Search Results (34)

Moldy pear core constitutes a severe internal defect that compromises fruit quality. This study proposes a nondestructive detection method for Korla pear moldy core using Vis/NIR spectral signals, aimed at supporting post-harvest quality control and automated industrial sorting. We collected spectral signals from pears and quantified the moldy pear core area to classify samples into healthy (S = 0%), slightly moldy (0 < S ≤ 10%), and severely moldy (S > 10%) categories. We constructed a three-tier comparative framework to evaluate the progression from conventional machine learning to advanced deep learning: traditional methods using univariate selection (US) and random forest (RF) for feature extraction followed by support vector machine (SVM) classification; 1D-ResNet for direct processing of spectral signals; and two-dimensional approaches transforming signals into improved gramian angular field (IGAF) or Laplacian pyramid Markov transition field (LPMTF) images processed through deep belief network (DBN), MobileNetv3, and Vision Transformer (ViT). The LPMTF-ViT combination delivered the best performance with 98.98% test accuracy and 94.44% external validation accuracy, significantly exceeding traditional approaches and 1D-ResNet. This innovative approach delivers effective technical support for early-stage, nondestructive detection of internal fruit defects. It also establishes a scalable foundation for automated industrial inspection systems, potentially reducing post-harvest losses while ensuring premium quality control in modern fruit supply chains. Full article

Background: Clinical imaging is an important part of health care providing physicians with great assistance in patients treatment. In fact, segmentation and grading of tumors can help doctors assess the severity of the cancer at an early stage and increase the chances of cure. Despite that Deep Learning for cancer diagnosis has achieved clinically acceptable accuracy, there still remains challenging tasks, especially in the context of insufficient labeled data and the subsequent need for expensive computational ressources. Objective: This paper presents a lightweight classification and segmentation deep learning model to assist in the identification of cancerous tumors with high accuracy despite the scarcity of medical data. Methods: We propose a multi-task architecture for classification and segmentation of cancerous tumors in the Brain, Skin, Prostate and lungs. The model is based on the UNet architecture with different pre-trained deep learning models (VGG 16 and MobileNetv2) as a backbone. The multi-task model is validated on relatively small datasets (slightly exceed 1200 images) that are diverse in terms of modalities (IRM, X-Ray, Dermoscopic and Digital Histopathology), number of classes, shapes, and sizes of cancer pathologies using the accuracy and dice coefficient as statistical metrics. Results: Experiments show that the multi-task approach improve the learning efficiency and the prediction accuracy for the segmentation and classification tasks, compared to training the individual models separately. The multi-task architecture reached a classification accuracy of 86%, 90%, 88%, and 87% respectively for Skin Lesion, Brain Tumor, Prostate Cancer and Pneumothorax. For the segmentation tasks we were able to achieve high precisions respectively 95%, 98% for the Skin Lesion and Brain Tumor segmentation and a 99% precise segmentation for both Prostate cancer and Pneumothorax. Proving that the multi-task solution is more efficient than single-task networks. Full article

Background/Objectives: In recent years, there has been a significant increase in the number of women with breast cancer. Breast cancer prediction is defined as a medical data analysis and image processing problem. Experts may need artificial intelligence technologies to distinguish between benign and malignant tumors in order to make decisions. When the studies in the literature are examined, it can be seen that applications of deep learning algorithms in the field of medicine have achieved very successful results. Methods: In this study, 11 different deep learning algorithms (Vanilla, ResNet50, ResNet152, VGG16, DenseNet152, MobileNetv2, EfficientB1, NasNet, DenseNet201, ensemble, and Tuned Model) were used. Images of pathological specimens from breast biopsies consisting of two classes, benign and malignant, were used for classification analysis. To limit the computational time and speed up the analysis process, 10,000 images, 6172 IDC-negative and 3828 IDC-positive, were selected. Of the images, 80% were used for training, 10% were used for validation, and 10% were used for testing the trained model. Results: The results demonstrate that DenseNet201 achieved the highest classification accuracy of 89.4%, with a precision of 88.2%, a recall of 84.1%, an F1 score of 86.1%, and an AUC score of 95.8%. Conclusions: In conclusion, this study highlights the potential of deep learning algorithms in breast cancer classification. Future research should focus on integrating multi-modal imaging data, refining ensemble learning methodologies, and expanding dataset diversity to further improve the classification accuracy and real-world clinical applicability. Full article

Precision and efficacy are vital in the constantly advancing field of food image identification, particularly in the domains of medicine and healthcare. Transfer learning and deep ensemble learning techniques are employed to enhance the accuracy and efficiency of the Indian Food Classification System. The ensemble model effectively captures various patterns and correlations within the information by employing many machine learning techniques. The ensemble method we employ utilizes the MobileNetV3 and DenseNet-121 transfer learning models to construct a robust model. The ensemble model benefits from the integration of model predictions, resulting in enhanced recognition of Indian food. The study utilized a dataset consisting of 6000 photographs of Indian cuisine, categorized into 26 distinct groups. The picture dataset is divided into two subsets: 80% is allocated for training and 20% is reserved for testing. The experimental results demonstrate that DenseNet-121 surpasses MobileNetv3 in terms of testing accuracy, achieving a rate of 90%. The MobileNetV3 model achieves an accuracy of 87.64% on the Indian food image dataset. The integration of both models in ensemble learning yields a model accuracy of 92.38%, surpassing the performance of each individual model. This research revolutionizes our food relationship with the use of state-of-the-art technologies. By utilizing the most advanced transfer learning algorithm specifically designed for the precise classification of Indian cuisine, our aim is to establish a new standard in both technology and gastronomy. This will facilitate innovation in food perception, comprehension, and engagement. Full article

Skin cancer represents a significant global public health concern, with over five million new cases diagnosed annually. If not diagnosed at an early stage, skin diseases have the potential to pose a significant threat to human life. In recent years, deep learning has increasingly been used in dermatological diagnosis. In this paper, a multiclassification model based on the Inception-v2 network and the focal loss function is proposed on the basis of deep learning, and the ISIC 2019 dataset is optimised using data augmentation and hair removal to achieve seven classifications of dermatological images and generate heat maps to visualise the predictions of the model. The results show that the model has an average accuracy of 89.04%, a precision of 87.37%, recall of 90.15%, and an F1-score of 88.76%, The accuracy rates of ResNext101, MobileNetv2, Vgg19, and ConvNet are 88.50%, 85.30%, 88.57%, and 86.90%, respectively. These results show that our proposed model performs better than the above models and performs well in classifying dermatological images, which has significant application value. Full article

Traditional deep learning methods employing 2D images can only classify healthy and unhealthy seedlings; consequently, this study proposes a method by which to further classify healthy seedlings into primary seedlings and secondary seedlings and finally to differentiate three classes of seedling through a 3D point cloud for the detection of useful eggplant seedling transplants. Initially, RGB images of three types of substrate-cultivated eggplant seedlings (primary, secondary, and unhealthy) were collected, and healthy and unhealthy seedlings were classified using ResNet50, VGG16, and MobilNetV2. Subsequently, a 3D point cloud was generated for the three seedling types, and a series of filtering processes (fast Euclidean clustering, point cloud filtering, and voxel filtering) were employed to remove noise. Parameters (number of leaves, plant height, and stem diameter) extracted from the point cloud were found to be highly correlated with the manually measured values. The box plot shows that the primary and secondary seedlings were clearly differentiated for the extracted parameters. The point clouds of the three seedling types were ultimately classified directly using the 3D classification models PointNet++, dynamic graph convolutional neural network (DGCNN), and PointConv, in addition to the point cloud complementary operation for plants with missing leaves. The PointConv model demonstrated the best performance, with an average accuracy, precision, and recall of 95.83, 95.83, and 95.88%, respectively, and a model loss of 0.01. This method employs spatial feature information to analyse different seedling categories more effectively than two-dimensional (2D) image classification and three-dimensional (3D) feature extraction methods. However, there is a paucity of studies applying 3D classification methods to predict useful eggplant seedling transplants. Consequently, this method has the potential to identify different eggplant seedling types with high accuracy. Furthermore, it enables the quality inspection of seedlings during agricultural production. Full article

As people age, abnormal gait recognition becomes a critical problem in the field of healthcare. Currently, some algorithms can classify gaits with different pathologies, but they cannot guarantee high accuracy while keeping the model lightweight. To address these issues, this paper proposes a lightweight network (NSVGT-ICBAM-FACN) based on the new side-view gait template (NSVGT), improved convolutional block attention module (ICBAM), and transfer learning that fuses convolutional features containing high-level information and attention features containing semantic information of interest to achieve robust pathological gait recognition. The NSVGT contains different levels of information such as gait shape, gait dynamics, and energy distribution at different parts of the body, which integrates and compensates for the strengths and limitations of each feature, making gait characterization more robust. The ICBAM employs parallel concatenation and depthwise separable convolution (DSC). The former strengthens the interaction between features. The latter improves the efficiency of processing gait information. In the classification head, we choose to employ DSC instead of global average pooling. This method preserves the spatial information and learns the weights of different locations, which solves the problem that the corner points and center points in the feature map have the same weight. The classification accuracies for this paper’s model on the self-constructed dataset and GAIT-IST dataset are 98.43% and 98.69%, which are 0.77% and 0.59% higher than that of the SOTA model, respectively. The experiments demonstrate that the method achieves good balance between lightweightness and performance. Full article

Soil salinization poses a critical challenge to global food security, impacting plant growth, development, and crop yield. This study investigates the efficacy of deep learning techniques alongside chlorophyll fluorescence (ChlF) imaging technology for discerning varying levels of salt stress in soybean seedlings. Traditional methods for stress identification in plants are often laborious and time-intensive, prompting the exploration of more efficient approaches. A total of six classic convolutional neural network (CNN) models—AlexNet, GoogLeNet, ResNet50, ShuffleNet, SqueezeNet, and MobileNetv2—are evaluated for salt stress recognition based on three types of ChlF images. Results indicate that ResNet50 outperforms other models in classifying salt stress levels across three types of ChlF images. Furthermore, feature fusion after extracting three types of ChlF image features in the average pooling layer of ResNet50 significantly enhanced classification accuracy, achieving the highest accuracy of 98.61% in particular when fusing features from three types of ChlF images. UMAP dimensionality reduction analysis confirms the discriminative power of fused features in distinguishing salt stress levels. These findings underscore the efficacy of deep learning and ChlF imaging technologies in elucidating plant responses to salt stress, offering insights for precision agriculture and crop management. Overall, this study demonstrates the potential of integrating deep learning with ChlF imaging for precise and efficient crop stress detection, offering a robust tool for advancing precision agriculture. The findings contribute to enhancing agricultural sustainability and addressing global food security challenges by enabling more effective crop stress management. Full article

The real-time classification of fish feeding behavior plays a crucial role in aquaculture, which is closely related to feeding cost and environmental preservation. In this paper, a Fish Feeding Intensity classification model based on the improved Vision Transformer (CFFI-Vit) is proposed, which is capable of quantifying the feeding behaviors of rainbow trout (Oncorhynchus mykiss) into three intensities: strong, moderate, and weak. The process is outlined as follows: firstly, we obtained 2685 raw feeding images of rainbow trout from recorded videos and classified them into three categories: strong, moderate, and weak. Secondly, the number of transformer encoder blocks in the internal structure of the ViT was reduced from 12 to 4, which can greatly reduce the computational load of the model, facilitating its deployment on mobile devices. And finally, a residual module was added to the head of the ViT, enhancing the model’s ability to extract features. The proposed CFFI-Vit has a computational load of 5.81 G (Giga) Floating Point Operations per Second (FLOPs). Compared to the original ViT model, it reduces computational demands by 65.54% and improves classification accuracy on the validation set by 5.4 percentage points. On the test set, the model achieves precision, recall, and F1 score of 93.47%, 93.44%, and 93.42%, respectively. Additionally, compared to state-of-the-art models such as ResNet34, MobileNetv2, VGG16, and GoogLeNet, the CFFI-Vit model’s classification accuracy is higher by 6.87, 8.43, 7.03, and 5.65 percentage points, respectively. Therefore, the proposed CFFI-Vit can achieve higher classification accuracy while significantly reducing computational demands. This provides a foundation for deploying lightweight deep network models on edge devices with limited hardware capabilities. Full article

The classification of certain agricultural species poses a formidable challenge due to their inherent resemblance and the absence of dependable visual discriminators. The accurate identification of these plants holds substantial importance in industries such as cosmetics, pharmaceuticals, and herbal medicine, where the optimization of essential compound yields and product quality is paramount. In response to this challenge, we have devised an automated classification system based on deep learning principles, designed to achieve precision and efficiency in species classification. Our approach leverages a diverse dataset encompassing various cultivars and employs the Parallel Artificial Multiple Intelligence System–Ensemble Deep Learning model (P-AMIS-E). This model integrates ensemble image segmentation techniques, including U-Net and Mask-R-CNN, alongside image augmentation and convolutional neural network (CNN) architectures such as SqueezeNet, ShuffleNetv2 1.0x, MobileNetV3, and InceptionV1. The culmination of these elements results in the P-AMIS-E model, enhanced by an Artificial Multiple Intelligence System (AMIS) for decision fusion, ultimately achieving an impressive accuracy rate of 98.41%. This accuracy notably surpasses the performance of existing methods, such as ResNet-101 and Xception, which attain 93.74% accuracy on the testing dataset. Moreover, when applied to an unseen dataset, the P-AMIS-E model demonstrates a substantial advantage, yielding accuracy rates ranging from 4.45% to 31.16% higher than those of the compared methods. It is worth highlighting that our heterogeneous ensemble approach consistently outperforms both single large models and homogeneous ensemble methods, achieving an average improvement of 13.45%. This paper provides a case study focused on the Centella Asiatica Urban (CAU) cultivar to exemplify the practical application of our approach. By integrating image segmentation, augmentation, and decision fusion, we have significantly enhanced accuracy and efficiency. This research holds theoretical implications for the advancement of deep learning techniques in image classification tasks while also offering practical benefits for industries reliant on precise species identification. Full article

Cutaneous leishmaniasis (CL) is a common illness that causes skin lesions, principally ulcerations, on exposed regions of the body. Although neglected tropical diseases (NTDs) are typically found in tropical areas, they have recently become more common along Africa’s northern coast, particularly in Libya. The devastation of healthcare infrastructure during the 2011 war and the following conflicts, as well as governmental apathy, may be causal factors associated with this catastrophic event. The main objective of this study is to evaluate alternative diagnostic strategies for recognizing amastigotes of cutaneous leishmaniasis parasites at various stages using Convolutional Neural Networks (CNNs). The research is additionally aimed at testing different classification models employing a dataset of ultra-thin skin smear images of Leishmania parasite-infected people with cutaneous leishmaniasis. The pre-trained deep learning models including EfficientNetB0, DenseNet201, ResNet101, MobileNetv2, and Xception are used for the cutaneous leishmania parasite diagnosis task. To assess the models’ effectiveness, we employed a five-fold cross-validation approach to guarantee the consistency of the models’ outputs when applied to different portions of the full dataset. Following a thorough assessment and contrast of the various models, DenseNet-201 proved to be the most suitable choice. It attained a mean accuracy of 0.9914 along with outstanding results for sensitivity, specificity, positive predictive value, negative predictive value, F1-score, Matthew’s correlation coefficient, and Cohen’s Kappa coefficient. The DenseNet-201 model surpassed the other models based on a comprehensive evaluation of these key classification performance metrics. Full article

Potato malformation seriously affects commercial value, and its removal has become one of the core steps in the post-harvest and pre-sales process of potatoes. At present, this work mainly relies on manual visual inspection, which requires a lot of labor and incurs high investment costs. Therefore, precise and efficient automatic detection technology urgently needs to be developed. Due to the efficiency of deep learning based on image information in the field of complex object feature extraction and pattern recognition, this study proposes the use of the YOLOv3 algorithm to undertake potato malformation classification. However, the target box regression loss function MSE of this algorithm is prone to small errors being ignored, and the model code is relatively large, which limits its performance due to the high demand for computing hardware performance and storage space. Accordingly, in this study, CIOU loss is introduced to replace MSE, and thus the shortcoming of the inconsistent optimization direction of the original algorithm’s loss function is overcome, which also significantly reduces the storage space and computational complexity of the network model. Furthermore, deep separable convolution is used instead of traditional convolution. Deep separable convolution first convolves each channel, and then combines different channels point by point. With the introduction of an inverted residual structure and the use of the h-swish activation function, deep separable convolution based on the MobileNetv3 structure can learn more comprehensive feature representations, which can significantly reduce the computational load of the model while improving its accuracy. The test results showed that the model capacity was reduced by 66%, mAP was increased by 4.68%, and training time was shortened by 6.1 h. Specifically, the correctness rates of malformation recognition induced by local protrusion, local depression, proportional imbalance, and mechanical injury within the test set range were 94.13%, 91.00%, 95.52%, and 91.79%, respectively. Misjudgment mainly stemmed from the limitation of training samples and the original accuracy of the human judgment in type labeling. This study lays a solid foundation for the final establishment of an intelligent recognition and classification picking system for malformed potatoes in the next step. Full article

The agricultural industry has the potential to meet the increasing food production requirements and supply nutritious and healthy food products. Since the Internet of Things (IoT) phenomenon has achieved considerable growth in recent years, IoT-based systems have been established for pest detection so as to mitigate the loss of crops and reduce serious damage by employing pesticides. In the event of pest attack, the detection of crop insects is a tedious process for farmers since a considerable proportion of crop yield is affected and the quality of pest detection is diminished. Based on morphological features, conventional insect detection is an option, although the process has a disadvantage, i.e., it necessitates highly trained taxonomists to accurately recognize the insects. In recent times, automated detection of insect categories has become a complex problem and has gained considerable interest since it is mainly carried out by agriculture specialists. Advanced technologies in deep learning (DL) and machine learning (ML) domains have effectively reached optimum performance in terms of pest detection and classification. Therefore, the current research article focuses on the design of the improved artificial-ecosystem-based optimizer with deep-learning-based insect detection and classification (IAEODL-IDC) technique in IoT-based agricultural sector. The purpose of the proposed IAEODL-IDC technique lies in the effectual identification and classification of different types of insects. In order to accomplish this objective, IoT-based sensors are used to capture the images from the agricultural environment. In addition to this, the proposed IAEODL-IDC method applies the median filtering (MF)-based noise removal process. The IAEODL-IDC technique uses the MobileNetv2 approach as well as for feature vector generation. The IAEO system is utilized for optimal hyperparameter tuning of the MobileNetv2 approach. Furthermore, the gated recurrent unit (GRU) methodology is exploited for effective recognition and classification of insects. An extensive range of simulations were conducted to exhibit the improved performance of the proposed IAEODL-IDC methodology. The simulation results validated the remarkable results of the IAEODL-IDC algorithm with recent systems. Full article

Various statistical data indicate that mobile source pollutants have become a significant contributor to atmospheric environmental pollution, with vehicle tailpipe emissions being the primary contributor to these mobile source pollutants. The motion shadow generated by motor vehicles bears a visual resemblance to emitted black smoke, making this study primarily focused on the interference of motion shadows in the detection of black smoke vehicles. Initially, the YOLOv5s model is used to locate moving objects, including motor vehicles, motion shadows, and black smoke emissions. The extracted images of these moving objects are then processed using simple linear iterative clustering to obtain superpixel images of the three categories for model training. Finally, these superpixel images are fed into a lightweight MobileNetv3 network to build a black smoke vehicle detection model for recognition and classification. This study breaks away from the traditional approach of “detection first, then removal” to overcome shadow interference and instead employs a “segmentation-classification” approach, ingeniously addressing the coexistence of motion shadows and black smoke emissions. Experimental results show that the Y-MobileNetv3 model, which takes motion shadows into account, achieves an accuracy rate of 95.17%, a 4.73% improvement compared with the N-MobileNetv3 model (which does not consider motion shadows). Moreover, the average single-image inference time is only 7.3 ms. The superpixel segmentation algorithm effectively clusters similar pixels, facilitating the detection of trace amounts of black smoke emissions from motor vehicles. The Y-MobileNetv3 model not only improves the accuracy of black smoke vehicle recognition but also meets the real-time detection requirements. Full article

The use of deep learning techniques in real-time monitoring can save a lot of manpower in various scenarios. For example, mask-wearing is an effective measure to prevent COVID-19 and other respiratory diseases, especially for vulnerable populations such as children, the elderly, and people with underlying health problems. Currently, many public places such as hospitals, nursing homes, social service facilities, and schools experiencing outbreaks require mandatory mask-wearing. However, most of the terminal devices currently available have very limited GPU capability to run large neural networks. This means that we have to keep the parameter size of a neural network modest while maintaining its performance. In this paper, we propose a framework that applies deep learning techniques to real-time monitoring and uses it for the real-time monitoring of mask-wearing status. The main contributions are as follows: First, a feature fusion technique called skip layer pooling fusion (SLPF) is proposed for image classification tasks. It fully utilizes both deep and shallow features of a convolutional neural network while minimizing the growth in model parameters caused by feature fusion. On average, this technique improves the accuracy of various neural network models by 4.78% and 5.21% on CIFAR100 and Tiny-ImageNet, respectively. Second, layer attention (LA), an attention mechanism tailor-made for feature fusion, is proposed. Since different layers of convolutional neural networks make different impacts on the final prediction results, LA learns a set of weights to better enhance the contribution of important convolutional layer features. On average, it improves the accuracy of various neural network models by 2.10% and 2.63% on CIFAR100 and Tiny-ImageNet, respectively. Third, a MobileNetv2-based lightweight mask-wearing status classification model is trained, which is suitable for deployment on mobile devices and achieves an accuracy of 95.49%. Additionally, a ResNet mask-wearing status classification model is trained, which has a larger model size but achieves high accuracy of 98.14%. By applying the proposed methods to the ResNet mask-wearing status classification model, the accuracy is improved by 1.58%. Fourth, a mask-wearing status detection model is enhanced based on YOLOv5 with a spatial-frequency fusion module resulting in a mAP improvement of 2.20%. Overall, this paper presents various techniques to improve the performance of neural networks and apply them to mask-wearing status monitoring, which can help stop pandemics. Full article