Machine Deep Learning Methods Research Articles

Deep machine learning with Sentinel satellite data to map paddy rice production stages across West Java, Indonesia

Indonesia recently implemented a novel, technology-driven approach for conducting agricultural production surveys, which involves monthly observations at many thousands of strategic locations and automated data logging via a cellular phone application. Data from these comprehensive field surveys offer immense value for advancing remote sensing technology to map crop production across Indonesia, particularly through the development of machine learning approaches to relate survey data with satellite imagery. The objective of this study was to compare different machine learning scenarios for classifying and mapping the temporal progression of paddy rice production stages across West Java, Indonesia using synthetic aperture radar (SAR) and optical remote sensing data from Sentinel-1 and Sentinel-2 satellites. Monthly paddy rice survey data at 21,696 locations across West Java from November 2018 through April 2019 were used for model training and testing. Five classes related to rice production stage or other field conditions were defined, including rice at tillering, heading, and harvest stages, rice fields with little to no vegetation present, and non-rice areas. A recurrent neural network (RNN) with long short term memory (LSTM) nodes provided optimal performance with classification accuracies of 79.6% and 75.9% for model training and testing, respectively, and reduced computational effort. Other approaches that incorporated a convolutional neural network (CNN) either reduced classification accuracy or increased computational effort. Deep machine learning methods (RNN and CNN) generally outperformed other non-deep classifiers, which achieved up to 63.3% accuracy for model testing. Classification accuracies were optimized by inputting two Sentinel-1 channels (VH and VV polarizations) and ten Sentinel-2 channels. Temporal patterns of paddy rice production stages were consistent between the monthly ground-based agricultural survey data and 10-m, satellite-based rice classification maps obtained by applying the LSTM-based RNN across West Java. The results demonstrated the value of combining modern agricultural survey data, satellite remote sensing, and a recurrent neural network to develop multitemporal maps of paddy rice production stages.

The Role of Artificial Intelligence in Arrhythmia Monitoring.

Arrhythmia management has been revolutionized by the ability to monitor the cardiac rhythm in a patient's home environment in real-time using high-fidelity prescription-grade and commercially available wearable electrodes. The vast amount of digitally acquired electrophysiological signals has generated the need for scalable and efficient data processing with actionable output that can be provided directly to clinicians and patients. In this setting, artificial intelligence applications are increasingly important in arrhythmia monitoring, ranging from conventional algorithmic analysis for rhythm determination to more complex deep machine learning methods that have led to the realization of fully automated humanlike rhythm determination in real-time.

Retraction Note: A deep learning model and machine learning methods for the classification of potential coronavirus treatments on a single human cell.

[This retracts the article DOI: 10.1007/s11051-020-05041-z.].

심층학습 기법을 이용한 원핫 안구 질환 진단 프레임워크

Multiple OCT images from the same patient for ophthalmic disease classification, such as AMD, DME, and Drusen, often conflict with each other in classification. The human doctor makes an experience-based medical decision for inconsistent OCT images, but no neural-network-based approach has been proposed to solve the same problem so far. This paper presents a new machine-learning-based framework that makes the comprehensive one-hot decision on AMD, DME, and Drusen, just like human doctors. In this study, we present a two-step deep machine learning method: In the first step, a classical Deep CNN along with transfer learning is used to make an ophthalmic diagnosis for a single OCT image. In the second step, a new framework, we propose, consisting of several supervised deep machine learning methods makes a comprehensive one-hot decision on eye disease from multiple OCT images. In this framework, we developed an AI model that can make comprehensive judgments from inconsistent results obtained from the same patient. Consequently, we could achieve 94% classification accuracy compared to the human doctor classification.

Deep Learning-Based Multi-Class Classification of Breast Digital Pathology Images.

IntroductionBreast cancer, one of the most common health threats to females worldwide, has always been a crucial topic in the medical field. With the rapid development of digital pathology, many scholars have used AI-based systems to classify breast cancer pathological images. However, most existing studies only stayed on the binary classification of breast lesions (normal vs tumor or benign vs malignant), far from meeting the clinical demand. Therefore, we established a multi-class classification system of breast digital pathology images based on AI, which is more clinically practical than the binary classification system.MethodsIn this paper, we adopted a two-stage architecture based on deep learning method and machine learning method for the multi-class classification (normal tissue, benign lesion, ductal carcinoma in situ, and invasive carcinoma) of breast digital pathological images.ResultsThe proposed approach achieved an overall accuracy of 86.67% at patch-level. At WSI-level, the overall accuracies of our classification system were 88.16% on validation data and 90.43% on test data. Additionally, we used two public datasets, the BreakHis and BACH, for independent verification. The accuracies our model obtained on these two datasets were comparable to related publications. Furthermore, our model could achieve accuracies of 85.19% on multi-classification and 96.30% on binary classification (non-malignant vs malignant) using pathology images of frozen sections, which was proven to have good generalizability. Then, we used t-SNE for visualization of patch classification efficiency. Finally, we analyzed morphological characteristics of patches learned by the model.ConclusionThe proposed two-stage model could be effectively applied to the multi-class classification task of breast pathology images and could be a very useful tool for assisting pathologists in diagnosing breast cancer.

An Attention Model With Transfer Embeddings to Classify Pneumonia-Related Bilingual Imaging Reports: Algorithm Development and Validation.

BackgroundIn the analysis of electronic health records, proper labeling of outcomes is mandatory. To obtain proper information from radiologic reports, several studies were conducted to classify radiologic reports using deep learning. However, the classification of pneumonia in bilingual radiologic reports has not been conducted previously.ObjectiveThe aim of this research was to classify radiologic reports into pneumonia or no pneumonia using a deep learning method.MethodsA data set of radiology reports for chest computed tomography and chest x-rays of surgical patients from January 2008 to January 2018 in the Asan Medical Center in Korea was retrospectively analyzed. The classification performance of our long short-term memory (LSTM)–Attention model was compared with various deep learning and machine learning methods. The area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, sensitivity, specificity, accuracy, and F1 score for the models were compared.ResultsA total of 5450 radiologic reports were included that contained at least one pneumonia-related word. In the test set (n=1090), our proposed model showed 91.01% (992/1090) accuracy (AUROCs for negative, positive, and obscure were 0.98, 0.97, and 0.90, respectively). The top 3 performances of the models were based on FastText or LSTM. The convolutional neural network–based model showed a lower accuracy 73.03% (796/1090) than the other 2 algorithms. The classification of negative results had an F1 score of 0.96, whereas the classification of positive and uncertain results showed a lower performance (positive F1 score 0.83; uncertain F1 score 0.62). In the extra-validation set, our model showed 80.0% (642/803) accuracy (AUROCs for negative, positive, and obscure were 0.92, 0.96, and 0.84, respectively).ConclusionsOur method showed excellent performance in classifying pneumonia in bilingual radiologic reports. The method could enrich the research on pneumonia by obtaining exact outcomes from electronic health data.

On application of machine learning method for history matching and forecasting of times series data from hydrocarbon recovery process using water flooding

The focus of this paper is on application of advance data analytics and deep machine learning methods for time series forecasting of injection/production data from subsurface hydrocarbon recovery processes. Injection and production data, from subsurface reservoir developed though implementation of water flooding recovery mechanism, is used with aim of developing a machine learning based forecasting methodology to eventually replace numerical simulation-based forecasting methods. Different machine learning algorithms exists for single- and multi-step time series forecasting, e.g., nonlinear regression, artificial neural network (ANN) and long-short-term-memory (LSTM) based recurrent neural networks (RNN). In this paper, RNN-LSTM algorithm is tested on real field data, comprising of a number of injection and production well patterns, and results of RNN-LSTM forecasting model are presented. Complexities related to data acquisition, analysis, and processing are also discussed in detail. The results presented in this paper are unique as it is for the first time that ML model is applied to forecast production from a tight carbonate hydrocarbon reservoir, which is developed through water flooding with help of long horizontal wells. Such an application for time series forecasting using RNN-LSTM model has never been presented, before in literature, to the best of author’s knowledge.

Метод глубокого метамультиагентного машинного обучения, основан-ный на принципе максимума

Метод глубокого метамультиагентного машинного обучения, основан-ный на принципе максимума

Machine Learning for Violence Risk Assessment Using Dutch Clinical Notes

Violence risk assessment in psychiatric institutions enables interventions to avoid violence incidents. Clinical notes written by practitioners and available in electronic health records are valuable resources capturing unique information, but are seldom used to their full potential. We explore conventional and deep machine learning methods to assess violence risk in psychiatric patients using practitioner notes. The performance of our best models is comparable to the currently used questionnaire-based method, with an area under the Receiver Operating Characteristic curve of approximately 0.8. We find that the deep-learning model BERTje performs worse than conventional machine learning methods. We also evaluate our data and our classifiers to understand the performance of our models better. This is particularly important for the applicability of evaluated classifiers to new data, and is also of great interest to practitioners, due to the increased availability of new data in electronic format.

Collective variables for the study of crystallisation

ABSTRACT The phenomenon of solidification of a substance from its liquid phase is of the greatest practical and theoretical importance, and atomistic simulations can provide precious information towards its understanding and control. Unfortunately, the time scale for crystallisation is much larger than what can be explored in standard simulations. Enhanced sampling methods can overcome this time scale hurdle. Many such methods rely on the definition of appropriate collective variables able to capture the slow degrees of freedom. To this effect, we introduce collective coordinates of general applicability to crystallisation simulations. They are based on the peaks of the three-dimensional structure factor that are combined non-linearly via the Deep Linear Discriminant Analysis machine learning method. We use these collective variables in the context of the on-the-fly probability enhanced sampling method that is a recent evolution of metadynamics. We demonstrate the validity of this approach by studying the crystallisation of a multicomponent system, Sodium Chloride, and a molecular system, Carbon Dioxide.

Using Machine Learning to Examine Cyberattack Motivations on Web Defacement Data

Social scientists have long been interested in the motives of hackers, particularly financially motivated attackers. This article analyzes web defacements, a less studied and more public form of cyberattack, in which the content of a web page is deliberately substituted with unwanted text and graphics chosen by the perpetrator. These attacks use a variety of strategies and are performed for a variety of motives, including political and ideological goals. The proliferation of such attacks has resulted in vast amounts of data that open new opportunities for qualitative and quantitative analysis. This article explores the usefulness of machine learning techniques to better understand attacker strategies and motivations. To detect overall attack patterns, this analysis utilized a sample of 40,000 images posted on defaced websites analyzed through deep machine learning methods. The approach demonstrates the potential of machine learning approaches for the study of cyberattacks, but it also reveals the considerable challenges that need to be overcome.

Plasmonic Anticounterfeit Tags with High Encoding Capacity Rapidly Authenticated with Deep Machine Learning.

Counterfeit goods create significant economic losses and product failures in many industries. Here, we report a covert anticounterfeit platform where plasmonic nanoparticles (NPs) create physically unclonable functions (PUFs) with high encoding capacity. By allowing anisotropic Au NPs of different sizes to deposit randomly, a diversity of surfaces can be facilely tagged with NP deposits that serve as PUFs and are analyzed using optical microscopy. High encoding capacity is engineered into the tags by the sizes of the Au NPs, which provide a range of color responses, while their anisotropy provides sensitivity to light polarization. An estimated encoding capacity of 270n is achieved, which is one of the highest reported to date. Authentication of the tags with deep machine learning allows for high accuracy and rapid matching of a tag to a specific product. Moreover, the tags contain descriptive metadata that is leveraged to match a tag to a specific lot number (i.e., a collection of tags created in the same manner from the same formulation of anisotropic Au NPs). Overall, integration of designer plasmonic NPs with deep machine learning methods can create a rapidly authenticated anticounterfeit platform with high encoding capacity.

Prediction of death status on the course of treatment in SARS-COV-2 patients with deep learning and machine learning methods

Background and ObjectiveThe new type of Coronavirus (2019-nCov) epidemic spread rapidly, causing more than 250 thousand deaths worldwide. The virus, which first appeared as a sign of pneumonia, was later called the SARS-COV-2 with Severe Acute Respiratory Syndrome by the World Health Organization. The SARS-COV-2 virus is triggered by binding to the Angiotensin-Converting Enzyme 2 (ACE 2) inhibitor, which is vital in cardiovascular diseases and the immune system, especially in conditions such as cerebrovascular, hypertension, and diabetes. This study aims to evaluate the prediction performance of death status based on the demographic/clinical factors (including COVID-19 severity) by data mining methods.MethodsThe dataset consists of 1603 SARS-COV-2 patients and 13 variables obtained from an open-source web address. The current dataset contains age, gender, chronic disease (hypertension, diabetes, renal, cardiovascular, etc.), some enzymes (ACE, angiotensin II receptor blockers), and COVID-19 severity, which are used to predict death status using deep learning and machine learning approaches (random forest, k-nearest neighbor, extreme gradient boosting [XGBoost]). A grid search algorithm tunes hyperparameters of the models, and predictions are assessed through performance metrics. Steps of knowledge discovery in databases are applied to obtain the relevant information.ResultsThe accuracy rate of deep learning (97.15%) was more successful than the accuracy rate based on classical machine learning (92.15% for RF and 93.4% for k-NN), but the ensemble classifier XGBoost method gave the highest accuracy (99.7%). While COVID-19 severity and age calculated from XGBoost were the two most important factors associated with death status, the most determining variables for death status estimated from deep learning were COVID-19 severity and hypertension.ConclusionsThe proposed model (XGBoost) achieved the best prediction of death status based on the factors as compared to the other algorithms. The results of this study can guide patients with certain variables to take early measures and access preventive health care services before they become infected with the virus.

A deep learning based framework for the registration of three dimensional multi-modal medical images of the head

Image registration is a fundamental task in image analysis in which the transform that moves the coordinate system of one image to another is calculated. Registration of multi-modal medical images has important implications for clinical diagnosis, treatment planning, and image-guided surgery as it provides the means of bringing together complimentary information obtained from different image modalities. However, since different image modalities have different properties due to their different acquisition methods, it remains a challenging task to find a fast and accurate match between multi-modal images. Furthermore, due to reasons such as ethical issues and need for human expert intervention, it is difficult to collect a large database of labelled multi-modal medical images. In addition, manual input is required to determine the fixed and moving images as input to registration algorithms. In this paper, we address these issues and introduce a registration framework that (1) creates synthetic data to augment existing datasets, (2) generates ground truth data to be used in the training and testing of algorithms, (3) registers (using a combination of deep learning and conventional machine learning methods) multi-modal images in an accurate and fast manner, and (4) automatically classifies the image modality so that the process of registration can be fully automated. We validate the performance of the proposed framework on CT and MRI images of the head obtained from a publicly available registration database.

The Use of Deep Machine Learning for the Automated Selection of Remote Sensing Data for the Determination of Areas of Arable Land Degradation Processes Distribution

Soil degradation processes are widespread on agricultural land. Ground-based methods for detecting degradation require a lot of labor and time. Remote methods based on the analysis of vegetation indices can significantly reduce the volume of ground surveys. Currently, machine learning methods are increasingly being used to analyze remote sensing data. In this paper, the task is set to apply deep machine learning methods and methods of vegetation indices calculation to automate the detection of areas of soil degradation development on arable land. In the course of the work, a method was developed for determining the location of degraded areas of soil cover on arable fields. The method is based on the use of multi-temporal remote sensing data. The selection of suitable remote sensing data scenes is based on deep machine learning. Deep machine learning was based on an analysis of 1028 scenes of Landsats 4, 5, 7 and 8 on 530 agricultural fields. Landsat data from 1984 to 2019 was analyzed. Dataset was created manually for each pair of “Landsat scene”/“agricultural field number”(for each agricultural field, the suitability of each Landsat scene was assessed). Areas of soil degradation were calculated based on the frequency of occurrence of low NDVI values over 35 years. Low NDVI values were calculated separately for each suitable fragment of the satellite image within the boundaries of each agricultural field. NDVI values of one-third of the field area and lower than the other two-thirds were considered low. During testing, the method gave 12.5% of type I errors (false positive) and 3.8% of type II errors (false negative). Independent verification of the method was carried out on six agricultural fields on an area of 713.3 hectares. Humus content and thickness of the humus horizon were determined in 42 ground-based points. In arable land degradation areas identified by the proposed method, the probability of detecting soil degradation by field methods was 87.5%. The probability of detecting soil degradation by ground-based methods outside the predicted regions was 3.8%. The results indicate that deep machine learning is feasible for remote sensing data selection based on a binary dataset. This eliminates the need for intermediate filtering systems in the selection of satellite imagery (determination of clouds, shadows from clouds, open soil surface, etc.). Direct selection of Landsat scenes suitable for calculations has been made. It allows automating the process of constructing soil degradation maps.

A Study On Deep Learning And Machine Learning Techniques On Detection Of Parkinson’s Disease

Parkinson’s disease (PD) is a sophisticated anxiety malady that impairs movement. Symptoms emerge gradually, initiating with a slight tremor in only one hand occasionally. Tremors are prevalent, although the condition is sometimes associated with stiffness or slowed mobility. In the early degrees of PD, your face can also additionally display very little expression. Your fingers won’t swing while you walk. Your speech can also additionally grow to be gentle or slurred. PD signs and symptoms get worse as your circumstance progresses over time. The goal of this study is to test the efficiency of deep learning and machine learning approaches in order to identify the most accurate strategy for sensing Parkinson’s disease at an early stage. In order to measure the average performance most accurately, we compared deep learning and machine learning methods.

A Survey on Leukemia Detection using Image Processing Techniques

Leukemia detection and diagnosis by inspecting the blood cell images is an intriguing and dynamic exploration region in both the Artificial Intelligence and Medical research fields. There are numerous procedures created to look at blood tests to identify leukemia illness, these strategies are the customary methods and the deep learning (DL) strategy. This survey paper presents a review on the distinctive conventional strategies and Deep Learning and Machine Learning methods towards that have been utilized in leukemia illness diagnosis dependent on platelets images and to analyze between the two methodologies in nature of appraisal, exactness, cost and speed. This article covers 11 research papers, 9 of these examinations were in customary strategies which utilized image handling and AI (ML) calculations, such as, K-closest neighbor (KNN), K-means, SVM, Naïve Bayes, and 2 investigations in cutting edge procedures which utilized Deep Learning, especially Convolutional Neural Networks (CNNs) which is the most generally utilized in the field leukemia detection since it is profoundly precise, quick, and has the smallest expense. What's more, it dissects various late works that have been presented in the field including the dataset size, the pre-owned procedures, the acquired outcomes, and so forth. At last, in view of the led study, it very well may be reasoned that the proposed framework CNN was accomplishing immense triumphs in the field whether in regards to highlights extraction or classification time, precision and also a best low cost in the identification of leukemia.

Book review of artificial intelligence in medicine Edited by LeiXing, MaryellenGiger, and JamesMin

Book review of artificial intelligence in medicine Edited by LeiXing, MaryellenGiger, and JamesMin

An Investigation of Deep Learning Models for EEG-Based Emotion Recognition.

Emotion is the human brain reacting to objective things. In real life, human emotions are complex and changeable, so research into emotion recognition is of great significance in real life applications. Recently, many deep learning and machine learning methods have been widely applied in emotion recognition based on EEG signals. However, the traditional machine learning method has a major disadvantage in that the feature extraction process is usually cumbersome, which relies heavily on human experts. Then, end-to-end deep learning methods emerged as an effective method to address this disadvantage with the help of raw signal features and time-frequency spectrums. Here, we investigated the application of several deep learning models to the research field of EEG-based emotion recognition, including deep neural networks (DNN), convolutional neural networks (CNN), long short-term memory (LSTM), and a hybrid model of CNN and LSTM (CNN-LSTM). The experiments were carried on the well-known DEAP dataset. Experimental results show that the CNN and CNN-LSTM models had high classification performance in EEG-based emotion recognition, and their accurate extraction rate of RAW data reached 90.12 and 94.17%, respectively. The performance of the DNN model was not as accurate as other models, but the training speed was fast. The LSTM model was not as stable as the CNN and CNN-LSTM models. Moreover, with the same number of parameters, the training speed of the LSTM was much slower and it was difficult to achieve convergence. Additional parameter comparison experiments with other models, including epoch, learning rate, and dropout probability, were also conducted in the paper. Comparison results prove that the DNN model converged to optimal with fewer epochs and a higher learning rate. In contrast, the CNN model needed more epochs to learn. As for dropout probability, reducing the parameters by ~50% each time was appropriate.

Prediction of tunnel boring machine operating parameters using various machine learning algorithms

The operating parameters of a tunnel boring machine (TBM) reflect its geological conditions and working status and are accordingly critical data for ensuring safe and efficient tunnel construction. The accurate prediction of the advance rate, rotation speed, thrust, and torque indicators based on the operating parameters can guide the control and application of a TBM. In this study, we analyzed the relationships between the TBM operating parameters and daily collected TBM data. We used the smoothing method and outlier detection to process this data, and determined the stable values of four different TBM indicators in the ascending phase of a complete TBM operational segment. Then, we evaluated the application of five different statistical and ensemble machine learning methods (Bayesian ridge regression (BR), nearest neighbors regression, random forests, gradient tree boosting (GTB), and support vector machine) and two different deep neural networks (a convolutional neural network (CNN) and long short-term memory network (LSTM)) to establish prediction models. The GTB method provided the best prediction accuracy and the BR method provided the least calculation time of the five different statistical and ensemble machine learning methods evaluated. The LSTM method provided a higher prediction accuracy than the CNN model. The ensemble machine learning methods were found to be the most accurate for the relatively limited data sets used in this study, suggesting that sufficient data must be present before the advantages of deep neural networks can be truly realized. The successful application of statistical, ensemble, and deep neural network machine learning methods to predict TBM indicators in this study suggests the promise of machine learning in this application.