Enhancing coffee bean classification: a comparative analysis of pre-trained deep learning models

Comparative analysis of deep convolution neural network models on small scale datasets

This article investigates whether higher classification accuracy can always be achieved by utilizing a pre-trained deep learning model as the feature extractor in the Bag-of-Deep-Visual-Words (BoDVW) classification model, as opposed to directly using the new classification layer of the pre-trained model for classification. Considering the multiple factors related to the feature extractor -such as model architecture, fine-tuning strategy, number of training samples, feature extraction method, and feature encoding method—we investigate these factors through experiments and then provide detailed answers to the question. In our experiments, we use five feature encoding methods: hard-voting, soft-voting, locally constrained linear coding, super vector coding, and fisher vector (FV). We also employ two popular feature extraction methods: one (denoted as Ext-DFs(CP)) uses a convolutional or non-global pooling layer, and another (denoted as Ext-DFs(FC)) uses a fully-connected or global pooling layer. Three pre-trained models—VGGNet-16, ResNext-50(32×4d), and Swin-B—are utilized as feature extractors. Experimental results on six datasets (15-Scenes, TF-Flowers, MIT Indoor-67, COVID-19 CXR, NWPU-RESISC45, and Caltech-101) reveal that compared to using the pre-trained model with only the new classification layer re-trained for classification, employing it as the feature extractor in the BoDVW model improves the accuracy in 35 out of 36 experiments when using FV. With Ext-DFs(CP), the accuracy increases by 0.13% to 8.43% (averaged at 3.11%), and with Ext-DFs(FC), it increases by 1.06% to 14.63% (averaged at 5.66%). Furthermore, when all layers of the pre-trained model are fine-tuned and used as the feature extractor, the results vary depending on the methods used. If FV and Ext-DFs(FC) are used, the accuracy increases by 0.21% to 5.65% (averaged at 1.58%) in 14 out of 18 experiments. Our results suggest that while using a pre-trained deep learning model as the feature extractor does not always improve classification accuracy, it holds great potential as an accuracy improvement technique.

In the realm of computer vision, image classification is a critical issue with many applications, including multimedia content analysis, security and surveillance, and medical imaging. The accuracy of image classification algorithms has considerably increased with the development of deep learning. The discipline of image classification has dramatically benefited from the usage of pre-trained Convolutional Neural Network (CNN) models. In this study, we perform image classification on the Wang dataset composed of 1000 images separated into ten categories, using six different pre-trained CNN models. The research made use of pre-trained versions of VGG16, Densenet, Mobilenet, Inception V3, Resnet50, and Xception models. We assessed the model performances in terms of training and testing accuracy. Testing accuracies for ten unique batches of data were calculated and averaged out. Densenet outperformed state-of-the-art models like Xception by a small margin, mainly due to low data availability. The findings of this study show how pre-trained models have advanced the field of image classification and shed light on how well these models perform in diverse image classification tasks. This study can serve as a valuable reference for researchers and practitioners in the field of computer vision and deep learning and help inform their choices when selecting pre-trained models for image classification, depending on their needs, while also considering data availability and computational constraints.

Pneumonia is a lung infection and causes the inflammation of the small air sacs (Alveoli) in one or both lungs. Proper and faster diagnosis of pneumonia at an early stage is imperative for optimal patient care. Currently, chest X-ray is considered as the best imaging modality for diagnosing pneumonia. However, the interpretation of chest X-ray images is challenging. To this end, we aimed to use an automated convolutional neural network-based transfer-learning approach to detect pneumonia in paediatric chest radiographs. Herein, an automated convolutional neural network-based transfer-learning approach using four different pre-trained models (i.e. VGG19, DenseNet121, Xception, and ResNet50) was applied to detect pneumonia in children (1-5 years) chest X-ray images. The performance of different proposed models for testing data set was evaluated using five performances metrics, including accuracy, sensitivity/recall, Precision, area under curve, and F1 score. All proposed models provide accuracy greater than 83.0% for binary classification. The pre-trained DenseNet121 model provides the highest classification performance of automated pneumonia classification with 86.8% accuracy, followed by Xception model with an accuracy of 86.0%. The sensitivity of the proposed models was greater than 91.0%. The Xception and DenseNet121 models achieve the highest classification performance with F1-score greater than 89.0%. The plotted area under curve of receiver operating characteristics of VGG19, Xception, ResNet50, and DenseNet121 models are 0.78, 0.81, 0.81, and 0.86, respectively. Our data showed that the proposed models achieve a high accuracy for binary classification. Transfer learning was used to accelerate training of the proposed models and resolve the problem associated with insufficient data. We hope that these proposed models can help radiologists for a quick diagnosis of pneumonia at radiology departments. Moreover, our proposed models may be useful to detect other chest-related diseases such as novel Coronavirus 2019. Herein, we used transfer learning as a machine learning approach to accelerate training of the proposed models and resolve the problem associated with insufficient data. Our proposed models achieved accuracy greater than 83.0% for binary classification.

The International Classification of Diseases (ICD) serves as a widely employed framework for assigning diagnosis codes to electronic health records of patients. These codes facilitate the encapsulation of diagnoses and procedures conducted during a patient’s hospitalisation. This study aims to devise a predictive model for ICD codes based on the MIMIC-III clinical text dataset. Leveraging natural language processing techniques and deep learning architectures, we constructed a pipeline to distill pertinent information from the MIMIC-III dataset: the Medical Information Mart for Intensive Care III (MIMIC-III), a sizable, de-identified, and publicly accessible repository of medical records. Our method entails predicting diagnosis codes from unstructured data, such as discharge summaries and notes encompassing symptoms. We used state-of-the-art deep learning algorithms, such as recurrent neural networks (RNNs), long short-term memory (LSTM) networks, bidirectional LSTM (BiLSTM) and BERT models after tokenizing the clinical test with Bio-ClinicalBERT, a pre-trained model from Hugging Face. To evaluate the efficacy of our approach, we conducted experiments utilizing the discharge dataset within MIMIC-III. Employing the BERT model, our methodology exhibited commendable accuracy in predicting the top 10 and top 50 diagnosis codes within the MIMIC-III dataset, achieving average accuracies of 88% and 80%, respectively. In comparison to recent studies by Biseda and Kerang, as well as Gangavarapu, which reported F1 scores of 0.72 in predicting the top 10 ICD-10 codes, our model demonstrated better performance, with an F1 score of 0.87. Similarly, in predicting the top 50 ICD-10 codes, previous research achieved an F1 score of 0.75, whereas our method attained an F1 score of 0.81. These results underscore the better performance of deep learning models over conventional machine learning approaches in this domain, thus validating our findings. The ability to predict diagnoses early from clinical notes holds promise in assisting doctors or physicians in determining effective treatments, thereby reshaping the conventional paradigm of diagnosis-then-treatment care. Our code is available online.

Deep neural networks such as Convolutional Neural Networks (CNNs) have achieved several significant milestones in visual data analytics. Benefited from transfer learning, many researchers use pre-trained CNN models to accelerate the training process. However, there is still uncertainty about the deep learning models, structures, and applications. For instance, the diversity of the datasets may affect the performance of each pre-trained model. Therefore, in this paper, we proposed a new approach based on genetic algorithms to select or regenerate the best pre-trained CNN models for different visual datasets. A new genetic encoding model is presented which denotes different pre-trained models in our population. During the evolutionary process, the optimal genetic code that represents the best model is selected, or new competitive individuals are generated using the genetic operations. The experimental results illustrate the effectiveness of the proposed framework which outperforms several existing approaches in visual data classification.

Convolution Neural Network plays an important role in the field of agriculture for the identification and classification of diseases in the different types of crops. Most of the families in India belong to the farming background. So, in farming the paddy crop plays the crucial role because most of the famers are interested in growing the paddy crop. There are many diseases which damages the paddy crop. and it effects the production of rice. Due to this, farmers can’t meet the required production of food. In order to reduce the damage from different types of diseases on paddy crop, the CNN model is chosen. There are other sources like machine learning technology for identification of diseases but in recent times due to increase in technology and accuracy metrics the deep learning is widely used. In paddy crop, there are more than 30 varieties of diseases which damage the crop. Among these, four types of diseases like Leaf Blast, Brown Spot, Hispa and Bacterial Leaf Blight are more commonly observed in the crop. And these diseases are similar to each other, so that they can’t even be identified by the naked eye. In order to reduce the damage from diseases they should be identified in early stage and the necessary precautions must be taken for the increase in the crop yield. The main objective of this project is to make a deep learning model for the identification and classification of paddy crop diseases through transfer learning and image processing and all the process is done in deep learning. This project is mainly focuses on four disease classes and the classification process, the accuracy metrics is analyzed. Among the different pre trained models such as InceptionV3, VGG 16, Resnet 50, the better accuracy is achieved from Inceptionv3 with an accuracy of 91.23%.

Automatic detection of knee medial collateral ligament (MCL) tear from magnetic resonance imaging using deep neural network.

This paper introduces an approach to employ deep features for person re-identification. In contrast to existing works, we focus on using pre-trained deep models and their concept-based output to enhance attribute presentations of person images. There are two main contributions. First, we investigate recent state-of-the-art deep learning models for the task and provide a comprehensive evaluation. Second, we present an approach to improve identification accuracy of a standard attribute-based person re-identification approach. By using pre-trained models, we avoid re-training new deep models which always require a huge amount of training data and high computational cost. The idea is to utilize the correlation between generic concepts learned by the deep models and specific pre-defined attributes commonly used for person re-identification. We employ the deeply learned features from generic concepts to represent person images. These images and their manually annotated attributes are then used to train attribute classifiers. Given the classifiers, attributes of the probe and gallery images can be automatically extracted to compose attribute-based feature vectors. Re-identification is done by matching the vectors. Experiments conducted on several benchmark datasets demonstrated the effectiveness of the proposed approach.

Comparison of pre-trained deep learning model classification performance of COVID-19 and normal chest X-ray images

The prevalence of age-related brain issues has risen in developed countries because of changes in lifestyle. Alzheimer's disease leads to a rapid and irreversible decline in cognitive abilities by damaging memory cells. A ResNet-18-based system is proposed, integrating Depth Convolution with a Squeeze and Excitation (SE) block to minimize tuning parameters. This design is based on analyses of existing deep learning architectures and feature extraction techniques. Additionally, pre-trained ResNet-18 models were created with and without the SE block to compare ROC and accuracy values across different hyperparameters. The proposed model achieved ROC values of 95% for Alzheimer's Disease (AD), 95% for Cognitively Normal (CN), and 93% for Mild Cognitive Impairment (MCI), with a maximum test accuracy of 88.51%. However, the pre-trained model with SE had 93.26% accuracy and ROC values of 98%, 99%, and 98%, while the model without SE had 94%, 97%, and 94% ROC values and 92.41% accuracy. Collecting medical data can be expensive and raises ethical concerns. Small data sets are also prone to local minima issues in the cost function. A scratch model that experiences extensive hyperparameter tuning may end up being either overfitted or underfitted. Class imbalance also reduces performance. Transfer learning is most effective with small, imbalanced datasets, and pre-trained models with SE blocks perform better than others. The proposed model introduced a method to reduce training parameters and prevent overfitting from imbalanced medical data. Overall performance findings show that the suggested approach performs better than the state-of-the-art techniques.

WhisPAr: Transferring pre-trained audio models to fine-grained classification via Prompt and Adapter

This article presents a pioneering approach for predicting wildfires risks using deep learning techniques. By combining convolutional neural networks (CNNs), recurrent neural networks (RNNs) and Adaptive Moment Estimation (ADAM), our framework analyses geospatial and environmental data to capture the intricate dynamics of disasters. Our model integrates satellite imagery, climate data, socioeconomic factors, and historical records to accurately assess risks. Leveraging transfer learning, we optimize training efficiency with pre-trained models. Extensive experiments demonstrate the superior performance of our deep learning framework compared to traditional methods. With its ability to enable proactive planning and decision-making, our approach strengthens disaster preparedness and response strategies. This research represents a significant advancement in utilizing deep learning for predicting wildfires risks, paving the way for further innovations in this vital field.

Black ice has recently been identified as a major cause of transportation accidents due to detecting difficulties on the road surface. It is crucial to provide traffic users with black ice warnings beforehand to sustain commuting safety. The identification of black ice, however, is a difficult initiative, since it necessitates the installation of sophisticated monitoring stations and demands frequently manual inspection. In order to build an economical automatic black ice detection technique, the datasets are built upon a variety of weather conditions, including clear, snowy, rainy, and foggy conditions, as well as two distinct forms of pavement: asphalt and concrete pavement. The Mask R-CNN model was performed to construct the black ice detection via image segmentation. The deep learning architecture was constructed based on pre-trained convolutional neural network models (ResNetV2) for black ice detection purposes. Different pretrained models and architecture (Yolov4) were then compared to determine which is superior for image segmentation of black ice. Afterward, through the retrieved bounding box data, the degree of danger area is determined based on the number of segmentation pixels. In general, the training results confirm the feasibility of the black ice detection method via the deep learning technique. Within “Clear” weather conditions, the detecting precision can be achieved up to 92.5%. The results also show that the increase in the number of weather types leads to a noticeable reduction in the training precision. Overall, the proposed image segmentation method is capable of real-time detection and can caution commuters of black ice in advance.

On-barn cattle facial recognition using deep transfer learning and data augmentation