Search

For deep model training, an optimization technique is required that minimizes loss and maximizes accuracy. The development of an effective optimization method is one of the most important study areas. The diffGrad optimization method uses gradient changes during optimization phases but does not update 2nd order moments based on 1st order moments, and the AngularGrad optimization method uses the angular value of the gradient, which necessitates additional calculation. Due to these factors, both of those approaches result in zigzag trajectories that take a long time and require additional calculations to attain a global minimum. To overcome those limitations, a novel adaptive deep learning optimization method based on square of first momentum (sqFm) has been proposed. By adjusting 2nd order moments depending on 1st order moments and changing step size according to the present gradient on the non-negative function, the suggested sqFm delivers a smoother trajectory and better image classification accuracy. The empirical research comparing the performance of the proposed sqFm with Adam, diffGrad, and AngularGrad applying non-convex functions demonstrates that the suggested method delivers the best convergence and parameter values. In comparison to SGD, Adam, diffGrad, RAdam, and AngularGrad(tan) using the Rosenbrock function, the proposed sqFm method can attain the global minima gradually with less overshoot. Additionally, it is demonstrated that the proposed sqFm gives consistently good classification accuracy when training CNN networks (ResNet16, ResNet50, VGG34, ResNet18, and DenseNet121) on the CIFAR10, CIFAR100, and MNIST datasets, in contrast to SGDM, diffGrad, Adam, AngularGrad(Cos), and AngularGrad(Tan). The proposed method also gives the best classification accuracy than SGD, Adam, AdaBelief, Yogi, RAdam, and AngularGrad using the ImageNet dataset on the ResNet18 network. Source code link: https://github.com/UtpalNandi/sqFm-A-novel-adaptive-optimization-scheme-for-deep-learning-model. [ABSTRACT FROM AUTHOR]

Pneumonia is a serious disease that can be fatal, particularly among children and the elderly. The accuracy of pneumonia diagnosis can be improved by combining artificial-intelligence technology with X-ray imaging. This study proposes X-ODFCANet, which addresses the issues of low accuracy and excessive parameters in existing deep-learning-based pneumonia-classification methods. This network incorporates a feature coordination attention module and an omni-dimensional dynamic convolution (ODConv) module, leveraging the residual module for feature extraction from X-ray images. The feature coordination attention module utilizes two one-dimensional feature encoding processes to aggregate feature information from different spatial directions. Additionally, the ODConv module extracts and fuses feature information in four dimensions: the spatial dimension of the convolution kernel, input and output channel quantities, and convolution kernel quantity. The experimental results demonstrate that the proposed method can effectively improve the accuracy of pneumonia classification, which is 3.77% higher than that of ResNet18. The model parameters are 4.45M, which was reduced by approximately 2.5 times. The code is available at https://github.com/limuni/X-ODFCANET. [ABSTRACT FROM AUTHOR]

As the scale of water conservancy projects continues to expand, the amount and complexity of analytical data have also correspondingly increased. At present, it is difficult to realize project management decision support based on a single data source, and most manual analysis methods not only have high labor costs, but also are prone to the risk of misjudgment, resulting in huge property losses. Based on this problem, this paper proposes visual analysis method for unmanned pumping stations on dynamic platforms based on data fusion technology. First, the method uses the transfer learning method to enable ResNet18 obtain generalization ability. Secondly, the method uses ResNet18 to extract image features, and outputs fixed length sequence data as the input of long short-term memory (LSTM). Finally, the method uses LSTM outputs the classification results. The experimental results demonstrate that the algorithm model can achieve an impressive accuracy of 99.032%, outperforming the combination of traditional feature extraction and machine learning methods. This model effectively recognizes and classifies images of pumping stations, significantly reducing the risk of accidents in these facilities. [ABSTRACT FROM AUTHOR]

This study aims to discriminate between leucine-rich glioma-inactivated 1 (LGI1) antibody encephalitis and gamma-aminobutyric acid B (GABAB) receptor antibody encephalitis using a convolutional neural network (CNN) model. A total of 81 patients were recruited for this study. ResNet18, VGG16, and ResNet50 were trained and tested separately using 3828 positron emission tomography image slices that contained the medial temporal lobe (MTL) or basal ganglia (BG). Leave-one-out cross-validation at the patient level was used to evaluate the CNN models. The receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) were generated to evaluate the CNN models. Based on the prediction results at slice level, a decision strategy was employed to evaluate the CNN models' performance at patient level. The ResNet18 model achieved the best performance at the slice (AUC = 0.86, accuracy = 80.28%) and patient levels (AUC = 0.98, accuracy = 96.30%). Specifically, at the slice level, 73.28% (1445/1972) of image slices with GABAB receptor antibody encephalitis and 87.72% (1628/1856) of image slices with LGI1 antibody encephalitis were accurately detected. At the patient level, 94.12% (16/17) of patients with GABAB receptor antibody encephalitis and 96.88% (62/64) of patients with LGI1 antibody encephalitis were accurately detected. Heatmaps of the image slices extracted using gradient-weighted class activation mapping indicated that the model focused on the MTL and BG for classification. In general, the ResNet18 model is a potential approach for discriminating between LGI1 and GABAB receptor antibody encephalitis. Metabolism in the MTL and BG is important for discriminating between these two encephalitis subtypes. [ABSTRACT FROM AUTHOR]

Most of the wheat produced and consumed worldwide is generally bread wheat and is used for bread making. Bread wheat varieties can affect the quality of bread. When comparing bread wheat to other varieties, there may be differences in taste, cost, and impact on human health. This study aims to classify bread wheat varieties using deep learning methods. Wheat cultivars used in this research ('Ayten Abla', 'Bayraktar 2000', 'Hamitbey', 'Şanlı', and 'Tosunbey') were obtained from the Central Field Crop Research Institute, Ministry of Agriculture and Forestry, Republic of Türkiye. First, a dataset of 8354 images of these wheat varieties was created. Then, the images in this dataset were trained with tree different Convolutional Neural Networks (CNNs) using the transfer learning method. The CNN models used are Inception-V3, Mobilenet-V2, and Resnet18, and the classification accuracies obtained are 97.37%, 97.07%, and 97.67%, respectively. Finally, the images not used for training and validation of the CNN models were segmented using image processing techniques. The segmented images were classified as bread wheat and unidentified seeds in the Resnet18 CNN model. [ABSTRACT FROM AUTHOR]

Although the pits of cherries, which are often consumed as fruits, jams and fruit juices, are generally used as waste, these pits contain beneficial components such as oil, protein, crude fibers, vitamins, minerals, etc. In this context, the determination of pits according to cultivars is important in the food industry since pits with different cultivars contain different compositions. This study is aimed to classify sour cherry pits with different cultivars using modern deep learning-based methods. In this context, four sour cherry cultivars were harvested and the pits extracted from these cherries were used in the study. Cherry pits' images were acquired by bringing the pits of each cultivar together. In the next pre-processing step, each pit was cropped with the help of thresholding to handle each pit in the images separately. The next step was data augmentation, which provided data diversity and robust learning, to increase the cherry pit images. In the last step, cherry pits were classified using four different state-of-the-art convolutional neural network (CNN) models: GoogleNet, ResNet18, ResNet50, MobileNetv2. The obtained classification accuracies were 94.51%, 98.41%, 99.29% and 97.35%, respectively. [ABSTRACT FROM AUTHOR]

Road cracks are caused due to the abundant usage of the roads, heavy traffic, and increased prerequisite of transportation. So road maintenance is an important aspect of such a huge number of vehicles on the roads to have safety measures and continuity. Besides the traffic, bad weather is also contributing its part in creating road cracks. In the proposed research automatic road cracks have been detected, it looks simple apparently but the intensity, and complexity of the background make it a challenging task. In this challenging task, the contrast of the processed image, complexity of different kinds of crack recognition, assembly of proper database images, elapsed time, and approximate classification, etc., are processed to get the optimum results. Deep learning has multiple neural networks among them few networks are used like AlexNet, ResNet18, and SqueezeNet for the data recognition mainly for the huge database having the optimum results in minimum throughput. In the accomplished research 4333 images with eight diverse road cracks classes are used. The classified images are processed by utilizing three different networks through a supervised dataset. Dataset is built by mixing the university resources-collected images and some online datasets. The best expected result is gained after proper training and tested along with classification. In this experiment, the training and testing images were kept the same in epoch and iteration. But the ResNet18 was superlative with an accuracy of 85.20%. [ABSTRACT FROM AUTHOR]

Electric arc welding machines are widely used in industry in metal technology. In parallel with the advancement of technology for the development and automation of electric arc welding machines, it is necessary to conduct scientific studies on the determination of optimal operation cases and control for optimal welding process. In this study, operating zones were classified and determined according to the measured welding current graph during the 5-s operation of the MAG electric arc welding machine. Five deep convolutional neural networks were used for this purpose. Four of these deep learning methods are pre-trained models. We used the concept of "ransfer learning" to use pre-trained models. According to the results we obtained from five different models, we were able to estimate the operating range of the electric arc welding machine, with 93.5% accuracy with the designed model and 95−100% accuracy with pre-trained models. [ABSTRACT FROM AUTHOR]

Lung abnormality is one of the common diseases in humans of all age group and this disease may arise due to various reasons. Recently, the lung infection due to SARS-CoV-2 has affected a larger human community globally, and due to its rapidity, the World-Health-Organisation (WHO) declared it as pandemic disease. The COVID-19 disease has adverse effects on the respiratory system, and the infection severity can be detected using a chosen imaging modality. In the proposed research work; the COVID-19 is detected using transfer learning from CT scan images decomposed to three-level using stationary wavelet. A three-phase detection model is proposed to improve the detection accuracy and the procedures are as follows; Phase1- data augmentation using stationary wavelets, Phase2- COVID-19 detection using pre-trained CNN model and Phase3- abnormality localization in CT scan images. This work has considered the well known pre-trained architectures, such as ResNet18, ResNet50, ResNet101, and SqueezeNet for the experimental evaluation. In this work, 70% of images are considered to train the network and 30% images are considered to validate the network. The performance of the considered architectures is evaluated by computing the common performance measures. The result of the experimental evaluation confirms that the ResNet18 pre-trained transfer learning-based model offered better classification accuracy (training = 99.82%, validation = 97.32%, and testing = 99.4%) on the considered image dataset compared with the alternatives. [ABSTRACT FROM AUTHOR]