model. EfficientNet V2 and ResNet50 emerged as top performers, achieving high accuracy and stable convergence using compound scaling and residual connections, enabling them to capture complex emotional features with minimal overfitting. DenseNet, GoogLeNet V1, and RepVGG also demonstrated strong performance, leveraging dense connectivity, inception modules, and re-parameterization techniques, though they exhibited slower initial convergence. In contrast, lightweight models such as MobileNet V1 and ShuffleNet V2, while excelling in computational efficiency, faced limitations in accuracy, particularly in challenging emotion categories like “fear” and “disgust”. The results highlight the critical trade-offs between computational efficiency and predictive accuracy, emphasizing the importance of selecting appropriate architecture based on application-specific requirements. This research contributes to ongoing advancements in deep learning, particularly in domains such as facial expression recognition, where capturing subtle and complex patterns is essential for high-performance outcomes. Full article

Oudemansiella raphanipes is valued for its rich nutritional content and medicinal properties, but traditional manual grading methods are time-consuming and labor-intensive. To address this, deep learning techniques are employed to automate the grading process, and knowledge distillation (KD) is used to enhance the accuracy of a small-parameter model while maintaining a low resource occupation and fast response speed in resource-limited devices. This study employs a three-teacher KD framework and investigates three cascaded structures: the parallel model, the standard series model, and the series model with residual connections (residual-series model). The student model used is a lightweight ShuffleNet V2 0.5x, while the teacher models are VGG16, ResNet50, and Xception. Our experiments show that the cascaded structures result in improved performance indices, compared with the traditional ensemble model with equal weights; in particular, the residual-series model outperforms the other models, achieving a grading accuracy of 99.7% on the testing dataset with an average inference time of 5.51 ms. The findings of this study have the potential for broader application of KD in resource-limited environments for automated quality grading. Full article

Fault arcs exhibit randomness, with current waveforms closely mirroring those of standard nonlinear load operations, posing challenges for traditional series fault arc detection methods. This study presents an improved detection approach using a lightweight convolutional neural network model, ShuffleNet V2. Current data from household loads were collected and preprocessed to establish a comprehensive database, leveraging one-dimensional convolution and channel attention mechanisms for precise analysis. Experimental results demonstrate a high fault arc detection accuracy of 97.8%, supporting real-time detection on the Jetson Nano embedded platform, with an efficient detection cycle time of 15.65 ms per sample. The proposed approach outperforms existing methods in both accuracy and speed, providing a robust foundation for developing advanced fault arc circuit breakers. Full article

Peanuts are susceptible to defects such as insect damage, breakage, germinant, and mildew, leading to varying qualities of peanuts. The disparity in peanut kernel quality results in significant differences in their prices and economic value. Conducting real-time, accurate, and non-destructive quality inspections of peanut kernels can effectively increase the utilization rate and commercial value of peanuts. Manual inspections are inefficient and subjective, while photoelectric sorting is costly and less precise. Therefore, this study proposes a peanut kernel quality detection algorithm based on an enhanced YOLO v5 model. Compared to other models, this model is practical, highly accurate, lightweight, and easy to integrate. Initially, YOLO v5s was chosen as the foundational training model through comparison. Subsequently, the original backbone network was replaced with a lightweight ShuffleNet v2 network to improve the model’s ability to differentiate features among various types of peanut kernels and reduce the parameters. The ECA (Efficient Channel Attention) mechanism was introduced into the C3 module to enhance feature extraction capabilities, thereby improving average accuracy. The CIoU loss function was replaced with the alpha-IoU loss function to boost detection accuracy. The experimental results indicated that the improved model, SEA-YOLOv5, achieved an accuracy of 98.8% with a parameter count of 0.47 M and an average detection time of 11.2 ms per image. When compared to other detection models, there was an improvement in accuracy, demonstrating the effectiveness of the proposed peanut kernel quality detection model. Furthermore, this model is suitable for deployment on resource-limited embedded devices such as mobile terminals, enabling real-time and precise detection of peanut kernel quality. Full article

The objective of this study was to develop an artificial intelligence (AI)-driven model for the detection of helmet usage among workers in tractor and agricultural machinery factories with the aim of enhancing occupational safety. A transfer learning approach was employed, utilizing nine pre-trained neural networks for the extraction of deep features. The following neural networks were employed: MobileNetV2, ResNet50, DarkNet53, AlexNet, ShuffleNet, DenseNet201, InceptionV3, Inception-ResNetV2, and GoogLeNet. Subsequently, the extracted features were subjected to iterative neighborhood component analysis (INCA) for feature selection, after which they were classified using the k-nearest neighbor (kNN) algorithm. The classification outputs of all networks were combined through iterative majority voting (IMV) to achieve optimal results. To evaluate the model, an image dataset comprising 662 images of individuals wearing helmets and 722 images of individuals without helmets sourced from the internet was constructed. The proposed model achieved an accuracy of 90.39%, with DenseNet201 producing the most accurate results. This AI-driven helmet detection model demonstrates significant potential in improving occupational safety by assisting safety officers, especially in confined environments, reducing human error, and enhancing efficiency. Full article

To address the computational complexity and deployment challenges of traditional convolutional neural networks in rice disease identification, this paper proposes an efficient and lightweight model: Ghost Channel Spatial Attention ShuffleNet with Mish-ReLU Adaptive Activation Function (GCA-MiRaNet). Based on ShuffleNet V2, we effectively reduced the model’s parameter count by streamlining convolutional layers, decreasing stacking depth, and optimizing output channels. Additionally, the model incorporates the Ghost Module as a replacement for traditional 1 × 1 convolutions, further reducing computational overhead. Innovatively, we introduce a Channel Spatial Attention Mechanism (CSAM) that significantly enhances feature extraction and generalization aimed at rice disease detection. Through combining the advantages of Mish and ReLU, we designed the Mish-ReLU Adaptive Activation Function (MAAF), enhancing the model’s generalization capacity and convergence speed. Through transfer learning and ElasticNet regularization, the model’s accuracy has notably improved while effectively avoiding overfitting. Sufficient experimental results indicate that GCA-MiRaNet attains a precision of 94.76% on the rice disease dataset, with a 95.38% reduction in model parameters and a compact size of only 0.4 MB. Compared to traditional models such as ResNet50 and EfficientNet V2, GCA-MiRaNet demonstrates significant advantages in overall performance, especially on embedded devices. This model not only enables efficient and accurate real-time disease monitoring but also provides a viable solution for rice field protection drones and Internet of Things management systems, advancing the process of contemporary agricultural smart management. Full article

Road crack detection is of paramount importance for ensuring vehicular traffic safety, and implementing traditional detection methods for cracks inevitably impedes the optimal functioning of traffic. In light of the above, we propose a USSC-YOLO-based target detection algorithm for unmanned aerial vehicle (UAV) road cracks based on machine vision. The algorithm aims to achieve the high-precision detection of road cracks at all scale levels. Compared with the original YOLOv5s, the main improvements to USSC-YOLO are the ShuffleNet V2 block, the coordinate attention (CA) mechanism, and the Swin Transformer. First, to address the problem of large network computational spending, we replace the backbone network of YOLOv5s with ShuffleNet V2 blocks, reducing computational overhead significantly. Next, to reduce the problems caused by the complex background interference, we introduce the CA attention mechanism into the backbone network, which reduces the missed and false detection rate. Finally, we integrate the Swin Transformer block at the end of the neck to enhance the detection accuracy for small target cracks. Experimental results on our self-constructed UAV near–far scene road crack i(UNFSRCI) dataset demonstrate that our model reduces the giga floating-point operations per second (GFLOPs) compared to YOLOv5s while achieving a 6.3% increase in mAP@50 and a 12% improvement in mAP@ [50:95]. This indicates that the model remains lightweight meanwhile providing excellent detection performance. In future work, we will assess road safety conditions based on these detection results to prioritize maintenance sequences for crack targets and facilitate further intelligent management. Full article

Image processing with artificial intelligence has shown significant promise in various medical imaging applications. The present study aims to evaluate the performance of 16 different convolutional neural networks (CNNs) in predicting age and gender from panoramic radiographs in children and young adults. The networks tested included DarkNet-19, DarkNet-53, Inception-ResNet-v2, VGG-19, DenseNet-201, ResNet-50, GoogLeNet, VGG-16, SqueezeNet, ResNet-101, ResNet-18, ShuffleNet, MobileNet-v2, NasNet-Mobile, AlexNet, and Xception. These networks were trained on a dataset of 7336 radiographs from individuals aged between 5 and 21. Age and gender estimation accuracy and mean absolute age prediction errors were evaluated on 340 radiographs. Statistical analyses were conducted using Shapiro–Wilk, one-way ANOVA, and Tukey tests (p < 0.05). The gender prediction accuracy and the mean absolute age prediction error were, respectively, 87.94% and 0.582 for DarkNet-53, 86.18% and 0.427 for DarkNet-19, 84.71% and 0.703 for GoogLeNet, 81.76% and 0.756 for DenseNet-201, 81.76% and 1.115 for ResNet-18, 80.88% and 0.650 for VGG-19, 79.41% and 0.988 for SqueezeNet, 79.12% and 0.682 for Inception-Resnet-v2, 78.24% and 0.747 for ResNet-50, 77.35% and 1.047 for VGG-16, 76.47% and 1.109 for Xception, 75.88% and 0.977 for ResNet-101, 73.24% and 0.894 for ShuffleNet, 72.35% and 1.206 for AlexNet, 71.18% and 1.094 for NasNet-Mobile, and 62.94% and 1.327 for MobileNet-v2. No statistical difference in age prediction performance was found between DarkNet-19 and DarkNet-53, which demonstrated the most successful age estimation results. Despite these promising results, all tested CNNs performed below 90% accuracy and were not deemed suitable for clinical use. Future studies should continue with more-advanced networks and larger datasets. Full article

The accurate identification of corn leaf diseases is crucial for preventing disease spread and improving corn yield. Plant leaf images are often affected by factors such as complex backgrounds, climate, light, and sample data imbalance. To address these issues, we propose a lightweight convolutional neural network, ICS-ResNet, based on ResNet50. This network incorporates improved spatial and channel attention modules as well as a deep separable residual structure to enhance recognition accuracy. (1) The residual connections in the ResNet network prevent gradient loss during deep network training. (2) The improved channel attention (ICA) and spatial attention (ISA) modules fully utilize semantic information from different feature layers to accurately localize key features of the network. (3) To reduce the number of parameters and lower computational costs, we replace traditional convolutional computation with a depth-separable residual structure. (4) We also employ cosine annealing to dynamically adjust the learning rate, enhancing the network’s training stability, improving model convergence, and preventing local optima. Experiments on the corn dataset in Plant Village compare the proposed ICS-ResNet with eight popular networks: CSPNet, InceptionNet_v3, EfficientNet, ShuffleNet, MobileNet, ResNet50, ResNet101 and ResNet152. The results show that the ICS-ResNet achieves an accuracy of 98.87%, which is 5.03%, 3.18%, 1.13%, 1.81%, 1.13%, 0.68%, 0.44% and 0.60% higher than the other networks, respectively. Furthermore, the number of parameters and computations are reduced by 69.21% and 54.88%, respectively, compared to the original ResNet50 network, significantly improving the efficiency of corn leaf disease classification. The study provides strong technical support for sustainable agriculture and the promotion of agricultural science and technology innovation. Full article

A lightweight forest fire detection model based on YOLOv8 is proposed in this paper in response to the problems existing in traditional sensors for forest fire detection. The performance of traditional sensors is easily constrained by hardware computing power, and their adaptability in different environments needs improvement. To balance the accuracy and speed of fire detection, the GhostNetV2 lightweight network is adopted to replace the backbone network for feature extraction of YOLOv8. The Ghost module is utilized to replace traditional convolution operations, conducting feature extraction independently in different dimensional channels, significantly reducing the complexity of the model while maintaining excellent performance. Additionally, an improved CPDCA channel priority attention mechanism is proposed, which extracts spatial features through dilated convolution, thereby reducing computational overhead and enabling the model to focus more on fire targets, achieving more accurate detection. In response to the problem of small targets in fire detection, the Inner IoU loss function is introduced. By adjusting the size of the auxiliary bounding boxes, this function effectively enhances the convergence effect of small target detection, further reducing missed detections, and improving overall detection accuracy. Experimental results indicate that, compared with traditional methods, the algorithm proposed in this paper significantly improves the average precision and FPS of fire detection while maintaining a smaller model size. Through experimental analysis, compared with YOLOv3-tiny, the average precision increased by 5.9% and the frame rate reached 285.3 FPS when the model size was only 4.9 M; compared with Shufflenet, the average precision increased by 2.9%, and the inference speed tripled. Additionally, the algorithm effectively addresses false positives, such as cloud and reflective light, further enhancing the detection of small targets and reducing missed detections. Full article