Search

Landslides are regarded as one of the most common geological hazards in a wide range of geo-environment. The aim of this study is to assess landslide susceptibility by integrating convolutional neural network (CNN) with three conventional machine learning classifiers of support vector machine (SVM), random forest (RF) and logistic regression (LR) in the case of Yongxin Country, China. To this end, 16 predisposing factors were first selected for landslide modelling. Then, a total of 364 landslide historical locations were randomly divided into training (70%; 255) and verification (30%; 109) sets for modelling process and assessment. Next, the training set was used for building three hybrid methods of CNN-SVM, CNN-RF and CNN-LR. In the following, the trained models were used for landslide susceptibility mapping. Finally, several objective measures were employed to compare and validate the performance of these methods. The experimental results demonstrated that the performance of the machine learning classifiers previously mentioned can be effectively improved by integrating the CNN technique. Therefore, the proposed hybrid methods can be recommended for landslide spatial modelling in other prone areas with similar geo-environmental conditions. • Landslide susceptibility prediction based on CNN and machine learning models. • CNN is used to extract useful features from landslide raw data. • Accuracy of single classifiers are improved using the CNN for feature extraction. • Reliable landslide susceptibility maps are obtained by using the hybrid methods. [ABSTRACT FROM AUTHOR]

Early detection of patients at risk for clinical deterioration is crucial for timely intervention. Traditional detection systems rely on a limited set of variables and are unable to predict the time of decline. We describe a machine learning model called MEWS++ that enables the identification of patients at risk of escalation of care or death six hours prior to the event. A retrospective single-center cohort study was conducted from July 2011 to July 2017 of adult (age > 18) inpatients excluding psychiatric, parturient, and hospice patients. Three machine learning models were trained and tested: random forest (RF), linear support vector machine, and logistic regression. We compared the models' performance to the traditional Modified Early Warning Score (MEWS) using sensitivity, specificity, and Area Under the Curve for Receiver Operating Characteristic (AUC-ROC) and Precision-Recall curves (AUC-PR). The primary outcome was escalation of care from a floor bed to an intensive care or step-down unit, or death, within 6 h. A total of 96,645 patients with 157,984 hospital encounters and 244,343 bed movements were included. Overall rate of escalation or death was 3.4%. The RF model had the best performance with sensitivity 81.6%, specificity 75.5%, AUC-ROC of 0.85, and AUC-PR of 0.37. Compared to traditional MEWS, sensitivity increased 37%, specificity increased 11%, and AUC-ROC increased 14%. This study found that using machine learning and readily available clinical data, clinical deterioration or death can be predicted 6 h prior to the event. The model we developed can warn of patient deterioration hours before the event, thus helping make timely clinical decisions. [ABSTRACT FROM AUTHOR]

• S2 imagery and machine learning can map crops as early as eight weeks before harvest. • Hand-selecting images for inclusion did not significantly improve results. • Pre-analyses of individual images is a viable alternative to hand-selecting images. Timely crop type information (preferably before harvest) is useful for predicting food surpluses or shortages. This study assesses the performance of several machine learning classifiers, namely SVM (support vector machine), DT (decision tree), k-NN (k-nearest neighbour), RF (random forest) and ML (maximum likelihood) for crop type mapping based on a series of Sentinel-2 images. Four experiments with different combinations of image sets were carried out. The first three experiments were undertaken with 1) single-date (uni-temporal) images; 2) combinations of five images selected from the best performing single-date images; and 3) five images selected manually based on crop development stages. The fourth experiment involved the chronologic addition of images to assess the performance of the classifiers when only pre-harvest images are used, with the purpose of investigating how early in the season reasonable accuracies can be achieved. The experiments were carried out in two different sites in the Western Cape Province of South Africa to provide a good representation of the grain-producing areas in the region which has a Mediterranean climate. The significance of image selection on classification accuracies as well as the performance of machine learning classifiers when only pre-harvest images are used were evaluated. The classification results were analysed by comparing overall accuracies and kappa coefficients, while McNemar′s test and ANOVA (analysis of variance) were used to assess the statistical significance of the differences in accuracies among experiments. The results show that by selecting images based on individual performance, a viable alternative to selecting images based on crop developmental stages is offered, and that the classification of crops with an entire time series can be just as accurate as when they are classified with a subset of hand-selected images. We also found that good classification accuracies (77.2%) can be obtained with the use of SVM and RF as early as eight weeks before harvest. This result shows that pre-harvest images have the potential to identify crops accurately, which holds much potential for operational within-season crop type mapping. [ABSTRACT FROM AUTHOR]

• Computer Aided Diagnostic (CAD) Technique for Epileptic Seizure Detection. • Discrete Wavelet Transform and Arithmetic Coding based Feature Extraction for EEG Signals. • Application of Machine Learning Classifiers in seizure detection. Epilepsy, a common neurological disorder, is generally detected by electroencephalogram (EEG) signals. Visual inspection and interpretation of EEGs is a slow, time consuming process that is vulnerable to error and subjective variability. Consequently, several efforts to develop automatic epileptic seizure detection and classification methods have been made. The present study proposes a novel computer aided diagnostic technique (CAD) based on the discrete wavelet transform (DWT) and arithmetic coding to differentiate epileptic seizure signals from normal (seizure-free) signals. The proposed CAD technique comprises three steps. The first step decomposes EEG signals into approximations and detail coefficients using DWT while discarding non-significant coefficients in view of threshold criteria; thus, limiting the number of significant wavelet coefficients. The second step converts significant wavelet coefficients to bit streams using arithmetic coding to compute the compression ratio. In the final step, the compression feature set is standardized, whereupon machine-learning classifiers detect seizure activity from seizure-free signals. We employed the widely used benchmark database from Bonn University to compare and validate the technique with results from prior approaches. The proposed method achieved a perfect classification performance (100% accuracy) for the detection of epileptic seizure activity from EEG data, using both linear and non-liner machine-learning classifiers. This CAD technique can thus be considered robust with an extraordinary detection capability that discriminates epileptic seizure activity from seizure-free and normal EEG activity with simple linear classifiers. The method has the potential for efficient application as an adjunct for the clinical diagnosis of epilepsy. [ABSTRACT FROM AUTHOR]

The classifier of support vector machine (SVM) learning for assessing the quality of arteriovenous fistulae (AVFs) in hemodialysis (HD) patients using a new photoplethysmography (PPG) sensor device is presented in this work. In clinical practice, there are two important indices for assessing the quality of AVF: the blood flow volume (BFV) and the degree of stenosis (DOS). In hospitals, the BFV and DOS of AVFs are nowadays assessed using an ultrasound Doppler machine, which is bulky, expensive, hard to use, and time consuming. In this study, a newly-developed PPG sensor device was utilized to provide patients and doctors with an inexpensive and small-sized solution for ubiquitous AVF assessment. The readout in this sensor was custom-designed to increase the signal-to-noise ratio (SNR) and reduce the environment interference via maximizing successfully the full dynamic range of measured PPG entering an analog–digital converter (ADC) and effective filtering techniques. With quality PPG measurements obtained, machine learning classifiers including SVM were adopted to assess AVF quality, where the input features are determined based on optical Beer–Lambert's law and hemodynamic model, to ensure all the necessary features are considered. Finally, the clinical experiment results showed that the proposed PPG sensor device successfully achieved an accuracy of 87.84% based on SVM analysis in assessing DOS at AVF, while an accuracy of 88.61% was achieved for assessing BFV at AVF. [ABSTRACT FROM AUTHOR]

Automatic identification of metallurgical phases based on thresholding methods in microstructural images may not be possible when the pixel intensities associated with the metallurgical phases overlap and, hence, are indistinguishable. To circumvent this problem, additional visual information about the metallurgical phases, referred to as textural features, are considered in this study. Mathematically, textural features are the second order statistics of an image domain and can be distinct for each metallurgical phase. Textural features are evaluated from the gray level co-occurrence matrix (GLCM) of each metallurgical phase (ferrite, pearlite, and martensite) present in heat-treated ASTM A36 steels in this study. The dataset of textural features and pixel intensities generated for the metallurgical phases is used to train supervised machine learning classifiers, which are subsequently employed to predict the metallurgical phases in the microstructure. Naïve Bayes (NB), k-nearest neighbor (K-NN), linear discriminant analysis (LDA), and decision tree (DT) classifiers are the four classifiers employed in this study. The performances of all four classifiers were assessed prior to their deployment, and the classification accuracy was found to be >97%. The proposed technique has two unique advantages: (1) unlike pixel intensity-based methods, the proposed method does not misclassify the grain boundaries as a metallurgical phase, and (2) the proposed method does not require the end-user to input the number of phases present in the microstructure. [ABSTRACT FROM AUTHOR]

Decision fusion is used to fuse classification results and improve the classification accuracy in order to reduce the consumption of energy and bandwidth demand for data transmission. The decentralized classification fusion problem was the reason to use the belief function-based decision fusion approach in Wireless Sensor Networks (WSNs). With the consideration of improving the belief function fusion approach, we have proposed four classification techniques, namely Enhanced K-Nearest Neighbor (EKNN), Enhanced Extreme Learning Machine (EELM), Enhanced Support Vector Machine (ESVM), and Enhanced Recurrent Extreme Learning Machine (ERELM). In addition, WSNs are prone to errors and faults because of their different software, hardware failures, and their deployment in diverse fields. Because of these challenges, efficient fault detection methods must be used to detect faults in a WSN in a timely manner. We have induced four types of faults: offset fault, gain fault, stuck-at fault, and out of bounds fault, and used enhanced classification methods to solve the sensor failure issues. Experimental results show that ERELM gave the first best result for the improvement of the belief function fusion approach. The other three proposed techniques ESVM, EELM, and EKNN provided the second, third, and fourth best results, respectively. The proposed enhanced classifiers are used for fault detection and are evaluated using three performance metrics, i.e., Detection Accuracy (DA), True Positive Rate (TPR), and Error Rate (ER). Simulations show that the proposed methods outperform the existing techniques and give better results for the belief function and fault detection in WSNs. [ABSTRACT FROM AUTHOR]

Machine learning models are increasingly being used in clinical settings for diagnostic and treatment recommendations, across a variety of diseases and diagnostic methods. To conceptualise how physicians can use them responsibly, and what the standard of care should be, there needs to be discussion beyond model accuracy levels and the types of explanation provided by such classifiers. There needs to be consideration of how the explanations are provided and how historical accuracy rates can together constitute the overall epistemic status of the model, and how models with different epistemic statuses should subsequently be deferred to by medical practitioners. Answering this will require a multi-disciplinary consideration of the literature on automation bias in human factors and ergonomics to higher-order evidence in social epistemology. Adjudicating physician responsibility will also require assessing when a physician's ignorance of the appropriate ways to engage with such classifiers, as outlined above, will be culpable and when not., Competing Interests: None.

In traditional databases, the entity resolution problem (which is also known as deduplication) refers to the task of mapping multiple manifestations of virtual objects to their corresponding real-world entities. When addressing this problem, in both theory and practice, it is widely assumed that such sets of virtual objects appear as the result of clerical errors, transliterations, missing or updated attributes, abbreviations, and so forth. In this paper, we address this problem under the assumption that this situation is caused by malicious actors operating in domains in which they do not wish to be identified, such as hacker forums and markets in which the participants are motivated to remain semi-anonymous (though they wish to keep their true identities secret, they find it useful for customers to identify their products and services). We are therefore in the presence of a different, and even more challenging, problem that we refer to as adversarial deduplication. In this paper, we study this problem via examples that arise from real-world data on malicious hacker forums and markets arising from collaborations with a cyber threat intelligence company focusing on understanding this kind of behavior. We argue that it is very difficult—if not impossible—to find ground truth data on which to build solutions to this problem, and develop a set of preliminary experiments based on training machine learning classifiers that leverage text analysis to detect potential cases of duplicate entities. Our results are encouraging as a first step towards building tools that human analysts can use to enhance their capabilities towards fighting cyber threats. [ABSTRACT FROM AUTHOR]

For the past several decades, there is growing demand for the development of low-power gas sensing technology for the selective detection of volatile organic compounds (VOCs), important for monitoring safety, pollution, and healthcare. Here we report the selective detection of homologous alcohols and different functional groups containing VOCs using the electrostatically formed nanowire (EFN) sensor without any surface modification of the device. Selectivity toward specific VOC is achieved by training machine-learning based classifiers using the calculated changes in the threshold voltage and the drain-source on current, obtained from systematically controlled biasing of the surrounding gates (junction and back gates) of the field-effect transistors (FET). This work paves the way for a Si complementary metal-oxide-semiconductor (CMOS)-based FET device as an electrostatically selective sensor suitable for mass production and low-power sensing technology.