Comparative evaluation of deep learning architectures for brinjal fruit disease classification

BrinjalFruitX: A field-collected image dataset for machine learning and deep learning-based disease identification in brinjal fruits.

In recent years, the use of Artificial Intelligence (AI) has played an important role in improving agricultural quality assessment, especially in fruit quality evaluation and disease detection. This study presents an AI-driven fruit quality and disease detection system that uses TensorFlow for efficient image classification. The proposed system classifies fruits into quality categories such as Good, Bad, Ripened, and Rotten, and fruit diseases such as Black Rot and Apple Scab. A Deep Convolutional Neural Network (DCNN) is trained on a diverse fruit image dataset to extract key visual features such as color, texture, and shape, which helps in achieving accurate and reliable predictions. The trained model is optimized and converted into TensorFlow Lite format to reduce computational complexity and inference latency while maintaining classification accuracy, enabling fast and efficient predictions even in resource-constrained environments. The system provides an easy-to-use interface where users can input fruit images and instantly receive quality classification, disease identification, and recommended treatment measures. Overall, the proposed solution offers a cost-effective and efficient AI-based approach to fruit quality assessment, helping to minimize post-harvest losses, support timely disease management, and enhance productivity across the agricultural supply chain.

Fruits are the important nutrition in human life. Different diseases occur in the Fruit quality that affect the economic growth. Disease detection is important for ensuring crop health, yield, and food security. Traditional methods rely on manual inspection, which is time- consuming and error-prone. Deep learning (DL) models are the powerful tool for identifying disease in various fruits. Convolutional Neural Networks (CNNs) are highly effective for detecting and classifying fruit diseases using image data, offering automated, accurate, and scalable solutions for agricultural diagnostics. Fruit disease dataset such as Kaggle for classification and roboflow dataset for identifying the disease in fruits. There are so many Challenges that include restricted data diversity, poor generalization, and lack of interpretability. Future directions for identifying fruit diseases using deep learning include explainable AI, multimodal data fusion, and real-time mobile deployment. This review aims to guide future research toward robust, scalable, and interpretable solutions.

Deep-learning models are highly parameterized, causing difficulty in inference and transfer learning. We propose a layered pathway evolution method to compress a deep convolutional neural network (DCNN) for classification of masses in DBT while maintaining the classification accuracy. Two-stage transfer learning was used to adapt the ImageNet-trained DCNN to mammography and then to DBT. In the first-stage transfer learning, transfer learning from ImageNet trained DCNN was performed using mammography data. In the second-stage transfer learning, the mammography-trained DCNN was trained on the DBT data using feature extraction from fully connected layer, recursive feature elimination and random forest classification. The layered pathway evolution encapsulates the feature extraction to the classification stages to compress the DCNN. Genetic algorithm was used in an iterative approach with tournament selection driven by count-preserving crossover and mutation to identify the necessary nodes in each convolution layer while eliminating the redundant nodes. The DCNN was reduced by 99% in the number of parameters and 95% in mathematical operations in the convolutional layers. The lesion-based area under the receiver operating characteristic curve on an independent DBT test set from the original and the compressed network resulted in 0.88±0.05 and 0.90±0.04, respectively. The difference did not reach statistical significance. We demonstrated a DCNN compression approach without additional fine-tuning or loss of performance for classification of masses in DBT. The approach can be extended to other DCNNs and transfer learning tasks. An ensemble of these smaller and focused DCNNs has the potential to be used in multi-target transfer learning.

Effective and timely diagnosis and treatment of ocular diseases is essential for swift recovery of the patients. Among ocular diseases, cataract and glaucoma are the most prevalent globally and need adequate attention. The present paper aims to develop an optimised deep learning based convolutional neural network (CNN) for the multi-classification of ocular diseases (normal, glaucoma and cataract). Three pre-trained CNNs (SqueezeNet, Darknet-53, EfficientNet-b0) were optimised concerning batch size (6/8/10) & optimiser type (SGDM, RMSProp, Adam) for obtaining maximum possible accuracy in the detection of multiple ocular diseases (cataract & glaucoma). Darknet-53 (batch size-6, optimiser type-Adam) gave the highest accuracy of 99.4% for a test sample of 1000 images. The performance metrics of Darknet-53 have been computed using a confusion matrix. Confusion matrix is also applied to calculate accuracy, sensitivity, specificity, f1 score and receiver operating curve (ROC). Through comparative performance analysis of the three CNNs, SqueezeNet, Darknet-53 and EfficientNet-b0 achieved the highest accuracy of 95%, 99.4% and 90%, respectively. The results indicate the importance of batch size and optimiser type on the performance of CNN models.

The convolutional neural networks (CNNs) are a powerful tool of image classification that has been widely adopted in applications of automated scene segmentation and identification. However, the mechanisms underlying CNN image classification remain to be elucidated. In this study, we developed a new approach to address this issue by investigating transfer of learning in representative CNNs (AlexNet, VGG, ResNet-101, and Inception-ResNet-v2) on classifying geometric shapes based on local/global features or invariants. While the local features are based on simple components, such as orientation of line segment or whether two lines are parallel, the global features are based on the whole object such as whether an object has a hole or whether an object is inside of another object. Six experiments were conducted to test two hypotheses on CNN shape classification. The first hypothesis is that transfer of learning based on local features is higher than transfer of learning based on global features. The second hypothesis is that the CNNs with more layers and advanced architectures have higher transfer of learning based global features. The first two experiments examined how the CNNs transferred learning of discriminating local features (square, rectangle, trapezoid, and parallelogram). The other four experiments examined how the CNNs transferred learning of discriminating global features (presence of a hole, connectivity, and inside/outside relationship). While the CNNs exhibited robust learning on classifying shapes, transfer of learning varied from task to task, and model to model. The results rejected both hypotheses. First, some CNNs exhibited lower transfer of learning based on local features than that based on global features. Second the advanced CNNs exhibited lower transfer of learning on global features than that of the earlier models. Among the tested geometric features, we found that learning of discriminating inside/outside relationship was the most difficult to be transferred, indicating an effective benchmark to develop future CNNs. In contrast to the “ImageNet” approach that employs natural images to train and analyze the CNNs, the results show proof of concept for the “ShapeNet” approach that employs well-defined geometric shapes to elucidate the strengths and limitations of the computation in CNN image classification. This “ShapeNet” approach will also provide insights into understanding visual information processing the primate visual systems.

COVID-19 originated in Wuhan, China, in December 2019 and quickly became a global outbreak in January 2020. COVID-19 is a disease caused by SARS-CoV-2, which is a human transmission disease. Since it is a human transmission disease, thus mass gathering in public is not allowed to prevent the possible spread of COVID-19. However, the current monitoring technology, such as closed-circuit television (CCTV), only cover a limited area of the public and lack of mobility. Image classification is one of the approaches that can detect crowds in an image and can be done through either machine learning or deep learning approach. Recently, deep learning, especially convolutional neural networks (CNNs) outperform classical machine learning in image classification and the common approach for modelling CNN is through transfer learning. Thus, this study aims to develop a convolutional neural network that can detect illegal crowd gathering from offline drone view images through image classification using the transfer learning technique. Several models are used to train on the same dataset obtained, and the all-model performance is evaluated through a confusion matrix. Based on performance analysis, it shows that the ResNet50 model outperforms the VGG16 model and InceptionV3 model by achieving 95% test accuracy, 95% precision, 95% recall and 95% F1-score. In conclusion, it can be concluded that the deep learning approach uses a pre-trained convolutional neural network that can be used to classify object images in this study.

Abstract. New particle formation (NPF) in the atmosphere is globally an important source of climate relevant aerosol particles. Occurrence of NPF events is typically analyzed by researchers manually from particle size distribution data day by day, which is time consuming and the classification of event types may be inconsistent. To get more reliable and consistent results, the NPF event analysis should be automatized. We have developed an automatic analysis method based on deep learning, a subarea of machine learning, for NPF event identification. To our knowledge, this is the first time that a deep learning method, i.e., transfer learning of a convolutional neural network (CNN), has successfully been used to automatically classify NPF events into different classes directly from particle size distribution images, similarly to how the researchers carry out the manual classification. The developed method is based on image analysis of particle size distributions using a pretrained deep CNN, named AlexNet, which was transfer learned to recognize NPF event classes (six different types). In transfer learning, a partial set of particle size distribution images was used in the training stage of the CNN and the rest of the images for testing the success of the training. The method was utilized for a 15-year-long dataset measured at San Pietro Capofiume (SPC) in Italy. We studied the performance of the training with different training and testing of image number ratios as well as with different regions of interest in the images. The results show that clear event (i.e., classes 1 and 2) and nonevent days can be identified with an accuracy of ca. 80 %, when the CNN classification is compared with that of an expert, which is a good first result for automatic NPF event analysis. In the event classification, the choice between different event classes is not an easy task even for trained researchers, and thus overlapping or confusion between different classes occurs. Hence, we cross-validated the learning results of CNN with the expert-made classification. The results show that the overlapping occurs, typically between the adjacent or similar type of classes, e.g., a manually classified Class 1 is categorized mainly into classes 1 and 2 by CNN, indicating that the manual and CNN classifications are very consistent for most of the days. The classification would be more consistent, by both human and CNN, if only two different classes are used for event days instead of three classes. Thus, we recommend that in the future analysis, event days should be categorized into classes of “quantifiable” (i.e., clear events, classes 1 and 2) and “nonquantifiable” (i.e., weak events, Class 3). This would better describe the difference of those classes: both formation and growth rates can be determined for quantifiable days but not both for nonquantifiable days. Furthermore, we investigated more deeply the days that are classified as clear events by experts and recognized as nonevents by the CNN and vice versa. Clear misclassifications seem to occur more commonly in manual analysis than in the CNN categorization, which is mostly due to the inconsistency in the human-made classification or errors in the booking of the event class. In general, the automatic CNN classifier has a better reliability and repeatability in NPF event classification than human-made classification and, thus, the transfer-learned pretrained CNNs are powerful tools to analyze long-term datasets. The developed NPF event classifier can be easily utilized to analyze any long-term datasets more accurately and consistently, which helps us to understand in detail aerosol–climate interactions and the long-term effects of climate change on NPF in the atmosphere. We encourage researchers to use the model in other sites. However, we suggest that the CNN should be transfer learned again for new site data with a minimum of ca. 150 figures per class to obtain good enough classification results, especially if the size distribution evolution differs from training data. In the future, we will utilize the method for data from other sites, develop it to analyze more parameters and evaluate how successfully CNN could be trained with synthetic NPF event data.

We developed a computer-aided diagnosis (CADx) method for classification between benign nodule, primary lung cancer, and metastatic lung cancer and evaluated the following: (i) the usefulness of the deep convolutional neural network (DCNN) for CADx of the ternary classification, compared with a conventional method (hand-crafted imaging feature plus machine learning), (ii) the effectiveness of transfer learning, and (iii) the effect of image size as the DCNN input. Among 1240 patients of previously-built database, computed tomography images and clinical information of 1236 patients were included. For the conventional method, CADx was performed by using rotation-invariant uniform-pattern local binary pattern on three orthogonal planes with a support vector machine. For the DCNN method, CADx was evaluated using the VGG-16 convolutional neural network with and without transfer learning, and hyperparameter optimization of the DCNN method was performed by random search. The best averaged validation accuracies of CADx were 55.9%, 68.0%, and 62.4% for the conventional method, the DCNN method with transfer learning, and the DCNN method without transfer learning, respectively. For image size of 56, 112, and 224, the best averaged validation accuracy for the DCNN with transfer learning were 60.7%, 64.7%, and 68.0%, respectively. DCNN was better than the conventional method for CADx, and the accuracy of DCNN improved when using transfer learning. Also, we found that larger image sizes as inputs to DCNN improved the accuracy of lung nodule classification.

Deep Learning is increasingly being adopted by industry for computer vision applications running on embedded devices. While Convolutional Neural Networks' accuracy has achieved a mature and remarkable state, inference latency and throughput are a major concern especially when targeting low-cost and low-power embedded platforms. CNNs' inference latency may become a bottleneck for Deep Learning adoption by industry, as it is a crucial specification for many real-time processes. Furthermore, deployment of CNNs across heterogeneous platforms presents major compatibility issues due to vendor-specific technology and acceleration libraries. In this work, we present QS-DNN, a fully automatic search based on Reinforcement Learning which, combined with an inference engine optimizer, efficiently explores through the design space and empirically finds the optimal combinations of libraries and primitives to speed up the inference of CNNs on heterogeneous embedded devices. We show that, an optimized combination can achieve 45x speedup in inference latency on CPU compared to a dependency-free baseline and 2x on average on GPGPU compared to the best vendor library. Further, we demonstrate that, the quality of results and time "to-solution" is much better than with Random Search and achieves up to 15x better results for a short-time search.

Skin diseases are common health problems that require early diagnosis to prevent serious complications. This study aims to develop an automatic skin disease image classification system using a transfer learning approach based on Convolutional Neural Networks (CNN). Image datasets were obtained from Kaggle and underwent preprocessing stages including resizing, normalization, and augmentation. Four CNN architectures were evaluated: VGG16, ResNet50, MobileNetV2, and InceptionV3, implemented using Python and the Keras library on the Google Colab platform. The dataset was split into three training and testing ratios (90:10, 80:20, and 70:30) to assess the impact of data proportion on model performance. Models were trained by modifying the output layer to match the number of classes, and evaluated using accuracy, precision, recall, F1-score, confusion matrix, and ROC curve metrics. The results show that a 70:30 ratio yielded the most optimal training performance. InceptionV3 achieved the highest validation accuracy at 80.04%, but experienced overfitting, while VGG16 demonstrated better generalization to test data. This study proves that transfer learning with CNN is effective in improving the accuracy of automatic skin disease diagnosis and has the potential to become an efficient diagnostic solution, especially in areas with limited medical infrastructure.

Mammography is the modality of choice for the early detection of breast cancer. Deep learning, using convolutional neural networks (CNNs) specifically, have achieved extraordinary results in the classification of diseases, including breast cancer, on imaging. The images used to train a CNN varies based on several factors, such as imaging technique, imaging equipment, and study population; these factors significantly affect the accuracy of the CNN models. The aim of this study was to develop a novel CNN for the classification of mammograms as benign or malignant and to compare its utility to that of popular pre-trained CNNs in the literature using transfer learning. All CNNs were trained to detect breast cancer on mammograms using mammograms from a created database of Mexican women (MAMMOMX-PABIOM) and from a public database of UK women (MIAS). A database (MAMMOMX-PABIOM) was built comprising 1,070 mammography images of 235 Mexican patients from 4 hospitals in Mexico. The study also used mammographic images from the Mammographic Image Analysis Society (MIAS) public database, which comprises mammography images from the UK National Breast Screening Programme. A novel CNN was developed and trained based on different configurations of training data; the accuracy of the models resulting from the novel CNN were compared with models resulting from more advanced pre-trained CNNs (DenseNet121, MobileNetV2, ResNet 50, VGG16) which were built using transfer learning. Of the models resulting from pre-trained CNNs using transfer learning, the model based on MobileNetV2 and training data from the MAMMOMX-PABIOM database achieved the highest validation accuracy of 70.10%. In comparison, the novel CNN, when trained with the data configuration A6, which comprises data from both the MAMMOMX-PABIOM database and the MIAS database, produced a much higher accuracy of 99.14%. Although transfer learning is a widely used technique when training, data is scarce. The novel CNN produced much higher accuracy values across all configurations of training data compared to the accuracy values of pre-trained CNNs using transfer learning. In addition, this study addresses the gap in that neither a national database of mammograms of Mexican women exists, nor a deep learning tool for the classification of mammograms as benign or malignant that is focused on this population.

Deep learning strategies for critical heat flux detection in pool boiling

Combined Transfer Learning and Test-Time Augmentation Improves Convolutional Neural Network-Based Semantic Segmentation of Prostate Cancer from Multi-Parametric MR Images

Healthcare industry plays a vital role in improving daily life. Machine learning and deep neural networks have contributed a lot to benefit various industries nowadays. Agriculture, healthcare, machinery, aviation, management, and even education have all benefited from the development and implementation of machine learning. Deep neural networks provide insight and assistance in improving daily activities. Convolutional neural network (CNN), one of the deep neural network methods, has had a significant impact in the field of computer vision. CNN has long been known for its ability to improve detection and classification in images. With the implementation of deep learning, more deep knowledge can be gathered and help healthcare workers to know more about a patient’s disease. Deep neural networks and machine learning are increasingly being used in healthcare. The benefit they provide in terms of improved detection and classification has a positive impact on healthcare. CNNs are widely used in the detection and classification of imaging tasks like CT and MRI scans. Although CNN has advantages in this industry, the algorithm must be trained with a large number of data sets in order to achieve high accuracy and performance. Large medical datasets are always unavailable due to a variety of factors such as ethical concerns, a scarcity of expert explanatory notes and labelled data, and a general scarcity of disease images. In this paper, lung nodules classification using CNN with transfer learning is proposed to help in classifying benign and malignant lung nodules from CT scan images. The objectives of this study are to pre-process lung nodules data, develop a CNN with transfer learning algorithm, and analyse the effectiveness of CNN with transfer learning compared to standard of other methods. According to the findings of this study, CNN with transfer learning outperformed standard CNN without transfer learning.