Towards building robust DNN applications

Carbonate rocks are important archives of past ocean conditions as well as hosts of economic resources such as hydrocarbons, water, and minerals. Geologists typically perform compositional analysis of grain, matrix, cement and pore types in order to interpret depositional environments, diagenetic modification, and reservoir quality of carbonate strata. Such information can be obtained primarily from petrographic analysis, a task that is costly, labor-intensive, and requires in-depth knowledge of carbonate petrology and micropaleontology. Recent studies have leveraged machine learning-based image analysis, including Deep Convolutional Neural Networks (DCNN), to automate description, classification and interpretation of thin sections, subsurface core images and seismic facies, which would accelerate data acquisition and reproducibility for these tasks. In carbonate rocks, this approach has been applied primarily to recognize carbonate lithofacies, and no attempt has been made to individually identify and quantify various types of carbonate grains, matrix, and cement. In this study, the applicability and performance of DCNN-based object detection and image classification approaches are assessed with respect to carbonate compositional analysis. The training data comprised of more than 13,000 individually labelled objects from nearly 4000 carbonate petrographic images. The dataset is grouped into six and nine different classes for the image classification and object detection tasks, respectively. Even with a small and relatively imbalanced training set, the DCNN was able to achieve an F1 score of 92% for image classification and 84% mean precision for object detection by combining one-cycle policy, class weight, and label mixup-smoothing methods. This study highlights the inefficiency of image classification as an approach to replicating human description and classification of carbonate petrography. By contrast, DCNN-based object detection appears capable of approaching human speed and accuracy in the area of carbonate petrography because it is able to individually locate and identify different carbonate components with greater cost-efficiency, speed, and reproducibility than conventional (human) petrographic analysis.

In various machine learning tasks, including image classification, data augmentation is widely used to expand the training dataset and prevent overfitting. In traditional data augmentation techniques, images from training data are flipped, distorted, added with some noise, or cropped to create new samples from the original images. This paper presents an improved and more effective data augmentation technique for image classification tasks, called Flip-and-Hide (FnH). Our technique was validated on four well-known datasets, MNIST, FMNIST, CIFAR-10 and CIFAR-100. We found 0.03% and 0.12% improvements on FMNIST and CIFAR-10, respectively, compared to the conventional Hide-and-Seek (HaS) augmentation technique. Moreover, we demonstrated the superiority of the proposed FnH augmentation technique by performing some visualisations. Consequently, our technique is particularly useful for image classification tasks that require limited training data.

Wheat is a primary carbohydrate-rich food commodity in the world, and the health of the wheat plants influences its production. Farmers can face a challenge due to decreased productivity caused by infected plants. However, wheat farmers have used conventional methods to survey diseases; however, these methods are often ineffective and inefficient, taking a lot of time and labor. And for enhanced wheat production, new strategies must be employed. Deep learning, specifically computer vision-based techniques, has proven significant capability in tasks like image classification, segmentation, and object detection. Deep learning techniques such as You Only Look Once (YOLO) models are state-of-the-art neural network algorithms used for accurate object detection. this study presents a comparative evaluation of two state-of-the-art object detection models, YOLOv5 and YOLOv8, for disease detection. Data augmentation techniques such as image noise, rotation, and flipping were implemented to improve the model’s performance during the training phase. The model’s performance was evaluated using metrics such as precision, recall, F1-score, and mean Average Precision (mAP).. The results show that the YOLOv5 and YOLOV8 models achieved good performance. They were able to detect the healthy and disease in images, These findings demonstrate that while both models are highly effective, but YOLOv8 offers greater robustness and accuracy for real-time detection.

Convolutional neural network based methods have provided great success in image classification and object detection tasks. However object detection, unlike the image classification task, requires much more computational intensities and energy consumption. As a result, object detection methods are difficult to integrate into embedded systems with limited resources. In this article, we propose a real-time handgun detection application on the embedded system. This application was implemented with 2 different convolutional neural network based object detection algorithms, and accuracy and speed performances were compared.

Purpose This study aims to automate the visual inspection of piling sheets in water channel construction using artificial intelligence (AI). By employing image classification and object detection techniques, the research focuses on extracting and analysing geometric features to enhance the accuracy and efficiency of the inspection process. It also addresses key challenges associated with the unique characteristics of construction materials and the limited variability of available inspection datasets. Design/methodology/approach Convolutional neural networks (CNNs) with varying complexities are employed for image classification, across four and six classes, and for object detection of piling sheets in water channel environments. A dataset provided by Witteveen + Bos is preprocessed to generate training sets, and the CNN architectures are optimized for enhanced performance. The accuracy and efficiency of the proposed models are evaluated and compared against traditional manual inspection methods. Findings The AI-driven approach significantly reduces processing time, evaluating 40,000 images in just 11.9 h, compared to approximately one month using manual assessment. The 4-class classification model achieves an accuracy of 96%, while the 6-class model attains 72%. The object detection model produces a mean average precision (mAP) of 79%. These results meet the performance standards set by the Dutch company Witteveen + Bos, which demonstrate the effectiveness of AI in automating the inspection of piling sheets. Originality/value This study introduces a novel AI-based approach for assessing piling sheets, demonstrating substantial improvements over traditional inspection methods. It introduces a systematic evaluation of various CNN architectures and hyperparameters to optimize the models specifically for piling sheet inspection rather than relying on off-the-shelf solutions. The use of CNNs for both image classification and object detection adheres to relevant Dutch engineering standards. Notably, the reduction in processing time, from one month to around 12 h, represents a major advancement in the efficiency of civil engineering inspections.

Transfer learning is a popular deep learning technique that involves fine-tuning a pre-trained CNN model on a new dataset to improve accuracy and speed. This article examines the effectiveness of transfer learning techniques in image classification tasks using CNNs. The paper reviews recent studies on transfer learning techniques, including their use in medical image analysis applications such as COVID-19 detection and Alzheimer’s disease classification. The study discusses the ImageNet dataset as a benchmark for pretraining CNN models and proposes an optimized CNN model that uses various optimization techniques to improve performance and efficiency. The article also includes a comparison table of various image classification techniques, including CNN, RNN, SVM, RF, and optimized CNN, with the optimized CNN offering the best performance and computational efficiency. The study emphasizes the importance of selecting the appropriate technique for specific applications based on factors such as available hardware and desired tradeoff between training time and prediction time. Overall, transfer learning techniques are shown to be effective in image classification tasks, particularly when labeled data is limited.

Currently, deep learning (DL) algorithms perform best in image classification and object detection tasks. Consequently, they are frequently used to address most problems involving computer vision. In this sense, the pervasive presence of smartphones and IoT devices has created a need to make this artificial intelligence portable. Given that deep neural network (DNN) models consist of millions of parameters, emerging research efforts have focused on enabling offline DL execution on low-resource devices, such as within the TinyML paradigm. This study analyzes the state-of-the-art of DL embedded in smartphones to develop an app for children that can recognize 3D geometric shapes without needing an internet connection. Alongside a systematic literature review, we conduct experiments with several pre-trained and lightweight models, which were subsequently evaluated using parametric statistical tests. While DL on smartphones is an underexplored area, it is expected to evolve significantly. Among the classification models tested, DenseNet169 demonstrated the highest accuracy (81%), whereas the MobileNet variants were faster and closer to real-time performance (30 FPS). In detection tasks, the EfficientDet-Lite and YOLOv8 models were evaluated, with EfficientDet-Lite being less accurate but faster (50 ms) compared to YOLOv8 (4 seconds). Although the field of DL on smartphones still requires further development, current lightweight models and frameworks offer significant opportunities for practical application.

Deep learning models have revealed outstanding performance on image classification and object detection tasks. However, there is a crucial drop in performance when they are subject to learn new data incrementally in the absence of previous training data. They suffer from catastrophic forgetting—abrupt drop in performance. This phenomenon affects the implementation of artificial intelligence in practical scenarios. To overcome catastrophic forgetting, the previous method has either saved previous data in memory or generated the previous data. However, these methods are computationally complex and infeasible for real-time applications. In this article, we proposed the YOLOv3 as an object detection framework for incremental learning. A knowledge distillation loss is introduced for the prediction of previously learned knowledge without utilizing previous training data. Consequently, these predictions are updated while learning the current model. Experimental results on the Pascal VOC2007 indicate that the proposed method significantly improved the mean average precision up to 74% for two classes in comparison to the state-of-the-art methods.

Various visual explanation methods, such as CAM and Grad-CAM, have been proposed to visualize and interpret predictions made by CNNs. Recent efforts go beyond mere visual interpretability, aiming to enhance CNN performance through the utilization of these generated visual explanations. In this work, we propose MANet (Mixed Attention Network)—a network architecture that advances the stability of visual explanations through an adaptive feature refinement mechanism via a mixed attention module. Concurrently, the generated attention maps are harnessed to bolster network performance in image recognition tasks. Experimental findings underscore the efficacy of MANet, demonstrating improved visual stability and consistency. The proposed architecture not only surpasses baseline models in image classification and object detection tasks but also establishes a novel paradigm for synergizing visual interpretability and network performance enhancement.

This work introduces a new training and compression pipeline to build nested sparse convolutional neural networks (ConvNets), a class of dynamic ConvNets suited for inference tasks deployed on resource-constrained devices at the edge of the Internet of Things. A nested sparse ConvNet consists of a single ConvNet architecture, containing <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> sparse subnetworks with nested weights subsets, like a Matryoshka doll, and can trade accuracy for latency at runtime, using the model sparsity as a dynamic knob. To attain high accuracy at training time, we propose a gradient masking technique that optimally routes the learning signals across the nested weight subsets. To minimize the storage footprint and efficiently process the obtained models at inference time, we introduce a new sparse matrix compression format with dedicated compute kernels that fruitfully exploit the characteristic of the nested weights subsets. Tested on image classification and object detection tasks on an off-the-shelf ARM-M7 microcontroller unit (MCU), nested sparse ConvNets outperform variable-latency solutions naively built assembling single sparse models trained as stand-alone instances, achieving 1) comparable accuracy; 2) remarkable storage savings; and 3) high performance. Moreover, when compared to state-of-the-art dynamic strategies, such as dynamic pruning and layer width scaling, nested sparse ConvNets turn out to be Pareto optimal in the accuracy versus latency space.

Game effect sprite generation with minimal data via conditional GAN

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

The extensive utilization of drones has led to numerous scenarios that encompass both advantageous and perilous outcomes. By using deep learning techniques, this study aimed to reduce the dangerous effects of drone use through early detection of drones. The purpose of this study is the evaluation of deep learning approaches such as pre-trained YOLOv8 drone detection for security issues. This study focuses on the YOLOv8 model to achieve optimal performance in object detection tasks using a publicly available dataset collected by Mehdi Özel for a UAV competition that is sourced from GitHub. These images are labeled using Roboflow, and the model is trained on Google Colab. YOLOv8, known for its advanced architecture, was selected due to its suitability for real-time detection applications and its ability to process complex visual data. Hyperparameter tuning and data augmentation techniques were applied to maximize the performance of the model. Basic hyperparameters such as learning rate, batch size, and optimization settings were optimized through iterative experiments to provide the best performance. In addition to hyperparameter tuning, various data augmentation strategies were used to increase the robustness and generalization ability of the model. Techniques such as rotation, scaling, flipping, and color adjustments were applied to the dataset to simulate different conditions and variations. Among the augmentation techniques applied to the specific dataset in this study, rotation was found to deliver the highest performance. Blurring and cropping methods were observed to follow closely behind. The combination of optimized hyperparameters and strategic data augmentation allowed YOLOv8 to achieve high detection accuracy and reliable performance on the publicly available dataset. This method demonstrates the effectiveness of YOLOv8 in real-world scenarios, while also highlighting the importance of hyperparameter tuning and data augmentation in increasing model capabilities. To enhance model performance, dataset augmentation techniques including rotation and blurring are implemented. Following these steps, a significant precision value of 0.946, a notable recall value of 0.9605, and a considerable precision–recall curve value of 0.978 are achieved, surpassing many popular models such as Mask CNN, CNN, and YOLOv5.

Deep learning (DL) has been shown to obtain superior results for classification tasks in the field of remote sensing hyperspectral imaging. Superpixel-based techniques can be applied to DL, significantly decreasing training and prediction times, but the results are usually far from satisfactory due to overfitting. Data augmentation techniques alleviate the problem by synthetically generating new samples from an existing dataset in order to improve the generalization capabilities of the classification model. In this paper we propose a novel data augmentation framework in the context of superpixel-based DL called dual-window superpixel (DWS). With DWS, data augmentation is performed over patches centered on the superpixels obtained by the application of simple linear iterative clustering (SLIC) superpixel segmentation. DWS is based on dividing the input patches extracted from the superpixels into two regions and independently applying transformations over them. As a result, four different data augmentation techniques are proposed that can be applied to a superpixel-based CNN classification scheme. An extensive comparison in terms of classification accuracy with other data augmentation techniques from the literature using two datasets is also shown. One of the datasets consists of small hyperspectral small scenes commonly found in the literature. The other consists of large multispectral vegetation scenes of river basins. The experimental results show that the proposed approach increases the overall classification accuracy for the selected datasets. In particular, two of the data augmentation techniques introduced, namely, dual-flip and dual-rotate, obtained the best results.

Image classification experiments face several problems related to image specifications, size of samples, and classification accuracy. The image classification related issues motivated the researchers to use Reinforcement Learning (RL) with image classification experiments to enhance it. RL is a self-learning approach where machines can learn from experience. This paper aims to study the influence of RL on image classification trials. Besides, exploring the main issues in RL-based image classification. The authors reviewed and analyzed 15 papers related to applying RL techniques on image classification. Major studies used RL techniques to solve image classification issues, e.g., high dimensionality and misclassifications. Whereas other studies developed RL-based image modification methods used for processing images, such as rotating and cropping. This work concludes that the RL has a beneficial impact on solving classification issues and modifying images. However, some areas should be further considered, such as applying RL techniques in image classification in real-world automation projects.