RST Analysis of Anomalous TIR Sequences in Relation with Earthquakes Occurred in Turkey in the Period 2004–2015

The paper provides, for the first time, a long-term (>10 years) analysis of anomalous transients in Earth’s emitted radiation over Turkey and neighbouring regions. The RST (Robust Satellite Techniques) approach is used to identify Significant Sequences of Thermal Anomalies (SSTAs) over about 12 years (May 2004 to October 2015) of night-time MSG-SEVIRI satellite images. The correlation analysis is performed with earthquakes with M ≥ 4, which occurred in the investigated period/region within a pre-defined space-time volume around SSTA occurrences. It confirms, also for Turkey, the possibility to qualify SSTAs among the candidate parameters of a multi-parametric system for time-Dependent Assessment of Seismic Hazard (t-DASH). After analysing about 4000 images (about 400 million of single satellite records), just 155 SSTAs (about 4 every 100 images) were isolated; 115 (74% out of the total) resulted in earthquake-related (false-positive rate 26%). Results of the error diagram confirms a non-casual correlation between RST-based SSTAs and earthquake occurrences, with probability gain values up to 2.2 in comparison with the random guess. The analysis, separately performed on Turkish areas characterized by different faults and earthquakes densities, demonstrates the SSTA correlation with a dynamic seismicity more than with static tectonic settings.

Predicting bitcoin price movements using sentiment analysis: a machine learning approach

Purpose Cryptocurrencies such as Bitcoin (BTC) attracted a lot of attention in recent months due to their unprecedented price fluctuations. This paper aims to propose a new method for predicting the direction of BTC price using linear discriminant analysis (LDA) together with sentiment analysis. Design/methodology/approach Concretely, the authors train an LDA-based classifier that uses the current BTC price information and BTC news announcements headlines to forecast the next-day direction of BTC prices. The authors compare the results with a Support Vector Machine (SVM) model and random guess approach. The use of BTC price information and news announcements related to crypto enables us to value the importance of these different sources and types of information. Findings Relative to the LDA results, the SVM model was more accurate in predicting BTC next day’s price movement. All models yielded better forecasts of an increase in tomorrow’s BTC price compared to forecasting a decrease in the crypto price. The inclusion of news sentiment resulted in the highest forecast accuracy of 0.585 on the test data, which is superior to a random guess. The LDA (SVM) model with asset specific (news sentiment and asset specific) input features ranked first within their respective model classifiers, suggesting both BTC news sentiment and asset specific are prized factors in predicting tomorrow’s price direction. Originality/value To the best of the authors’ knowledge, this is the first study to analyze the potential effect of crypto-related sentiment and BTC specific news on BTC’s price using LDA and sentiment analysis.

Investigating Deep Learning Approaches on the Security Analysis of Cryptographic Algorithms

This paper studies the use of deep learning (DL) models under a known-plaintext scenario. The goal of the models is to predict the secret key of a cipher using DL techniques. We investigate the DL techniques against different ciphers, namely, Simplified Data Encryption Standard (S-DES), Speck, Simeck and Katan. For S-DES, we examine the classification of the full key set, and the results are better than a random guess. However, we found that it is difficult to apply the same classification model beyond 2-round Speck. We also demonstrate that DL models trained under a known-plaintext scenario can successfully recover the random key of S-DES. However, the same method has been less successful when applied to modern ciphers Speck, Simeck, and Katan. The ciphers Simeck and Katan are further investigated using the DL models but with a text-based key. This application found the linear approximations between the plaintext–ciphertext pairs and the text-based key.

Towards Interpretable Machine Learning in EEG Analysis

In this paper a machine learning model for automatic detection of abnormalities in electroencephalography (EEG) is dissected into parts, so that the influence of each part on the classification accuracy score can be examined. The most successful setup of several shallow artificial neural networks aggregated via voting results in accuracy of 81%. Stepwise simplification of the model shows the expected decrease in accuracy, but a naive model with thresholding of a single extracted feature (relative wavelet energy) is still able to achieve 75%, which remains strongly above the random guess baseline of 54%. These results suggest the feasibility of building a simple classification model ensuring accuracy scores close to the state-of-the-art research but remaining fully interpretable.

Keystroke Dynamics Patterns While Writing Positive and Negative Opinions

This paper deals with analysis of behavioural patterns in human–computer interaction. In the study, keystroke dynamics were analysed while participants were writing positive and negative opinions. A semi-experiment with 50 participants was performed. The participants were asked to recall the most negative and positive learning experiences (subject and teacher) and write an opinion about it. Keystroke dynamics were captured and over 50 diverse features were calculated and checked against the ability to differentiate positive and negative opinions. Moreover, classification of opinions was performed providing accuracy slightly above the random guess level. The second classification approach used self-report labels of pleasure and arousal and showed more accurate results. The study confirmed that it was possible to recognize positive and negative opinions from the keystroke patterns with accuracy above the random guess; however, combination with other modalities might produce more accurate results.

The knowledge norm of assertion: keep it simple

The simple knowledge norm of assertion (SKNA) holds that one may (epistemically permissibly) assert that p only if one knows that p. Turri (Aust J Philos 89(1):37–45, 2011) and Williamson (Knowledge and its limits, Oxford University Press, Oxford, 2000) both argue that more is required for epistemically permissible assertion. In particular, they both think that the asserter must assert on the basis of her knowledge. Turri calls this the express knowledge norm of assertion (EKNA). I defend SKNA and argue against EKNA. First, I argue that EKNA faces counterexamples. Second, I argue that EKNA assumes an implausible view of permissibility on which an assertion is epistemically permissible only if it is made for a right reason, i.e., a reason that contributes to making it the case that it is epistemically permissible to make that assertion. However, the analogous view in other normative domains is both controversial and implausible. This is because it doesn’t make it possible for one to act or react rightly for the wrong reason. I suggest that proponents of EKNA have conflated requirements for φ-ing rightly (or permissibly) with requirements for φ-ing well. Finally, I argue that proponents of SKNA can explain the intuitive defectiveness of asserting on the basis of an epistemically bad reason (e.g., a random guess), even when the asserters know the content of their assertion, by arguing that the asserters are epistemically blameworthy.

Deep Learning–Based COVID-19 Pneumonia Classification Using Chest CT Images: Model Generalizability

Since the outbreak of the COVID-19 pandemic, worldwide research efforts have focused on using artificial intelligence (AI) technologies on various medical data of COVID-19–positive patients in order to identify or classify various aspects of the disease, with promising reported results. However, concerns have been raised over their generalizability, given the heterogeneous factors in training datasets. This study aims to examine the severity of this problem by evaluating deep learning (DL) classification models trained to identify COVID-19–positive patients on 3D computed tomography (CT) datasets from different countries. We collected one dataset at UT Southwestern (UTSW) and three external datasets from different countries: CC-CCII Dataset (China), COVID-CTset (Iran), and MosMedData (Russia). We divided the data into two classes: COVID-19–positive and COVID-19–negative patients. We trained nine identical DL-based classification models by using combinations of datasets with a 72% train, 8% validation, and 20% test data split. The models trained on a single dataset achieved accuracy/area under the receiver operating characteristic curve (AUC) values of 0.87/0.826 (UTSW), 0.97/0.988 (CC-CCCI), and 0.86/0.873 (COVID-CTset) when evaluated on their own dataset. The models trained on multiple datasets and evaluated on a test set from one of the datasets used for training performed better. However, the performance dropped close to an AUC of 0.5 (random guess) for all models when evaluated on a different dataset outside of its training datasets. Including MosMedData, which only contained positive labels, into the training datasets did not necessarily help the performance of other datasets. Multiple factors likely contributed to these results, such as patient demographics and differences in image acquisition or reconstruction, causing a data shift among different study cohorts.

Validation of Maternal Recall of Iron Folic Supplementation During Antenatal Care in Rural Southern Nepal

Objectives This study's primary objective is to examine the validity of maternal recall of iron folate supplementation during antenatal care and factors associated with accuracy of maternal recall. Methods A longitudinal cohort design was employed for the validation study. The direct observation of all iron folate supplementation (IFA) received during all antenatal care visits at the five study health posts served as the “gold standard” to the maternal report of IFA received collected during a postpartum interview. Individual-level validity was assessed by calculating indicator sensitivity, specificity and area under the receiver operating curve (AUC). The inflation factor (IF) measured population-level bias, comparing the true coverage to the survey measure (maternal report) coverage of IFA. A multivariable log-binomial model was used to assess factors associated with accurate recall. Results The majority (95.8%) of women were observed receiving IFA during pregnancy. Women overreported the number IFA tablets received compared to what was observed during ANC visits. On average the reported number of tablets received was 45 tablets greater than the number observed. Individual-level accuracy of maternal report of any IFA receipt was moderate (AUC = 0.60) and population bias was low (IF = 1.01). However, the individual-level validity was poor across the seven IFA tablet count categories; the AUC for categories ranged from 0.47 to 0.58, indicating a performance that at best was slightly better than a random guess and at worst, misleading. Driven by the trend of maternal overreport, the inflation factor indicated that the survey measure drastically underestimated the prevalence of lower tablet categories and overestimated the prevalence of higher tablet counts. Accuracy of maternal report was not associated with months since last ANC observation nor any maternal characteristics. Conclusions Maternal report of the amount IFA supplementation received during pregnancy produced extremely biased population prevalence and performed comparably to or worse than a random guess for individual level validity. It's imperative to improve this indicator for future use, as it is included in global frameworks, initiatives and national program planning. Funding Sources This research was funded by the Bill and Melinda Gates Foundation.

Blinding, sham, and treatment effects in randomized controlled trials for back pain in 2000–2019: A review and meta-analytic approach

Background: Blinding aims to minimize biases from what participants and investigators know or believe. Randomized controlled trials, despite being the gold standard to evaluate treatment effect, do not generally assess the success of blinding. We investigated the extent of blinding in back pain trials and the associations between participant guesses and treatment effects. Methods: We did a review with PubMed/OvidMedline, 2000–2019. Eligibility criteria were back pain trials with data available on treatment effect and participants’ guess of treatment. For blinding, blinding index was used as chance-corrected measure of excessive correct guess (0 for random guess). For treatment effects, within- or between-arm effect sizes were used. Analyses of investigators’ guess/blinding or by treatment modality were performed exploratorily. Results: Forty trials (3899 participants) were included. Active and sham treatment groups had mean blinding index of 0.26 (95% confidence interval: 0.12, 0.41) and 0.01 (−0.11, 0.14), respectively, meaning 26% of participants in active treatment believed they received active treatment, whereas only 1% in sham believed they received sham treatment, beyond chance, that is, random guess. A greater belief of receiving active treatment was associated with a larger within-arm effect size in both arms, and ideal blinding (namely, “random guess,” and “wishful thinking” that signifies both groups believing they received active treatment) showed smaller effect sizes, with correlation of effect size and summary blinding indexes of 0.35 ( p = 0.028) for between-arm comparison. We observed uniformly large sham treatment effects for all modalities, and larger correlation for investigator’s (un)blinding, 0.53 ( p = 0.046). Conclusion: Participants in active treatments in back pain trials guessed treatment identity more correctly, while those in sham treatments tended to display successful blinding. Excessive correct guesses (that could reflect weaker blinding and/or noticeable effects) by participants and investigators demonstrated larger effect sizes. Blinding and sham treatment effects on back pain need due consideration in individual trials and meta-analyses.

Confidence of treatment decision and perceived risk of procedure-related neurological complications in the management of unruptured intracranial aneurysms

Background and purposeTo evaluate factors influencing the confidence of management recommendation for unruptured intracranial aneurysms (UIAs) and to assess the ability of neurointerventionalists to predict procedure-related neurological complications compared with a 3-point risk score.Materials and methodsTwenty-eight neurointerventionalists were asked to evaluate digital subtraction angiographies examinations of patients with UIAs by determining the best management approach, their level of confidence in their management recommendation, and estimating the risk of procedure-related neurological complications. Knowledge and experience in interventional neuroradiology (INR) of each participant were assessed.ResultsReliability was moderate regarding any treatment recommendation (ICC=0.49) and low regarding the estimation of risk of complications (ICC=0.38). The recommendation of clipping was less likely with more experience in INR (OR=0.6) and more likely with increasing knowledge (OR=1.7). Odds of recommending WEB device were lower with more experience in INR (OR=0.6), higher in patients with multiple aneurysms (OR=3.6) and increasing neck width (OR=2.7). The recommendation of stent-assisted coiling was more likely with increasing neck width (OR=2.4) and when cerebral ischemic comorbidities were present (OR=2.9). The participants were significantly worse than the risk score (mean area under the curve of 0.53) and not better than random guess in predicting complications. Neither knowledge nor experience in INR was significantly associated with the participants’ ability to predict neurological complications.ConclusionsOur study shows a moderate interrater reliability of treatment recommendations of UIAs. Confidence in treatment recommendation varied significantly according to recommended treatments. Overall performance in predicting neurological complications was worse than the risk score and not better than random guess.