Classification of malware based on string and function feature selection

Anti-malware software producers are continually challenged to identify and counter new malware as it is released into the wild. A dramatic increase in malware production in recent years has rendered the conventional method of manually determining a signature for each new malware sample untenable. This paper presents a scalable, automated approach for detecting and classifying malware by using pattern recognition algorithms and statistical methods at various stages of the malware analysis life cycle. Our framework combines the static features of function length and printable string information extracted from malware samples into a single test which gives classification results better than those achieved by using either feature individually. In our testing we input feature information from close to 1400 unpacked malware samples to a number of different classification algorithms. Using k-fold cross validation on the malware, which includes Trojans and viruses, along with 151 clean files, we achieve an overall classification accuracy of over 98%.

Damage identification of steel beams using local and global methods

Structural condition monitoring methods can be generally classified as local and global. While the global method needs only a small number of sensors to measure the low-frequency structural vibration properties, the acquired information is often not sufficiently sensitive to minor damages in a structure. Local methods, on the other hand, could be very sensitive to minor damages but their detection range is usually small. To overcome the drawbacks and take advantage of both methods, an integrated condition monitoring system has been recently developed for structural damage detection, which combines guided wave and structural vibration tests. This study aims at finding a viable damage identification method for steel structures by using this system. First, a spectral element modelling method is developed, which can simulate both wave propagation and structural vibration properties. Then the model is used in updating analysis to identify crack damage. Extensive numerical simulations and model updating works are conducted. The experimental and numerical results suggest that simply combining the objective functions cannot provide better structural damage identification. A two-stage damage identification scheme is more suitable for identifying damage in steel beams.

Using feature selection for intrusion detection system

A good intrusion system gives an accurate and efficient classification results. This ability is an essential functionality to build an intrusion detection system. In this paper, we focused on using various training functions with feature selection to achieve high accurate results. The data we used in our experiments are NSL-KDD. However, the training and testing time to build the model is very high. To address this, we proposed feature selection based on information gain, which can detect several attack types with high accurate result and low false rate. Moreover, we executed experiments to category each of the five classes (probe, denial of service (DoS), user to super-user (U2R), and remote to local (R2L), normal). Our proposed outperform other state-of-art methods.

Ground-based survey methods both overestimate and underestimate the abundance of suitable tree-cavities for the endangered Swift Parrot

Most cavity-dependent species select tree-cavities with a narrow range of characteristics so that only a small subset of available cavities may be suitable for any species. Most surveys for tree-cavities are done from the ground using binoculars to reduce effort, but this technique is prone to error. These errors are likely to contribute to the loss of the cavity resource when used to inform conservation efforts for cavity-dependent species. The Swift Parrot (Lathamus discolor) is an endangered migratory bird threatened by ongoing removal of cavity-bearing trees by production forestry. We climbed trees with cavities used for nesting by Swift Parrots and determined that they prefer cavities with small entrances, deep chambers and wide floors. Such cavities are rare and occur in large trees that support higher than average numbers of tree-cavities. Importantly, cavities used by Swift Parrots were also likely to be both overestimated and underestimated using ground-based surveys, and without calibration by climbing, the size and direction of survey error could not be determined. We conclude that the most effective way to gain detailed information about the characteristics and abundance of tree-cavities is to climb a representative sample of trees to calibrate ground-based methods for a specific ecosystem.

A new energy efficient cluster-head and backup selection scheme in WSN

Despite significant advancements in wireless sensor networks (WSNs), energy conservation remains one of the most important research challenges. Proper organization of nodes (clustering) is one of the major techniques to expand the lifespan of the whole network through aggregating data at the cluster head. The cluster head is the backbone of the entire cluster. That means if a cluster head fails to accomplish its function, the received and collected data by cluster head can be lost. Moreover, the energy consumption following direct communications from sources to base stations will be increased. In this paper, we propose a type-2 fuzzy based self-configurable cluster head selection (SCCH) approach to not only consider the selection criterion of the cluster head but also present the cluster backup approach. Thus, in case of cluster failure, the system still works in an efficient way. The novelty of this protocol is the ability of handling communication uncertainty, which is an inherent operational aspect of sensor networks. The experiment results indicate SCCH performs better than other recently developed methods.

A novel aggregate gene selection method for microarray data classification

This paper introduces a novel method for gene selection based on a modification of analytic hierarchy process (AHP). The modified AHP (MAHP) is able to deal with quantitative factors that are statistics of five individual gene ranking methods: two-sample t-test, entropy test, receiver operating characteristic curve, Wilcoxon test, and signal to noise ratio. The most prominent discriminant genes serve as inputs to a range of classifiers including linear discriminant analysis, k-nearest neighbors, probabilistic neural network, support vector machine, and multilayer perceptron. Gene subsets selected by MAHP are compared with those of four competing approaches: information gain, symmetrical uncertainty, Bhattacharyya distance and ReliefF. Four benchmark microarray datasets: diffuse large B-cell lymphoma, leukemia cancer, prostate and colon are utilized for experiments. As the number of samples in microarray data datasets are limited, the leave one out cross validation strategy is applied rather than the traditional cross validation. Experimental results demonstrate the significant dominance of the proposed MAHP against the competing methods in terms of both accuracy and stability. With a benefit of inexpensive computational cost, MAHP is useful for cancer diagnosis using DNA gene expression profiles in the real clinical practice.

Hierarchical gene selection and genetic fuzzy system for cancer microarray data classification

This paper introduces a novel approach to gene selection based on a substantial modification of analytic hierarchy process (AHP). The modified AHP systematically integrates outcomes of individual filter methods to select the most informative genes for microarray classification. Five individual ranking methods including t-test, entropy, receiver operating characteristic (ROC) curve, Wilcoxon and signal to noise ratio are employed to rank genes. These ranked genes are then considered as inputs for the modified AHP. Additionally, a method that uses fuzzy standard additive model (FSAM) for cancer classification based on genes selected by AHP is also proposed in this paper. Traditional FSAM learning is a hybrid process comprising unsupervised structure learning and supervised parameter tuning. Genetic algorithm (GA) is incorporated in-between unsupervised and supervised training to optimize the number of fuzzy rules. The integration of GA enables FSAM to deal with the high-dimensional-low-sample nature of microarray data and thus enhance the efficiency of the classification. Experiments are carried out on numerous microarray datasets. Results demonstrate the performance dominance of the AHP-based gene selection against the single ranking methods. Furthermore, the combination of AHP-FSAM shows a great accuracy in microarray data classification compared to various competing classifiers. The proposed approach therefore is useful for medical practitioners and clinicians as a decision support system that can be implemented in the real medical practice.

Dynamic cloud service selection using an adaptive learning mechanism in multi-cloud computing

Cloud service selection in a multi-cloud computing environment is receiving more and more attentions. There is an abundance of emerging cloud service resources that makes it hard for users to select the better services for their applications in a changing multi-cloud environment, especially for online real time applications. To assist users to efficiently select their preferred cloud services, a cloud service selection model adopting the cloud service brokers is given, and based on this model, a dynamic cloud service selection strategy named DCS is put forward. In the process of selecting services, each cloud service broker manages some clustered cloud services, and performs the DCS strategy whose core is an adaptive learning mechanism that comprises the incentive, forgetting and degenerate functions. The mechanism is devised to dynamically optimize the cloud service selection and to return the best service result to the user. Correspondingly, a set of dynamic cloud service selection algorithms are presented in this paper to implement our mechanism. The results of the simulation experiments show that our strategy has better overall performance and efficiency in acquiring high quality service solutions at a lower computing cost than existing relevant approaches.

Impact of automated dispensing cabinets on medication selection and preparation error rates in an emergency department: a prospective and direct observational before-and-after study

RATIONALE, AIMS AND OBJECTIVES: The implementation of automated dispensing cabinets (ADCs) in healthcare facilities appears to be increasing, in particular within Australian hospital emergency departments (EDs). While the investment in ADCs is on the increase, no studies have specifically investigated the impacts of ADCs on medication selection and preparation error rates in EDs. Our aim was to assess the impact of ADCs on medication selection and preparation error rates in an ED of a tertiary teaching hospital. METHODS: Pre intervention and post intervention study involving direct observations of nurses completing medication selection and preparation activities before and after the implementation of ADCs in the original and new emergency departments within a 377-bed tertiary teaching hospital in Australia. Medication selection and preparation error rates were calculated and compared between these two periods. Secondary end points included the impact on medication error type and severity. RESULTS: A total of 2087 medication selection and preparations were observed among 808 patients pre and post intervention. Implementation of ADCs in the new ED resulted in a 64.7% (1.96% versus 0.69%, respectively, P = 0.017) reduction in medication selection and preparation errors. All medication error types were reduced in the post intervention study period. There was an insignificant impact on medication error severity as all errors detected were categorised as minor. CONCLUSION: The implementation of ADCs could reduce medication selection and preparation errors and improve medication safety in an ED setting.

A systematic evaluation of field-based screening methods for the assessment of anterior cruciate ligament (ACL) injury risk

BACKGROUND: Laboratory-based measures provide an accurate method to identify risk factors for anterior cruciate ligament (ACL) injury; however, these methods are generally prohibitive to the wider community. Screening methods that can be completed in a field or clinical setting may be more applicable for wider community use. Examination of field-based screening methods for ACL injury risk can aid in identifying the most applicable method(s) for use in these settings. OBJECTIVE: The objective of this systematic review was to evaluate and compare field-based screening methods for ACL injury risk to determine their efficacy of use in wider community settings. DATA SOURCES: An electronic database search was conducted on the SPORTDiscus™, MEDLINE, AMED and CINAHL databases (January 1990-July 2015) using a combination of relevant keywords. A secondary search of the same databases, using relevant keywords from identified screening methods, was also undertaken. STUDY SELECTION: Studies identified as potentially relevant were independently examined by two reviewers for inclusion. Where consensus could not be reached, a third reviewer was consulted. Original research articles that examined screening methods for ACL injury risk that could be undertaken outside of a laboratory setting were included for review. STUDY APPRAISAL AND SYNTHESIS METHODS: Two reviewers independently assessed the quality of included studies. Included studies were categorized according to the screening method they examined. A description of each screening method, and data pertaining to the ability to prospectively identify ACL injuries, validity and reliability, recommendations for identifying 'at-risk' athletes, equipment and training required to complete screening, time taken to screen athletes, and applicability of the screening method across sports and athletes were extracted from relevant studies. RESULTS: Of 1077 citations from the initial search, a total of 25 articles were identified as potentially relevant, with 12 meeting all inclusion/exclusion criteria. From the secondary search, eight further studies met all criteria, resulting in 20 studies being included for review. Five ACL-screening methods-the Landing Error Scoring System (LESS), Clinic-Based Algorithm, Observational Screening of Dynamic Knee Valgus (OSDKV), 2D-Cam Method, and Tuck Jump Assessment-were identified. There was limited evidence supporting the use of field-based screening methods in predicting ACL injuries across a range of populations. Differences relating to the equipment and time required to complete screening methods were identified. LIMITATIONS: Only screening methods for ACL injury risk were included for review. Field-based screening methods developed for lower-limb injury risk in general may also incorporate, and be useful in, screening for ACL injury risk. CONCLUSIONS: Limited studies were available relating to the OSDKV and 2D-Cam Method. The LESS showed predictive validity in identifying ACL injuries, however only in a youth athlete population. The LESS also appears practical for community-wide use due to the minimal equipment and set-up/analysis time required. The Clinic-Based Algorithm may have predictive value for ACL injury risk as it identifies athletes who exhibit high frontal plane knee loads during a landing task, but requires extensive additional equipment and time, which may limit its application to wider community settings.

Comparison of cell disruption methods for improving lipid extraction from thraustochytrid strains

Lipid extraction is an integral part of biodiesel production, as it facilitates the release of fatty acids from algal cells. To utilise thraustochytrids as a potential source for lipid production. We evaluated the extraction efficiency of various solvents and solvent combinations for lipid extraction from Schizochytrium sp. S31 and Thraustochytrium sp. AMCQS5-5. The maximum lipid extraction yield was 22% using a chloroform:methanol ratio of 2:1. We compared various cell disruption methods to improve lipid extraction yields, including grinding with liquid nitrogen, bead vortexing, osmotic shock, water bath, sonication and shake mill. The highest lipid extraction yields were obtained using osmotic shock and 48.7% from Schizochytrium sp. S31 and 29.1% from Thraustochytrium sp. AMCQS5-5. Saturated and monounsaturated fatty acid contents were more than 60% in Schizochytrium sp. S31 which suggests their suitability for biodiesel production.

Stable feature selection with support vector machines

The support vector machine (SVM) is a popular method for classification, well known for finding the maximum-margin hyperplane. Combining SVM with l1-norm penalty further enables it to simultaneously perform feature selection and margin maximization within a single framework. However, l1-norm SVM shows instability in selecting features in presence of correlated features. We propose a new method to increase the stability of l1-norm SVM by encouraging similarities between feature weights based on feature correlations, which is captured via a feature covariance matrix. Our proposed method can capture both positive and negative correlations between features. We formulate the model as a convex optimization problem and propose a solution based on alternating minimization. Using both synthetic and real-world datasets, we show that our model achieves better stability and classification accuracy compared to several state-of-the-art regularized classification methods.

Cost-effectiveness of recruitment methods in a population-based epidemiological study: the Melbourne Visual Impairment Project

The cost-effectiveness of five recruitment methods was evaluated to determine the best method of encouraging eligible persons to participate in the Melbourne Visual Impairment Project (a population-based epidemiological study). The evaluation was divided into two phases. Phase 1 included one of two types of initial contact, by direct personal contact or by telephone. Phase 2 involved recruiting residents after an attempt had been made by either the telephone or the doorstep approach, and included a second attempt by a field interviewer, subsequent attempts by senior field staff, and finally, financial incentives. The cost-effectiveness of each method was determined by dividing the approach's cost by the effectiveness ratio. We identified 269 eligible households with 356 eligible residents. An 89 per cent response rate was achieved at the examination centre, comprising 61 per cent from Phase 1 and 28 per cent from Phase 2. Although both recruitment methods in Phase 1 were equally cost-effective, there was a significant difference in the effectiveness of each method in actually recruiting residents. The doorstep method was more costly per attender but was far more effective at 76 per cent recruitment than the telephone method at 47 per cent (P < 0.001). We have demonstrated a practical two-stage approach (the doorstep method in Phase 1 and follow-up strategies in Phase 2) to population-based recruitment involving the middle to elderly age group that should be relevant to many epidemiological studies.

Recruitment methods for community-based screening for diabetic retinopathy

Regular screening of all people with diabetes is the most efficient and cost-effective way to detect early stages of diabetic retinopathy so that laser treatment can be performed at the optimal time. A major aim of the Program for the Early Detection of Diabetic Retinopathy was to increase compliance with guidelines for screening for diabetic retinopathy. This community-based screening program used non-mydriatic retinal photography and was initiated in four areas of Victoria, Australia from 1996-1998. Recruitment strategies included targeted mail-outs, provision of the program brochure in English and the main languages spoken in the areas and media promotion in ethnic newspapers and on ethnic radio stations. In Victoria, only 55% of the population with diabetes currently access eye care services at the recommended intervals. This program was able to increase compliance with guidelines to 70% among people with diabetes that had not had a recent eye examination. A total of 1,197 people with diabetes were screened for diabetic retinopathy. Of the 1,197 people who were screened, 620 (15% of the estimated number of people with diabetes) had not had their eyes examined in the past two years. This pilot study identified strategies to encourage people with diabetes to have their eyes examined at the recommended intervals.