Model-Driven Integration of Deep Learning for Artifact Classification in Museum Information Systems

Recently, deep learning using convolutional neural network (CNN) has been used successfully to classify the images of breast cells accurately. However, the accuracy of manual classification of those histopathological images is comparatively low. This research aims to increase the accuracy of the classification of breast cancer images by utilizing a patch‐based classifier (PBC) along with deep learning architecture. The proposed system consists of a deep convolutional neural network that helps in enhancing and increasing the accuracy of the classification process. This is done by the use of the PBC. CNN has completely different layers where images are first fed through convolutional layers using hyperbolic tangent function together with the max‐pooling layer, drop out layers, and SoftMax function for classification. Further, the output obtained is fed to a PBC that consists of patch‐wise classification output followed by majority voting. The results are obtained throughout the classification stage for breast cancer images that are collected from breast‐histology datasets. The proposed solution improves the accuracy of classification whether or not the images had normal, benign, in‐situ, or invasive carcinoma from 87% to 94% with a decrease in processing time from 0.45 to 0.2 s on average. The proposed solution focused on increasing the accuracy of classifying cancer in the breast by enhancing the image contrast and reducing the vanishing gradient. Finally, this solution for the implementation of the contrast limited adaptive histogram equalization technique and modified tangent function helps in increasing the accuracy.

Deep learning has been successfully applied in classification of white blood cells (WBCs), however, accuracy and processing time are found to be less than optimal hindering it from getting its full potential. This is due to imbalanced dataset, intra-class compactness, inter-class separability and overfitting problems. The main research idea is to enhance the classification and prediction accuracy of blood images while lowering processing time through the use of deep convolutional neural network (DCNN) architecture by using the modified loss function. The proposed system consists of a deep neural convolution network (DCNN) that will improve the classification accuracy by using modified loss function along with regularization. Firstly, images are pre-processed and fed through DCNN that contains different layers with different activation function for the feature extraction and classification. Along with modified loss function with regularization, weight function aids in the classification of WBCs by considering weights of samples belonging to each class for compensating the error arising due to imbalanced dataset. The processing time will be counted by each image to check the time enhancement. The classification accuracy and processing time are achieved using the dataset-master. Our proposed solution obtains better classification performance in the given dataset comparing with other previous methods. The proposed system enhanced the classification accuracy of 98.92% from 96.1% and a decrease in processing time from 0.354 to 0.216 s. Less time will be required by our proposed solution for achieving the model convergence with 9 epochs against the current convergence time of 13.5 epochs on average, epoch is the formation white blood cells (WBCs) and the development of granular cells. The proposed solution modified loss function to solve the adverse effect caused due to imbalance dataset by considering weight and use regularization technique for overfitting problem.

Logistic regression (LR) is a popular method that is used for estimating causal effects in observational studies using propensity scores. We examine the use of deep learning models such as the deep neural network (DNN), PropensityNet (PN), convolutional neural network (CNN), and convolutional neural network-long short-term memory network (CNN-LSTM) to estimate propensity scores and evaluate causal inference. We conducted studies using simulated data with different sample sizes (N = 500, N = 1000, N = 2000), 15 covariates, a continuous outcome and a binary exposure. These data were used in seven scenarios that were different in the degree of nonlinearity and nonadditivity associations between the exposure and covariates. Estimation of propensity scores was considered a classification task and performance metrics that included classification accuracy, receiver operating characteristic curve area under the curve (AUCROC), covariate balance, standard error, absolute bias, and the 95% confidence interval coverage were evaluated for each model. Our simulation results show that deep learning models (CNN, DNN, and CNN-LSTM) outperformed LR in the estimation of the propensity score. CNN and CNN-LSTM achieved good results for covariate balance, classification accuracy, AUCROC, and Cohen’s Kappa. Although LR provided substantially better bias reduction, it produced subpar performance based on classification accuracy, AUCROC, Cohen’s Kappa, and 95% confidence interval coverage compared to the deep learning models. The results suggest that deep learning methods, especially CNN, may be useful for estimating propensity scores that are used to estimate causal effects.

Abstract. New particle formation (NPF) in the atmosphere is globally an important source of climate relevant aerosol particles. Occurrence of NPF events is typically analyzed by researchers manually from particle size distribution data day by day, which is time consuming and the classification of event types may be inconsistent. To get more reliable and consistent results, the NPF event analysis should be automatized. We have developed an automatic analysis method based on deep learning, a subarea of machine learning, for NPF event identification. To our knowledge, this is the first time that a deep learning method, i.e., transfer learning of a convolutional neural network (CNN), has successfully been used to automatically classify NPF events into different classes directly from particle size distribution images, similarly to how the researchers carry out the manual classification. The developed method is based on image analysis of particle size distributions using a pretrained deep CNN, named AlexNet, which was transfer learned to recognize NPF event classes (six different types). In transfer learning, a partial set of particle size distribution images was used in the training stage of the CNN and the rest of the images for testing the success of the training. The method was utilized for a 15-year-long dataset measured at San Pietro Capofiume (SPC) in Italy. We studied the performance of the training with different training and testing of image number ratios as well as with different regions of interest in the images. The results show that clear event (i.e., classes 1 and 2) and nonevent days can be identified with an accuracy of ca. 80 %, when the CNN classification is compared with that of an expert, which is a good first result for automatic NPF event analysis. In the event classification, the choice between different event classes is not an easy task even for trained researchers, and thus overlapping or confusion between different classes occurs. Hence, we cross-validated the learning results of CNN with the expert-made classification. The results show that the overlapping occurs, typically between the adjacent or similar type of classes, e.g., a manually classified Class 1 is categorized mainly into classes 1 and 2 by CNN, indicating that the manual and CNN classifications are very consistent for most of the days. The classification would be more consistent, by both human and CNN, if only two different classes are used for event days instead of three classes. Thus, we recommend that in the future analysis, event days should be categorized into classes of “quantifiable” (i.e., clear events, classes 1 and 2) and “nonquantifiable” (i.e., weak events, Class 3). This would better describe the difference of those classes: both formation and growth rates can be determined for quantifiable days but not both for nonquantifiable days. Furthermore, we investigated more deeply the days that are classified as clear events by experts and recognized as nonevents by the CNN and vice versa. Clear misclassifications seem to occur more commonly in manual analysis than in the CNN categorization, which is mostly due to the inconsistency in the human-made classification or errors in the booking of the event class. In general, the automatic CNN classifier has a better reliability and repeatability in NPF event classification than human-made classification and, thus, the transfer-learned pretrained CNNs are powerful tools to analyze long-term datasets. The developed NPF event classifier can be easily utilized to analyze any long-term datasets more accurately and consistently, which helps us to understand in detail aerosol–climate interactions and the long-term effects of climate change on NPF in the atmosphere. We encourage researchers to use the model in other sites. However, we suggest that the CNN should be transfer learned again for new site data with a minimum of ca. 150 figures per class to obtain good enough classification results, especially if the size distribution evolution differs from training data. In the future, we will utilize the method for data from other sites, develop it to analyze more parameters and evaluate how successfully CNN could be trained with synthetic NPF event data.

Community science image libraries offer a massive, but largely untapped, source of observational data for phenological research. The iNaturalist platform offers a particularly rich archive, containing more than 49 million verifiable, georeferenced, open access images, encompassing seven continents and over 278,000 species. A critical limitation preventing scientists from taking full advantage of this rich data source is labor. Each image must be manually inspected and categorized by phenophase, which is both time-intensive and costly. Consequently, researchers may only be able to use a subset of the total number of images available in the database. While iNaturalist has the potential to yield enough data for high-resolution and spatially extensive studies, it requires more efficient tools for phenological data extraction. A promising solution is automation of the image annotation process using deep learning. Recent innovations in deep learning have made these open-source tools accessible to a general research audience. However, it is unknown whether deep learning tools can accurately and efficiently annotate phenophases in community science images. Here, we train a convolutional neural network (CNN) to annotate images of Alliaria petiolata into distinct phenophases from iNaturalist and compare the performance of the model with non-expert human annotators. We demonstrate that researchers can successfully employ deep learning techniques to extract phenological information from community science images. A CNN classified two-stage phenology (flowering and non-flowering) with 95.9% accuracy and classified four-stage phenology (vegetative, budding, flowering, and fruiting) with 86.4% accuracy. The overall accuracy of the CNN did not differ from humans (p = 0.383), although performance varied across phenophases. We found that a primary challenge of using deep learning for image annotation was not related to the model itself, but instead in the quality of the community science images. Up to 4% of A. petiolata images in iNaturalist were taken from an improper distance, were physically manipulated, or were digitally altered, which limited both human and machine annotators in accurately classifying phenology. Thus, we provide a list of photography guidelines that could be included in community science platforms to inform community scientists in the best practices for creating images that facilitate phenological analysis.

3-D optimized classification and characterization artificial intelligence paradigm for cardiovascular/stroke risk stratification using carotid ultrasound-based delineated plaque: Atheromatic™ 2.0

Comprehensive Study for Breast Cancer Using Deep Learning and Traditional Machine Learning

Aim: Deep learning models, such as deep convolutional neural networks (CNNs), have undergone extensive scrutiny in the context of food classification because of their exceptional feature extraction capabilities. Background: Similarly, ensemble-based learning approaches have exhibited great potential for achieving effective supervised classification. Objective: We suggest an innovative approach to improve the effectiveness of deep learningbased food classification. Methods: Our proposal involves a novel deep learning ensemble framework that draws inspiration from the fusion of deep learning models with ensemble learning based on random subspaces. The random subspaces play a role in diversifying the ensemble system in a straightforward but impactful way. Moreover, to enhance the classification accuracy even more, we explore transfer learning, employing the migration of acquired weights from a single classifier to another (namely, CNNs). This approach expedites the process of learning. Results: Results from experiments conducted using well-established food datasets illustrate that the suggested deep learning ensemble system delivers competitive performance compared to state-of-the-art techniques, as evidenced by its classification accuracy. Conclusion: The amalgamation of deep learning and ensemble learning holds substantial promise for dependable food categorization.

BackgroundEpilepsy is one of the diseases of the nervous system, which has a large population in the world. Traditional diagnosis methods mostly depended on the professional neurologists’ reading of the electroencephalogram (EEG), which was time-consuming, inefficient, and subjective. In recent years, automatic epilepsy diagnosis of EEG by deep learning had attracted more and more attention. But the potential of deep neural networks in seizure detection had not been fully developed.MethodsIn this article, we used a one-dimensional convolutional neural network (1-D CNN) to replace the residual network architecture’s traditional convolutional neural network (CNN). Moreover, we combined the Independent recurrent neural network (indRNN) and CNN to form a new residual network architecture-independent convolutional recurrent neural network (RCNN). Our model can achieve an automatic diagnosis of epilepsy EEG. Firstly, the important features of EEG were learned by using the residual network architecture of 1-D CNN. Then the relationship between the sequences were learned by using the recurrent neural network. Finally, the model outputted the classification results.ResultsOn the small sample data sets of Bonn University, our method was superior to the baseline methods and achieved 100% classification accuracy, 100% classification specificity. For the noisy real-world data, our method also exhibited powerful performance.ConclusionThe model we proposed can quickly and accurately identify the different periods of EEG in an ideal condition and the real-world condition. The model can provide automatic detection capabilities for clinical epilepsy EEG detection. We hoped to provide a positive significance for the prediction of epileptic seizures EEG.

The primary task of museums is to preserve museum objects in the form of physical objects. Despite its apparent simplicity and comprehensibility, damage to man-made objects – artefacts – is a complex and complicated field. Damage processes are grouped as being physical, chemical, mechanical, and biological. In most cases, different processes work together, damaging the materials and structure of the artefacts. A number of factors, the most important of which are the composition and structure of materials, environmental conditions, and human impacts, affect damage processes. It is very difficult, and in most cases impossible, to take all these factors into account. At the same time, modelling the aging of museum objects is especially important for their successful preservation. Modelling of damage processes makes it possible to assess the extent of such processes (which objects have been damaged and what the degree of damage is), the speed of damage processes, and thereby changes in the number of damaged objects over time, and finally, the effectiveness of possible management measures.
 In this article, we discuss the machine learning model Sälli, which predicts the durability of museum objects. For this purpose, the machine learning model uses data from MuIS (Estonian Museum Information System). The condition of objects is assessed in MuIS with four values: ‘good’, ‘satisfactory’, ‘poor’, and ‘very poor’. Almost 3.7 million condition assessments have been entered into MuIS. The development of a condition prediction model based on these data requires at least pairs of consecutive condition assessments in order to attempt to determine what correlates with the change in condition, whether it be one or another event, or a property (nature, material, age, techniques) of a museum object, or some combination of such factors. There are more than 1.4 million such pairs among the museum objects with several condition assessments. Almost 32,000 of them, or a little over 2%, consist of two different condition assessments, i.e., they indicate a change in condition. According to the data entered in MuIS, almost 30,000 museum objects, i.e., less than one percent of all museum objects, have been subject to a change in condition.
 As data points, we used at least two condition assessments for each museum object, to which we added the characteristics of the respective museum object and other features that help to predict the deterioration of the condition of the museum object. These data included static data related to the museum object: museum, museum collection, nature, material, material group, technology, exhibitability, and dating. As additional information, we used the history of the museum object, i.e., a summary of the events related to the museum object, taking into account only the events that took place during the condition assessment (because we do not have information on the future). The model finds the probability that the condition of the museum object will deteriorate in the next n years. If the probability of deterioration is greater than or equal to a set threshold, the model responds with ‘deterioration’. In finding the optimal decision threshold, we used a 10-year forecast period, i.e., we trained the decision-makers to predict deterioration over the next 10 years.
 The best results were obtained using the decision forest algorithm, which was able to identify 92% of deteriorating museum objects with 50% accuracy. This model was also used to create the Sälli prototype. The task of the Kratt Sälli prototype is to draw the attention of museum staff to museum objects, the condition of which may deteriorate in the next 10 years and the situation of which should therefore be reviewed. For testing, a prototype of the 1,000 highest-risk museum objects from that museum was added to each test museum. To test the usefulness and usability of the machine learning model predictions, we created a simple web application that was tested in pilot museums. We found that the available data have the potential to predict deterioration, but the data still need to be improved and the model trained on them is not yet mature enough.

This paper proposes to enable deep learning for generic machine learning tasks. Our goal is to allow deep learning to be applied to data which are already represented in instancefeature tabular format for a better classification accuracy. Because deep learning relies on spatial/temporal correlation to learn new feature representation, our theme is to convert each instance of the original dataset into a synthetic matrix format to take the full advantage of the feature learning power of deep learning methods. To maximize the correlation of the matrix, we use 0/1 optimization to reorder features such that the ones with strong correlations are adjacent to each other. By using a two dimensional feature reordering, we are able to create a synthetic matrix, as an image, to represent each instance. Because the synthetic image preserves the original feature values and data correlation, existing deep learning algorithms, such as convolutional neural networks (CNN), can be applied to learn effective features for classification. Our experiments on 20 generic datasets, using CNN as the deep learning classifier, confirm that enabling deep learning to generic datasets has clear performance gain, compared to generic machine learning methods. In addition, the proposed method consistently outperforms simple baselines of using CNN for generic dataset. As a result, our research allows deep learning to be broadly applied to generic datasets for learning and classification (Algorithm source code is available at http://github.com/hhmzwc/EDLT).

Development of hybrid models based on deep learning and optimized machine learning algorithms for brain tumor Multi-Classification

Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Machine learning has been around for decades, but deep learning is the new focus of study within machine learning. The goals of implementing deep learning into remote sensing are resulting in much faster and more accurate results for much larger datasets. The field of remote sensing has focused on increasing the accuracy of land classification. A possible solution for increasing accuracy is the use of convolutional neural networks. The goals of this study were to determine whether convolutional neural networks can be used on moderate-resolution imagery to accurately classify land. The study site of focus was the Konza Prairie in Geary County, Kansas. The image data are from Landsat 4 and 5 spanning the years 1985-2011. The Konza was split into 4 x 4-pixel size fishnet of cells that were classified as either burnt or non-burnt. To better examine the convolutional neural network, it was compared to machine learning and other neural network models. The machine learning models explored were logistic regression, k-nearest neighbor, decision tree, and linear support vector machine. The neural networks implemented included the basic neural network, shallow neural network, flatten time window neural network, convolutional neural network, and deep convolutional neural network. The results show that the k-nearest neighbor produce the highest overall accuracy compared to all the machine learning and neural networks but consist of high errors of omission proving that the classification is not represented accurately. The deep convolutional neural network has the best results for classifying burnt and non-burnt cells and low errors of omission and commission, which best represents the classification.