Analysis of Bayesian classification-based approaches for Android malware detection

Mobile malware has been growing in scale and complexity spurred by the unabated uptake of smartphones worldwide. Android is fast becoming the most popular mobile platform resulting in sharp increase in malware targeting the platform. Additionally, Android malware is evolving rapidly to evade detection by traditional signature-based scanning. Despite current detection measures in place, timely discovery of new malware is still a critical issue. This calls for novel approaches to mitigate the growing threat of zero-day Android malware. Hence, the authors develop and analyse proactive machine-learning approaches based on Bayesian classification aimed at uncovering unknown Android malware via static analysis. The study, which is based on a large malware sample set of majority of the existing families, demonstrates detection capabilities with high accuracy. Empirical results and comparative analysis are presented offering useful insight towards development of effective static-analytic Bayesian classification-based solutions for detecting unknown Android malware.

DiveRsity: An R package for the estimation and exploration of population genetics parameters and their associated errors

Summary: We present a new R package, diveRsity, for the calculation of various diversity statistics, including common diversity partitioning statistics (?, G) and population differentiation statistics (D, GST ', ? test for population heterogeneity), among others. The package calculates these estimators along with their respective bootstrapped confidence intervals for loci, sample population pairwise and global levels. Various plotting tools are also provided for a visual evaluation of estimated values, allowing users to critically assess the validity and significance of statistical tests from a biological perspective. diveRsity has a set of unique features, which facilitate the use of an informed framework for assessing the validity of the use of traditional F-statistics for the inference of demography, with reference to specific marker types, particularly focusing on highly polymorphic microsatellite loci. However, the package can be readily used for other co-dominant marker types (e.g. allozymes, SNPs). Detailed examples of usage and descriptions of package capabilities are provided. The examples demonstrate useful strategies for the exploration of data and interpretation of results generated by diveRsity. Additional online resources for the package are also described, including a GUI web app version intended for those with more limited experience using R for statistical analysis. © 2013 British Ecological Society.

Monitoring daily MLC positional errors using trajectory log files and EPID measurements for IMRT and VMAT deliveries

This work investigated the differences between multileaf collimator (MLC) positioning accuracy determined using either log files or electronic portal imaging devices (EPID) and then assessed the possibility of reducing patient specific quality control (QC) via phantom-less methodologies. In-house software was developed, and validated, to track MLC positional accuracy with the rotational and static gantry picket fence tests using an integrated electronic portal image. This software was used to monitor MLC daily performance over a 1 year period for two Varian TrueBeam linear accelerators, with the results directly compared with MLC positions determined using leaf trajectory log files. This software was validated by introducing known shifts and collimator errors. Skewness of the MLCs was found to be 0.03 ± 0.06° (mean ±1 standard deviation (SD)) and was dependent on whether the collimator was rotated manually or automatically. Trajectory log files, analysed using in-house software, showed average MLC positioning errors with a magnitude of 0.004 ± 0.003 mm (rotational) and 0.004 ± 0.011 mm (static) across two TrueBeam units over 1 year (mean ±1 SD). These ranges, as indicated by the SD, were lower than the related average MLC positioning errors of 0.000 ± 0.025 mm (rotational) and 0.000 ± 0.039 mm (static) that were obtained using the in-house EPID based software. The range of EPID measured MLC positional errors was larger due to the inherent uncertainties of the procedure. Over the duration of the study, multiple MLC positional errors were detected using the EPID based software but these same errors were not detected using the trajectory log files. This work shows the importance of increasing linac specific QC when phantom-less methodologies, such as the use of log files, are used to reduce patient specific QC. Tolerances of 0.25 mm have been created for the MLC positional errors using the EPID-based automated picket fence test. The software allows diagnosis of any specific leaf that needs repair and gives an indication as to the course of action that is required.

Novel genetic susceptibility loci for diabetic end-stage renal disease identified through robust naive Bayes classification

Aims/hypothesis: Diabetic nephropathy is a major diabetic complication, and diabetes is the leading cause of end-stage renal disease (ESRD). Family studies suggest a hereditary component for diabetic nephropathy. However, only a few genes have been associated with diabetic nephropathy or ESRD in diabetic patients. Our aim was to detect novel genetic variants associated with diabetic nephropathy and ESRD. Methods: We exploited a novel algorithm, ‘Bag of Naive Bayes’, whose marker selection strategy is complementary to that of conventional genome-wide association models based on univariate association tests. The analysis was performed on a genome-wide association study of 3,464 patients with type 1 diabetes from the Finnish Diabetic Nephropathy (FinnDiane) Study and subsequently replicated with 4,263 type 1 diabetes patients from the Steno Diabetes Centre, the All Ireland-Warren 3-Genetics of Kidneys in Diabetes UK collection (UK–Republic of Ireland) and the Genetics of Kidneys in Diabetes US Study (GoKinD US). Results: Five genetic loci (WNT4/ZBTB40-rs12137135, RGMA/MCTP2-rs17709344, MAPRE1P2-rs1670754, SEMA6D/SLC24A5-rs12917114 and SIK1-rs2838302) were associated with ESRD in the FinnDiane study. An association between ESRD and rs17709344, tagging the previously identified rs12437854 and located between the RGMA and MCTP2 genes, was replicated in independent case–control cohorts. rs12917114 near SEMA6D was associated with ESRD in the replication cohorts under the genotypic model (p < 0.05), and rs12137135 upstream of WNT4 was associated with ESRD in Steno. Conclusions/interpretation: This study supports the previously identified findings on the RGMA/MCTP2 region and suggests novel susceptibility loci for ESRD. This highlights the importance of applying complementary statistical methods to detect novel genetic variants in diabetic nephropathy and, in general, in complex diseases.

Tunnel spoil classification and applicability of lime addition in weak formations for muck reuse

Tunnel construction planning requires careful consideration of the spoil management part, as this involves environmental, economic and legal requirements. In this paper a methodological approach that considers the interaction between technical and geological factors in determining the features of the resulting muck is proposed. This gives indications about the required treatments as well as laboratory and field characterisation tests to be performed to assess muck recovery alternatives. While this reuse is an opportunity for excavations in good quality homogeneous grounds (e.g. granitic mass), it is critical for complex formation. This approach has been validated, at present, for three different geo-materials resulting from a tunnel excavation carried out with a large diameter Earth Pressure Balance Shield (EPB) through a complex geological succession. Physical parameters and technological features of the three materials have been assessed, according to their valorisation potential, for defining re-utilisation patterns. The methodology proved to be effective and the laboratory tests carried out on the three materials allowed the suitability and treatment effectiveness for each muck recovery strategy to be defined. © 2014 Elsevier Ltd.

The distribution of COPD in UK general practice using the new GOLD classification

The new Global Initiative for Chronic Obstructive Lung Disease (GOLD) 2011 document recommends a combined assessment of chronic obstructive pulmonary disease (COPD) based on current symptoms and future risk.

A large database of primary-care COPD patients across the UK was used to determine COPD distribution and characteristics according to the new GOLD classification. 80 general practices provided patients with a Read code diagnosis of COPD. Electronic and hand searches of patient medical records were undertaken, optimising data capture.

Data for 9219 COPD patients were collected. For the 6283 patients with both forced expiratory volume in 1 s (FEV1) and modified Medical Research Council scores (mean¡SD age 69.2¡10.6 years, body mass index 27.3¡6.2 kg?m-2), GOLD 2011 group distributions were: A (low risk and fewer symptoms) 36.1%, B (low risk and more symptoms) 19.1%, C (high risk and fewer symptoms) 19.6% and D (high risk and more symptoms) 25.3%. This is in contrast with GOLD 2007 stage classification: I (mild) 17.1%, II (moderate) 52.2%, III (severe) 25.5% and IV (very severe) 5.2%. 20% of patients with FEV1 o50% predicted had more than two exacerbations in the previous 12 months. 70% of patients with FEV1 ,50% pred had fewer than two exacerbations in the previous 12 months.

This database, representative of UK primary-care COPD patients, identified greater proportions of patients in the mildest and most severe categories upon comparing 2011 versus 2007 GOLD classifications. Discordance between airflow limitation severity and exacerbation risk was observed.

Online Thévenin Equivalent Determination Considering System Side Changes and Measurement Errors

This paper presents a new method for online determination of the Thèvenin equivalent parameters of a power system at a given node using the local PMU measurements at that node. The method takes into account the measurement errors and the changes in the system side. An analysis of the effects of changes in system side is carried out on a simple two-bus system to gain an insight of the effect of system side changes on the estimated Thévenin equivalent parameters. The proposed method uses voltage and current magnitudes as well as active and reactive powers; thus avoiding the effect of phase angle drift of the PMU and the need to synchronize measurements at different instances to the same reference. Applying the method to the IEEE 30-bus test system has shown its ability to correctly determine the Thévenin equivalent even in the presence of measurement errors and/or system side changes.

Prediction of integral type failures in semiconductor manufacturing through classification methods

Smart management of maintenances has become fundamental in manufacturing environments in order to decrease downtime and costs associated with failures. Predictive Maintenance (PdM) systems based on Machine Learning (ML) techniques have the possibility with low added costs of drastically decrease failures-related expenses; given the increase of availability of data and capabilities of ML tools, PdM systems are becoming really popular, especially in semiconductor manufacturing. A PdM module based on Classification methods is presented here for the prediction of integral type faults that are related to machine usage and stress of equipment parts. The module has been applied to an important class of semiconductor processes, ion-implantation, for the prediction of ion-source tungsten filament breaks. The PdM has been tested on a real production dataset. © 2013 IEEE.