Convolutional Neural Networks For Image Classification Research Articles

An Analysis of Convolutional Neutral Network for Image Classification

Abstract: Convolutional Neural Networks (CNNs) have emerged as a powerful tool for image classification tasks, owing to their ability to automatically learn hierarchical representations from raw pixel data. This paper presents a comprehensive analysis of CNNs for image classification, focusing on their architecture, training process, and performance evaluation metrics. The study investigates various CNN architectures, including AlexNet, GoogLeNet, and ResNet, highlighting their respective strengths and weaknesses in different scenarios. Moreover, the paper explores the impact of hyperparameters such as network depth, filter size, and pooling strategies on classification accuracy and computational efficiency. Furthermore, the training process of CNNs, encompassing data preprocessing, augmentation techniques, and optimization algorithms, is scrutinized to elucidate best practices for achieving optimal performance. Additionally, the paper discusses commonly used evaluation metrics such as accuracy, precision, recall, and F1-score, elucidating their interpretation and significance in assessing model performance. Through a systematic review of existing literature and experimental validation, this analysis aims to provide insights into the underlying mechanisms of CNNs for image classification tasks. Finally, the paper outlines future research directions, emphasizing the need for exploring novel architectures, optimizing hyperparameters, and enhancing interpretability and robustness of CNN models. Overall, this study contributes to a deeper understanding of CNNs for image classification and provides valuable guidance for practitioners and researchers in the field.

Development of a Method for Estimating the Angle of Lumbar Spine X-ray Images Using Deep Learning with Pseudo X-ray Images Generated from Computed Tomography

Background and Objectives: In lumbar spine radiography, the oblique view is frequently utilized to assess the presence of spondylolysis and the morphology of facet joints. It is crucial to instantly determine whether the oblique angle is appropriate for the evaluation and the necessity of retakes after imaging. This study investigates the feasibility of using a convolutional neural network (CNN) to estimate the angle of lumbar oblique images. Since there are no existing lumbar oblique images with known angles, we aimed to generate synthetic lumbar X-ray images at arbitrary angles from computed tomography (CT) images and to estimate the angles of these images using a trained CNN. Methods: Synthetic lumbar spine X-ray images were created from CT images of 174 individuals by rotating the lumbar spine from 0° to 60° in 5° increments. A line connecting the center of the spinal canal and the spinous process was used as the baseline to define the shooting angle of the synthetic X-ray images based on how much they were tilted from the baseline. These images were divided into five subsets and trained using ResNet50, a CNN for image classification, implementing 5-fold cross-validation. The models were trained for angle estimation regression and image classification into 13 classes at 5° increments from 0° to 60°. For model evaluation, mean squared error (MSE), root mean squared error (RMSE), and the correlation coefficient (r) were calculated for regression analysis, and the area under the curve (AUC) was calculated for classification. Results: In the regression analysis for angles from 0° to 60°, the MSE was 14.833 degree2, the RMSE was 3.820 degrees, and r was 0.981. The average AUC for the 13-class classification was 0.953. Conclusion: The CNN developed in this study was able to estimate the angle of an lumbar oblique image with high accuracy, suggesting its usefulness.

Deep learning with adaptive convolutions for classification of retinal diseases via optical coherence tomography

Optical coherence tomography (OCT) uses interferometry to capture high-resolution cross-sectional images of the retina to diagnose retinal diseases. Convolutional neural networks (CNNs) have become essential for developing efficient computer-aided diagnostic algorithms, but noisy images can hinder their performance. This study introduces an innovative image preprocessing strategy that involves a new method of representing images to reduce image noise and a new adaptive convolution layer. The adaptive convolution layer aims to replace traditional convolution layers for OCT image classification by relying on local’Feature Content’. The proposed image representation is based on Zeckendorf's theorem, which states that every positive integer may be split into a unique sum of distinct, non-adjacent Fibonacci numbers. The proposed approach enables the generation of two separate images, known as the ‘base’ and ‘fine,’ where the ‘base’ image is the denoised image. We assessed our methodology by evaluating against ten filters, comprising a Low-pass filter, Gaussian filter, Wiener filter, Wavelet filter, Guided filter, Lee filter, Frost filter, Kuan filter, Detail Preserving Anisotropic Diffusion (DPAD) filter, and Non-Local Means (NLM) filter. In our study, we found that the proposed filter produced the most favorable results in five of the six no-reference parameters (Blur Percent (BP), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Naturalness Image Quality Evaluator (NIQE), Wavelet Variance (WAVV), Wavelet Variance Radial (WAVR)) used to assess the effectiveness of the proposed image enhancement technique. The OCT dataset utilized in the study was compiled by the University of California San Diego. The proposed adaptive convolution layer and its accompanying activation function were tested using seven OCT image classification CNN architectures. The test architectures comprise OctNET, NT-CNN, AOCT-NET, M-CNN, LightOCT, RetiNet, and DeepOCT. Experiments were conducted to assess the impact of the new preprocessing algorithm and the placement of the adaptive convolution layer as a substitute for the conventional convolution layer. Implementing the proposed approaches resulted in accuracy improvements ranging from 0.44% to 2.44% across architectures. Our findings highlight the efficacy of the proposed indirect noise reduction technique and a texture-sensitive adaptive convolution layer.

Combining bag of visual words-based features with CNN in image classification

Abstract Although traditional image classification techniques are often used in authentic ways, they have several drawbacks, such as unsatisfactory results, poor classification accuracy, and a lack of flexibility. In this study, we introduce a combination of convolutional neural network (CNN) and support vector machine (SVM), along with a modified bag of visual words (BoVW)-based image classification model. BoVW uses scale-invariant feature transform (SIFT) and Oriented Fast and Rotated BRIEF (ORB) descriptors; as a consequence, the SIFT–ORB–BoVW model developed contains highly discriminating features, which enhance the performance of the classifier. To identify appropriate images and overcome challenges, we have also explored the possibility of utilizing a fuzzy Bag of Visual Words (BoVW) approach. This study also discusses using CNNs/SVM to improve the proposed feature extractor’s ability to learn more relevant visual vocabulary from the image. The proposed technique was compared with classic BoVW. The experimental results proved the significant enhancement of the proposed technique in terms of performance and accuracy over state-of-the-art models of BoVW.

Application of CNN in computer vision

Today's deep learning continues to be hot, and the application of machine learning can be seen in more and more fields. A neural network model called a Convolutional Neural Network (CNN) was created to imitate the structure of the human brain. It is a convolution operation that maps the relationship between input features and output features to a two-dimensional in the vector space of , the network can effectively process the input data. CNN emerged to solve the computational bottleneck problem faced by traditional networks. This paper discusses the application of the deep learning model CNN in image classification, target detection and face recognition. In these fields, models are continuously proposed, and architectures in each field are constantly emerging. Among them will be the classic architecture of CNN in this field. These classic architectures have their advantages, but there will also be improvements brought about by the shortcomings of the classic architecture. Through the application of these different fields, we can see that CNN-based deep learning can help various fields, and the efficiency will be improved, but it is not perfect and needs continuous improvement.

Automatic detection of Opisthorchis viverrini egg in stool examination using convolutional-based neural networks.

Human opisthorchiasis is a dangerous infectious chronic disease distributed in many Asian areas in the water-basins of large rivers, Siberia, and Europe. The gold standard for human opisthorchiasis laboratory diagnosis is the routine examination of Opisthorchis spp. eggs under a microscope. Manual detection is laborious, time-consuming, and dependent on the microscopist's abilities and expertise. Automatic screening of Opisthorchis spp. eggs with deep learning techniques is a useful diagnostic aid. Herein, we propose a convolutional neural network (CNN) for classifying and automatically detecting O. viverrini eggs from digitized images. The image data acquisition was acquired from infected human feces and was processed using the gold standard formalin ethyl acetate concentration technique, and then captured under the microscope digital camera at 400x. Microscopic images containing artifacts and O.viverrini egg were augmented using image rotation, filtering, noising, and sharpening techniques. This augmentation increased the image dataset from 1 time to 36 times in preparation for the training and validation step. Furthermore, the overall dataset was subdivided into a training-validation and test set at an 80:20 ratio, trained with a five-fold cross-validation to test model stability. For model training, we customized a CNN for image classification. An object detection method was proposed using a patch search algorithm to detect eggs and their locations. A performance matrix was used to evaluate model efficiency after training and IoU analysis for object detection. The proposed model, initially trained on non-augmented data of artifacts (class 0) and O. viverrini eggs (class 1), showed limited performance with 50.0% accuracy, 25.0% precision, 50.0% recall, and a 33.0% F1-score. After implementing data augmentation, the model significantly improved, reaching 100% accuracy, precision, recall, and F1-score. Stability assessments using 5-fold cross-validation indicated better stability with augmented data, evidenced by an ROC-AUC metric improvement from 0.5 to 1.00. Compared to other models such as ResNet50, InceptionV3, VGG16, DenseNet121, and Xception, the proposed model, with a smaller file size of 2.7 MB, showed comparable perfect performance. In object detection, the augmented data-trained model achieved an IoU score over 0.5 in 139 out of 148 images, with an average IoU of 0.6947. This study demonstrated the successful application of CNN in classifying and automating the detection of O. viverrini eggs in human stool samples. Our CNN model's performance metrics and true positive detection rates were outstanding. This innovative application of deep learning can automate and improve diagnostic precision, speed, and efficiency, particularly in regions where O. viverrini infections are prevalent, thereby possibly improving infection sustainable control and treatment program.

Improved Image Classification Task Using Enhanced Visual Geometry Group of Convolution Neural Networks

Convolutional Neural Networks (CNNs) have become essential to solving image classification tasks. One of the most frequent models of CNNs for image classification is the Visual Geometry Group (VGG). The VGG architecture is made up of multiple layers of convolution and pooling processes followed by fully connected layers. Among the various VGG models, the VGG16 architecture has gained great attention due to its remarkable performance and simplicity. However, the VGG16 architecture is still prone to have many parameters contributing to its complexity. Moreover, the complexity of VGG16 may cause a longer execution time. The complexity of VGG16 architecture is also more highly prone to overfitting and may affect the classification accuracy. This study proposes an enhancement of VGG16 architecture to overcome such drawbacks. The enhancement involved the reduction of the convolution blocks, implementing batch normalization (B.N.) layers, and integrating global average pooling (GAP) layers with the addition of dense and dropout layers in the architecture. The experiment was carried out with six benchmark datasets for image classification tasks. The results from the experiment show that the network parameters are 79% less complex than the standard VGG16. The proposed model also yields better classification accuracy and shorter execution time. Reducing the parameters in the proposed improved VGG architecture allows for more efficient computation and memory usage. Overall, the proposed improved VGG architecture offers a promising solution to the challenges of long execution times and excessive memory usage in VGG16 architecture.

Comparison between vision transformers and convolutional neural networks to predict non-small lung cancer recurrence

Non-Small cell lung cancer (NSCLC) is one of the most dangerous cancers, with 85% of all new lung cancer diagnoses and a 30–55% of recurrence rate after surgery. Thus, an accurate prediction of recurrence risk in NSCLC patients during diagnosis could be essential to drive targeted therapies preventing either overtreatment or undertreatment of cancer patients. The radiomic analysis of CT images has already shown great potential in solving this task; specifically, Convolutional Neural Networks (CNNs) have already been proposed providing good performances. Recently, Vision Transformers (ViTs) have been introduced, reaching comparable and even better performances than traditional CNNs in image classification. The aim of the proposed paper was to compare the performances of different state-of-the-art deep learning algorithms to predict cancer recurrence in NSCLC patients. In this work, using a public database of 144 patients, we implemented a transfer learning approach, involving different Transformers architectures like pre-trained ViTs, pre-trained Pyramid Vision Transformers, and pre-trained Swin Transformers to predict the recurrence of NSCLC patients from CT images, comparing their performances with state-of-the-art CNNs. Although, the best performances in this study are reached via CNNs with AUC, Accuracy, Sensitivity, Specificity, and Precision equal to 0.91, 0.89, 0.85, 0.90, and 0.78, respectively, Transformer architectures reach comparable ones with AUC, Accuracy, Sensitivity, Specificity, and Precision equal to 0.90, 0.86, 0.81, 0.89, and 0.75, respectively. Based on our preliminary experimental results, it appears that Transformers architectures do not add improvements in terms of predictive performance to the addressed problem.

Deep Learning for Earthquake Disaster Assessment: Objects, Data, Models, Stages, Challenges, and Opportunities

Earthquake Disaster Assessment (EDA) plays a critical role in earthquake disaster prevention, evacuation, and rescue efforts. Deep learning (DL), which boasts advantages in image processing, signal recognition, and object detection, has facilitated scientific research in EDA. This paper analyses 204 articles through a systematic literature review to investigate the status quo, development, and challenges of DL for EDA. The paper first examines the distribution characteristics and trends of the two categories of EDA assessment objects, including earthquakes and secondary disasters as disaster objects, buildings, infrastructure, and areas as physical objects. Next, this study analyses the application distribution, advantages, and disadvantages of the three types of data (remote sensing data, seismic data, and social media data) mainly involved in these studies. Furthermore, the review identifies the characteristics and application of six commonly used DL models in EDA, including convolutional neural network (CNN), multi-layer perceptron (MLP), recurrent neural network (RNN), generative adversarial network (GAN), transfer learning (TL), and hybrid models. The paper also systematically details the application of DL for EDA at different times (i.e., pre-earthquake stage, during-earthquake stage, post-earthquake stage, and multi-stage). We find that the most extensive research in this field involves using CNNs for image classification to detect and assess building damage resulting from earthquakes. Finally, the paper discusses challenges related to training data and DL models, and identifies opportunities in new data sources, multimodal DL, and new concepts. This review provides valuable references for scholars and practitioners in related fields.

Automatic Classification of Desmids using Transfer Learning

This research paper presents a novel approach to classifying microscopic images of desmids using transfer learning and convolutional neural networks (CNNs). The purpose of this study was to automate the tedious task of manually classifying microscopic algae and improve our understanding of water quality in aquatic ecosystems. To accomplish this, we utilized transfer learning to fine-tune 13 pre-trained CNN models on a dataset of five categories of desmids. We evaluated the performance of our models using several metrics, including accuracy, precision, recall, and F1-score. Our results show that transfer learning can significantly improve the classification accuracy of microscopic images of desmids, and efficient CNN models can further enhance performance. The practical implications of this research include a more efficient and accurate method for classifying microscopic algae and assessing water quality. The theoretical implications include a better understanding of the application of transfer learning and CNNs in image classification. This research contributes to both theory and practice by providing a new method for automating the classification of microscopic algae and improving our understanding of aquatic ecosystems

A FUSION OF HAND-CRAFTED FEATURES AND DEEP NEURAL NETWORK FOR INDOOR SCENE CLASSIFICATION

Convolutional neural networks (CNN) have proved to be the best choice left for image classification tasks. However, hand-crafted features cannot be ignored as these are the basic to conventional image processing. Hand-crafted features provide a priori information that often acts as the contemporary solution to CNN in image classification, and hence an attempt is made to fuse the two. This paper gives a feature fusion approach to combine CNN and hand-crafted features. The proposed methodology uses two stages, where the first stage comprises feature encoder that encodes non-normalized features of CNN, which utilizes edge, texture, and local features. The fusion of handcrafted features with CNN features is carried out in the second Hand-crafted crafted features are validated that helped CNN to perform better. Experimental results reveal that the proposed methodology improves over the original Efficient-Net(E) on the MIT-67 dataset and achieved an average accuracy of 93.87%. The results are compared with state-of-the-art methods.

A Review on Quality Scanner Device for Radish and Carrot using Image Processing Technique

Abstract: Agriculture is the backbone of the Indian economy and productivity. The market value obtained from them is immense and effect both the export and quality valuation . Although grading and quality can be analysed by humans it is still inaccurate, time intensive, unreliable, subjective, and also hard which can be easily influenced by surrounding. Hence, there is an ultimate need for intelligent classification for vegetables. This paper focuses on Developing an analysis device for Radish (Raphanus raphanistrum ) and Carrot (Daucus carota subsp. sativus) which is an edible root vegetable grown in most parts of India. Radish and carrots are good sources of natural nitrates, minerals, calcium, and potassium. Thus, vegetables must be used as soon as possible to get a superior fresh character from them. External parameters such as size, shape, and quality factors of radish are important for finding out the total quality that is acceptable to the people. Various methods and algorithms are been put forwarded for the quality evaluation for the external defects present in it. Convolutional Neural Networks is the method used in image processing as this is more advantageous since it can learn special characteristics from images and by establish CNN for image classification where analyst have to gather the dataset. The requirement for doing this project is to have a computer and a python program for use the driver code. Image processing method is used for estimating quality of the particular food product efficiently in these days. This review paper examines current developments in methods for assessing food quality through image processing. The use of CNN (Convolutional Neural Networks) to identify characteristics of vegetables and its diseases through several built-in python libraries

OM-NAS: pigmented skin lesion image classification based on a neural architecture search.

Because pigmented skin lesion image classification based on manually designed convolutional neural networks (CNNs) requires abundant experience in neural network design and considerable parameter tuning, we proposed the macro operation mutation-based neural architecture search (OM-NAS) approach in order to automatically build a CNN for image classification of pigmented skin lesions. We first used an improved search space that was oriented toward cells and contained micro and macro operations. The macro operations include InceptionV1, Fire and other well-designed neural network modules. During the search process, an evolutionary algorithm based on macro operation mutation was employed to iteratively change the operation type and connection mode of parent cells so that the macro operation was inserted into the child cell similar to the injection of virus into host DNA. Ultimately, the searched best cells were stacked to build a CNN for the image classification of pigmented skin lesions, which was then assessed on the HAM10000 and ISIC2017 datasets. The test results showed that the CNN built with this approach was more accurate than or almost as accurate as state-of-the-art (SOTA) approaches such as AmoebaNet, InceptionV3 + Attention and ARL-CNN in terms of image classification. The average sensitivity of this method on the HAM10000 and ISIC2017 datasets was 72.4% and 58.5%, respectively.

PatchResNet: Multiple Patch Division-Based Deep Feature Fusion Framework for Brain Tumor Classification Using MRI Images.

Modern computer vision algorithms are based on convolutional neural networks (CNNs), and both end-to-end learning and transfer learning modes have been used with CNN for image classification. Thus, automated brain tumor classification models have been proposed by deploying CNNs to help medical professionals. Our primary objective is to increase the classification performance using CNN. Therefore, a patch-based deep feature engineering model has been proposed in this work. Nowadays, patch division techniques have been used to attain high classification performance, and variable-sized patches have achieved good results. In this work, we have used three types of patches of different sizes (32 × 32, 56 × 56, 112 × 112). Six feature vectors have been obtained using these patches and two layers of the pretrained ResNet50 (global average pooling and fully connected layers). In the feature selection phase, three selectors-neighborhood component analysis (NCA), Chi2, and ReliefF-have been used, and 18 final feature vectors have been obtained. By deploying k nearest neighbors (kNN), 18 results have been calculated. Iterative hard majority voting (IHMV) has been applied to compute the general classification accuracy of this framework. This model uses different patches, feature extractors (two layers of the ResNet50 have been utilized as feature extractors), and selectors, making this a framework that we have named PatchResNet. A public brain image dataset containing four classes (glioblastoma multiforme (GBM), meningioma, pituitary tumor, healthy) has been used to develop the proposed PatchResNet model. Our proposed PatchResNet attained 98.10% classification accuracy using the public brain tumor image dataset. The developed PatchResNet model obtained high classification accuracy and has the advantage of being a self-organized framework. Therefore, the proposed method can choose the best result validation prediction vectors and achieve high image classification performance.

NextDet: Efficient Sparse-to-Dense Object Detection with Attentive Feature Aggregation

Object detection is a computer vision task of detecting instances of objects of a certain class, identifying types of objects, determining its location, and accurately labelling them in an input image or a video. The scope of the work presented within this paper proposes a modern object detection network called NextDet to efficiently detect objects of multiple classes which utilizes CondenseNeXt, an award-winning lightweight image classification convolutional neural network algorithm with reduced number of FLOPs and parameters as the backbone, to efficiently extract and aggregate image features at different granularities in addition to other novel and modified strategies such as attentive feature aggregation in the head, to perform object detection and draw bounding boxes around the detected objects. Extensive experiments and ablation tests, as outlined in this paper, are performed on Argoverse-HD and COCO datasets, which provide numerous temporarily sparse to dense annotated images, demonstrate that the proposed object detection algorithm with CondenseNeXt as the backbone result in an increase in mean Average Precision (mAP) performance and interpretability on Argoverse-HD’s monocular ego-vehicle camera captured scenarios by up to 17.39% as well as COCO’s large set of images of everyday scenes of real-world common objects by up to 14.62%.

Drought stress impact on the performance of deep convolutional neural networks for weed detection in Bahiagrass

AbstractMachine vision‐based weed detection relies on features such as plant colour, leaf texture, shape, and patterns. Drought stress in plants can alter leaf colour and morphological features, which may in turn affect the reliability of machine vision‐based weed detection. The objective of this research was to evaluate the feasibility of using deep convolutional neural networks for the detection of Florida pusley (Richardia scabra L.) growing in drought stressed and unstressed bahiagrass (Paspalum natatum Flugge). The object detection neural networks you only look once (YOLO)v3, faster region‐based convolutional network (Faster R‐CNN), and variable filter net (VFNet) failed to effectively detect Florida pusley growing in drought stressed or unstressed bahiagrass, with F1 scores ≤0.54 in the testing dataset. Nevertheless, the use of the image classification neural networks AlexNet, GoogLeNet, and Visual Geometry Group‐Network (VGGNet) was highly effective and achieved high (≥0.97) F1 scores and recall values (≥0.98) in detecting images containing Florida pusley growing in drought stressed or unstressed bahiagrass. Overall, these results demonstrated the effectiveness of using an image classification convolutional neural network for detecting Florida pusley in drought stressed or unstressed bahiagrass. These findings illustrate the broad applicability of these neural networks for weed detection.

Quantized convolutional neural networks through the lens of partial differential equations

Quantization of convolutional neural networks (CNNs) is a common approach to ease the computational burden involved in the deployment of CNNs, especially on low-resource edge devices. However, fixed-point arithmetic is not natural to the type of computations involved in neural networks. In this work, we explore ways to improve quantized CNNs using PDE-based perspective and analysis. First, we harness the total variation (TV) approach to apply edge-aware smoothing to the feature maps throughout the network. This aims to reduce outliers in the distribution of values and promote piecewise constant maps, which are more suitable for quantization. Secondly, we consider symmetric and stable variants of common CNNs for image classification and graph convolutional networks for graph node classification. We demonstrate through several experiments that the property of forward stability preserves the action of a network under different quantization rates. As a result, stable quantized networks behave similarly to their non-quantized counterparts even though they rely on fewer parameters. We also find that at times, stability even aids in improving accuracy. These properties are of particular interest for sensitive, resource-constrained, low-power or real-time applications like autonomous driving.

Compressive Domain Deep CNN for Image Classification and Performance Improvement Using Genetic Algorithm-Based Sensing Mask Learning

The majority of digital images are stored in compressed form. Generally, image classification using convolution neural network (CNN) is done in uncompressed form rather than compressed one. Training the CNN in the compressed domain eliminates the requirement for decompression process and results in improved efficiency, minimal storage, and lesser cost. Compressive sensing (CS) is one of the effective and efficient method for signal acquisition and recovery and CNN training on CS measurements makes the entire process compact. The most popular sensing phenomenon used in CS is based on image acquisition using single pixel camera (SPC) which has complex design implementation and usually a matrix simulation is used to represent the SPC process in numerical demonstration. The CS measurements using this phenomenon are visually different from the image and to add this in the training set of the compressed learning framework, there is a need for an inverse SPC process that is to be applied all through the training and testing dataset image samples. In this paper we proposed a simple sensing phenomenon which can be implemented using the image output of a standard digital camera by retaining few pixels and forcing the rest of the pixels to zero and this reduced set of pixels is assumed as CS measurements. This process is modeled by a binary mask application on the image and the resultant image still subjectively legible for human vision and can be used directly in the training dataset. This sensing mask has very few active pixels at arbitrary locations and there is a lot of scope to heuristically learn the sensing mask suitable for the dataset. Only very few attempts had been made to learn the sensing matrix and the sole effect of this learning process on the improvement of CNN model accuracy is not reported. We proposed to have an ablation approach to study how this sensing matrix learning improves the accuracy of the basic CNN architecture. We applied CS for two class image dataset by applying a Primitive Walsh Hadamard (PWH) binary mask function and performed the classification experiment using a basic CNN. By retaining arbitrary amount of pixel in the training and testing dataset we applied CNN on the compressed measurements to perform image classification and studied and reported the model performance in terms of training and validation accuracies by varying the amount of pixels retained. A novel Genetic Algorithm-based compressive learning (GACL) method is proposed to learn the PWH mask to optimize the model training accuracy by using two different crossover techniques. In the experiment conducted for the case of compression ratio (CR) 90% by retaining only 10% of the pixels in every images both in training and testing dataset that represent two classes, the training accuracy is improved from 67% to 85% by using diagonal crossover in offspring creation of GACL. The robustness of the method is examined by applying GACL for user defined multiclass dataset and achieved better CNN model accuracies. This work will bring out the strength of sensing matrix learning which can be integrated with advanced training models to minimize the amount of information that is to be sent to central servers and will be suitable for a typical IoT frame work.

Thai digit handwriting image classification with convolutional neural networks

This paper aims to determine the efficiency in classifying and recognizing Thai digit handwritten using convolutional neural networks (CNN). We created a new dataset called the Thai digit dataset. The performance test was divided into two parts: the first part determines the exact number of epochs, and the second part examines the occurrence of overfits in the model with Keras library's EarlyStoping() function, processed through Cloud Computing with Google Colaboratory, and used a Python programming language. The main parameters for the model were a dropout of 0.75, mini-batch size of 128, the learning rate of 0.0001, and using an Adam optimizer. This study found the model's predictive accuracy was 96.88 and the loss was 0.1075. The results showed that using CNN in image classification and recognition. It has a high level of prediction efficiency. However, the parameters in the model must be adjusted accordingly.

An image classification deep-learning algorithm for shrapnel detection from ultrasound images

Ultrasound imaging is essential for non-invasively diagnosing injuries where advanced diagnostics may not be possible. However, image interpretation remains a challenge as proper expertise may not be available. In response, artificial intelligence algorithms are being investigated to automate image analysis and diagnosis. Here, we highlight an image classification convolutional neural network for detecting shrapnel in ultrasound images. As an initial application, different shrapnel types and sizes were embedded first in a tissue mimicking phantom and then in swine thigh tissue. The algorithm architecture was optimized stepwise by minimizing validation loss and maximizing F1 score. The final algorithm design trained on tissue phantom image sets had an F1 score of 0.95 and an area under the ROC curve of 0.95. It maintained higher than a 90% accuracy for each of 8 shrapnel types. When trained only on swine image sets, the optimized algorithm format had even higher metrics: F1 and area under the ROC curve of 0.99. Overall, the algorithm developed resulted in strong classification accuracy for both the tissue phantom and animal tissue. This framework can be applied to other trauma relevant imaging applications such as internal bleeding to further simplify trauma medicine when resources and image interpretation are scarce.