Particle Swarm Optimization Algorithm for Hyperparameter Convolutional Neural Network and Transfer Learning VGG16 Model

Plants are an integral part of human life, and the ability to identify a fruit plant from its leaf image is both fascinating and challenging. Advances in image processing and pattern recognition have made it feasible to perform plant identification using digital images. Machine learning (ML) and convolutional neural network (CNN) models have demonstrated strong capabilities in handling texture-related features in image processing tasks, including segmentation. In this Paper, we present an approach that utilises ML and CNN models, including AlexNet, Inception, ResNet, LeNet, VGG Net, MobileNet, DenseNet, and GoogLeNet. These models are employed for classifying fruit plants through leaf images, achieving promising performance on leaf image datasets. Among the evaluated CNN models, MobileNet achieved the highest performance with 94.81% training, 99.57% validation, and 99.44% test accuracy, outperforming all others. LeNet, AlexNet, and ResNet also showed strong results above 93%, while DenseNet, GoogLeNet, and VGGNet achieved moderate accuracy. Inception performed the weakest, confirming MobileNet as the most efficient and reliable model for fruit plant leaf classification.

The thesis addresses the following challenging problems of detecting and tracking humans in the presence of occlusions in typical surveillance videos: (1) adaptation of semantic-part-based human detectors to new surveillance video sequence when trained detectors using other video data not performing well on the new video data; (2) tracking of humans with person identification minimizing identification errors over longer tracking periods; and (3) hierarchical spatial and temporal analysis for discriminative tracking of human targets. The thesis aims to improve the state-of-the-art performance in human detection and tracking by studying the human detectors, extended tracking of track segments (tracklets) generated from short term tracking of detection responses. For the adaptation of semantic-part-based human detectors to new surveillance video sequence, a uni ed deep CNN model for joint learning of features, semantic pedestrian part detectors and a transfer learning model is developed. The components within this deep CNN model interact with each other in the learning process, which facilitates the optimization of the learned components during the co-operative learning. In particular, an adaptation layer is proposed to embed the capability of knowledge transfer into the CNN model. As a result, the proposed transferred CNN (T-CNN) model is able to transfer the visual knowledge of the semantic pedestrian parts from the source data to target data. Extensive experimental evaluations show that the proposed method is better than other deep learning based methods in terms of detection performance. Moreover, the adaptive deep features can be complementary to the pre-defined features used by other state-of-the-art methods. For tracking of humans with person identification minimizing identification errors over longer tracking periods, a novel method, based on online target-specific metric learning and coherent dynamics estimation, for tracklet association by network flow optimization is developed. The proposed framework aims to exploit appearance and motion cues to prevent identity switches during tracking and also to recover missed detections. The target-specific metrics (appearance cue) and motion dynamics (motion cue) are proposed to be learned and estimated online, i.e. during the tracking process. Furthermore, a learning algorithm to learn the weights of motion and appearance tracking cues for tracklet affinity models is proposed to handle some difficult situations. Extensive evaluations following state-of-the-art practices have been conducted and the results from these evaluations show the improvements by the proposed method over some existing state-of-the-art methods. In hierarchical spatial and temporal analysis for discriminative tracking of human targets, inspired by recent advances in convolutional neural network (CNN) architectures, a novel uni ed deep model for tracklet association, which can jointly learn the CNNs and temporally constrained metrics, is developed. Furthermore, a novel loss function incorporating temporally constrained multi-task learning mechanism is developed to make the deep model more effective in solving the tracklet association problem. Extensive experimental results comparing with the state-of-the-art methods demonstrate the effectiveness and superiority of the proposed unified deep model.

Among the many deep learning methods, the convolutional neural network (CNN) model has an excellent performance in image recognition. Research on identifying and classifying image datasets using CNN is ongoing. Animal species recognition and classification with CNN is expected to be helpful for various applications. However, sophisticated feature recognition is essential to classify quasi-species with similar features, such as the quasi-species of parrots that have a high color similarity. The purpose of this study is to develop a vision-based mobile application to classify endangered parrot species using an advanced CNN model based on transfer learning (some parrots have quite similar colors and shapes). We acquired the images in two ways: collecting them directly from the Seoul Grand Park Zoo and crawling them using the Google search. Subsequently, we have built advanced CNN models with transfer learning and trained them using the data. Next, we converted one of the fully trained models into a file for execution on mobile devices and created the Android package files. The accuracy was measured for each of the eight CNN models. The overall accuracy for the camera of the mobile device was 94.125%. For certain species, the accuracy of recognition was 100%, with the required time of only 455 ms. Our approach helps to recognize the species in real time using the camera of the mobile device. Applications will be helpful for the prevention of smuggling of endangered species in the customs clearance area.

IntroductionThe utility of non-contact technologies for screening infectious diseases such as COVID-19 can be enhanced by improving the underlying Artificial Intelligence (AI) models and integrating them into data visualization frameworks. AI models that are a fusion of different Machine Learning (ML) models where one has leveraged the different positive attributes of these models have the potential to perform better in detecting infectious diseases such as COVID-19. Furthermore, integrating other patient data such as clinical, socio-demographic, economic and environmental variables with the image data (e.g., chest X-rays) can enhance the detection capacity of these models.MethodsIn this study, we explore the use of chest X-ray data in training an optimized hybrid AI model based on a real-world dataset with limited sample size to screen patients with COVID-19. We develop a hybrid Convolutional Neural Network (CNN) and Random Forest (RF) model based on image features extracted through a CNN and EfficientNet B0 Transfer Learning Model and applied to an RF classifier. Our approach includes an intermediate step of using the RF's wrapper function, the Boruta Algorithm, to select important variable features and further reduce the number of features prior to using the RF model.Results and discussionThe new model obtained an accuracy and recall of 96% for both and outperformed the base CNN model and four other experimental models that combined transfer learning and alternative options for dimensionality reduction. The performance of the model fares closely to relatively similar models previously developed, which were trained on large datasets drawn from different country contexts. The performance of the model is very close to that of the “gold standard” PCR tests, which demonstrates the potential for use of this approach to efficiently scale-up surveillance and screening capacities in resource limited settings.

The COVID-19 pandemic grounds a major outbreak around the world, having a severe impact on the health and life of many people globally. The critical step in fighting COVID-19 is the capability to identify the infected patients during initial stages and situate them under extraordinary care. Detecting COVID-19 disease from radiography and radiology images is one of the effective way to detect the infected patients. Inspired by the chest radiograms of patients infected with COVID-19, we study the application of machine learning and convolutional neural network models to detect COVID-19 patients from their chest radiography images. We first prepare a dataset of chest X-rays from the publicly available ieee8023/covid-chestxray-dataset. This paper aims to provide the following contributions. Firstly, the dataset is preprocessed and segregated as healthy, COVID-19, bacterial pneumonia and viral pneumonia. Secondly, the dataset is processed to form the initial trained layers of base model and is fitted with several convolutional neural network models like VGG, ResNet, Xception and DenseNet to extract the high-level general features. Thirdly, the base model of several convolutional neural network models are added to the custom layers developed with transfer learning deep learning approach to analyze the performance of prediction of COVID-19 patients. Fourth, the performance of the convolutional neural network models along with transfer learning is analyzed with the metrics like model loss, precision, accuracy, recall and F-Score. The project is implemented with Python in Spyder under anaconda navigator. Experimental results show that Xception CNN model is found to experience 95% accuracy with the available chest X-ray images.KeywordsCNNVGGResNetXceptionDenseNet and transfer learning

Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries

Oral cancer detection using feature-level fusion and novel self-attention mechanisms

The leather industry plays a crucial role in the production of high-quality leather products to remain competitive in the market. Due to various reasons such as material handling and turning, leather defects can appear at different stages of the production process. This paper proposed deep learning techniques, specifically transfer learning, deep convolutional neural networks (D-CNN), and ensemble learning for automating leather defect detection and classification. The dataset was taken from the open source Kaggle. The dataset was preprocessed from the beginning. However, we performed Error Level Analysis (ELA) to detect possible changes or fraud in the image. We also used data augmentation techniques (resizing, rescaling, flipping, rotation, zooming, and contrasting) on the dataset to improve the model performance. This study investigated deep learning architectures for automatic leather defect detection, comparing them with seven deep convolutional neural networks (D-CNN) models and transfer learning architectures. Furthermore, we introduce and evaluate two novel ensemble models: MER built on transfer learning architecture (MobileNetV2, EfficientNetB0, and ResNet50) and AZL built on D-CNN architecture (AlexNet, ZfNet, and LeNet). A key contribution of this study is the demonstration of significant performance improvements achieved by strategically integrating squeeze and excitation and label smoothing techniques into transfer learning, D-CNN, and ensemble frameworks. Our proposed MER ensemble method achieves a state-of-the-art of 96.39% for leather defect detection. The proposed model was evaluated using performance metrics including precision, recall, F1-score, AUC, ROC, and Matthews Correlation Coefficient (MCC). Additionally, Grad-CAM was employed for explainable AI to visualize and interpret the model’s decision-making process. Comparative analysis against separate transfer learning and D-CNN models fails to establish the superior performance of our MER ensemble, which highlights the potential to significantly advance automated quality inspection in leather production. This study provides insights into evaluating the best deep learning techniques for leather defect classification, paving the way for more accurate, efficient, and reliable industrial applications. Proposes a robust deep learning-based framework for automated leather defect detection using transfer learning, deep CNNs, and two novel ensemble models (MER and AZL), enhanced with squeeze-and-excitation and label smoothing techniques. Achieves state-of-the-art performance with the proposed MER ensemble model, achieve 96.39% accuracy, and demonstrates superior results across precision, recall, F1-score, AUC–ROC, and MCC. Integrates Error Level Analysis (ELA), extensive data augmentation, and Grad-CAM–based explainable AI to ensure data reliability, improve generalization, and provide transparent visual interpretation of defect regions for industrial quality inspection.

Understanding the learning mechanism of convolutional neural networks in spectral analysis

Batik is the work of the Indonesian nation which is a combination of art and technology by the ancestors of the Indonesian people. UNESCO designated batik as a Humanitarian Heritage for Masterpieces of the Oral and Intangible Heritage of Humanity, followed by a presidential decree on 2 October 2009 which was designated as Indonesia's National Batik Day. In maintaining the existence of batik in the era of technological advances, they have utilized Artificial Intelligence and Machine Learning technologies. Even though research on batik motifs has become a common topic, there are still many mistakes found during the process of identifying motifs. As is well known, Indonesia has various types of traditional batik which have very diverse colors, patterns and motifs. This is the main problem in the identification of batik motifs, where it is found that many batik motifs adopt or have similarities in either pattern or color to other batik motifs, giving rise to thin predictions when identified with other motifs. This study uses the Convolutional Neural Networks (CNN) method using Edge Detection to identify batik motifs. Using the main dataset of 1106 images divided into 4 classes, namely Kawung, Megamendung, Merak Ngibing, and Parang motifs. The research is focused on comparing the results of prediction effectiveness on the CNN model with Canny edge detection (CNN-Canny) and the CNN model with Sobel edge detection (CNN-Sobel). The training process for each model is applied the same configuration to the dataset with a ratio of 8:2. Then in the model augmentation the functions of random flip, random zoom, and random invert are applied. The results obtained from learning the machine learning model at the testing and validation stage on the CNN-Sobel model obtained an accuracy of 91.2% in the training process and 91.8% in the validation process. Meanwhile, CNN-Canny got 90.5% accuracy in the training process and 86.2% in the validation process. The results of the comparison of the performance of the two models which are mapped to the confusion matrix table on 16 data testing in the form of images of batik motifs that have never been studied by each model show that the CNN-Sobel model can work more optimally than the CNN-Canny model with an accuracy comparison percentage of 94%. compared to 76% in the process of identifying batik motifs.

Human like visual and auditory sensory devices became very popular in recent years through the work of deep learning models that incorporate aspects of brain processing such as edge and line detectors found in the visual cortex. However, very little work has been done on the human memory, and thus our aim is to model human long-term declarative episodic memory storage using deep learning methods. An innovative way of deep neural network was created on supervised feature learning dataset such as MNIST to achieve high accuracy as well as storing the models hidden layers for future extraction. Convolutional Neural Network (CNN) learning models with transfer learning models were trained to imitate the long-term declarative episodic memory storage of human. A Recurrent Neural Network (RNN) in the form of Long Short Term Memory (LSTM) model was assembled in layers and then trained and evaluated. A Variational Autoencoder was also used for training and evaluation to mimic the human memory model. Frameworks were constructed using TensorFlow for training and testing the deep learning models.

Diagnosing burns in humans has become critical, as early identification can save lives. The manual process of burn diagnosis is time-consuming and complex, even for experienced doctors. Machine learning (ML) and deep convolutional neural network (CNN) models have emerged as the standard for medical image diagnosis. The ML-based approach typically requires handcrafted features for training, which may result in suboptimal performance. Conversely, DL-based methods automatically extract features, but designing a robust model is challenging. Additionally, shallow DL methods lack long-range feature dependency, decreasing efficiency in various applications. We implemented several deep CNN models, ResNeXt, VGG16, and AlexNet, for human burn diagnosis. The results obtained from these models were found to be less reliable since shallow deep CNN models need improved attention modules to preserve the feature dependencies. Therefore, in the proposed study, the feature map is divided into several categories, and the channel dependencies between any two channel mappings within a given class are highlighted. A spatial attention map is built by considering the links between features and their locations. Our attention-based model BuRnGANeXt50 kernel and convolutional layers are also optimized for human burn diagnosis. The earlier study classified the burn based on depth of graft and non-graft. We first classified the burn based on the degree. Subsequently, it is classified into graft and non-graft. Furthermore, the proposed model performance is evaluated on Burns_BIP_US_database. The sensitivity of the BuRnGANeXt50 is 97.22% and 99.14%, respectively, for classifying burns based on degree and depth. This model may be used for quick screening of burn patients and can be executed in the cloud or on a local machine. The code of the proposed method can be accessed at https://github.com/dhirujis02/Journal.git for the sake of reproducibility.

EEG based multi-class seizure type classification using convolutional neural network and transfer learning

This study leveraged Convolutional Neural Network (CNN) models to estimate canopy height in Southeast Australian forests before and after the 2019–2020 bushfire event, using inputs from Sentinel-1, Sentinel-2, spectral indices, and terrain features and GEDI canopy height (rh99) as target variables. Our research consisted of three primary objectives: (1) an evaluation of GEDI rh99 canopy height in relation to an nDSM derived from airborne LiDAR, (2) the development of two CNN models for pre- and post-fire scenarios, and (3) utilizing the trained CNN models to generate pre- and post-fire canopy height maps and canopy height change maps across the continuous landscape. GEDI rh99 accuracy analysis revealed R 2 = 0.85, RMSE = 7.25 m and nRMSE = 0.23 for pre-fire GEDI and R 2 = 0.78, RMSE = 10.1 m and nRMSE = 0.3 for post-fire GEDI. The pre-fire CNN model achieved R 2 = 0.75, RMSE = 7.29 m and nRMSE = 0.22, and post-fire CNN model achieved R 2 = 0.62, RMSE = 11.67 m, and nRMSE = 0.34 when validated against nDSM. Bias analysis was conducted, revealing that GEDI rh99 underestimated nDSM across all canopy height ranges, and slope has no significant impact on GEDI accuracy. Notably, post-fire GEDI rh99 exhibited significant underestimation in high to extreme fire severity. The CNN models’ prediction displayed overestimation in short forests < 20 m and increasing underestimation in taller forests > 20 m and underestimation in high and extreme fire severity. Subsequent investigation indicated that canopy layer thinning in high fire severity conditions resulted in weak GEDI waveform signals and consequent bias. Additionally, the GEDI rh99 bias was propagated to the CNN models, together with insensitivity of spectral band values to canopy height in dense and burnt forests potentially contributed to models’ bias. Finally, we demonstrated CNN models’ ability to monitor forest recovery by generating canopy height maps spanning East Gippsland from 2019 to 2023.

The adoption of artificial intelligence in post-earthquake inspections and reconnaissance has received considerable attention in recent years, owing to its exponential increase in computation capabilities and inherent potential in addressing disadvantages associated with manual inspections. Herein, we present the effectiveness of automated deep learning in enhancing the assessment of damage caused by the 2017 Pohang earthquake. Six classical pre-trained convolutional neural network (CNN) models are implemented through transfer learning (TL) on a small dataset, comprising 1780 manually labeled images of structural damage. Feature extraction and fine-tuning TL methods are trained on the image datasets. The performances of various CNN models are compared on a testing image dataset. Results confirm that the MobileNet fine-tuned model offers the best performance. Therefore, the model is further developed as a web-based application for classifying earthquake damage. The severity of damage is quantified by assigning damage assessment values, derived using the CNN model and gradient-weighted class activation mapping. The web-based application can effectively and automatically classify structural damage resulting from earthquakes, rendering it suitable for decision making, such as in resource allocation, policy development, and emergency response.