Microphone identification using one-class classification approach

Rapid growth of technical developments has created huge challenges for microphone forensics - a subcategory of audio forensic science, because of the availability of numerous digital recording devices and massive amount of recording data. Demand for fast and efficient methods to assure integrity and authenticity of information is becoming more and more important in criminal investigation nowadays. Machine learning has emerged as an important technique to support audio analysis processes of microphone forensic practitioners. However, its application to real life situations using supervised learning is still facing great challenges due to expensiveness in collecting data and updating system. In this paper, we introduce a new machine learning approach which is called One-class Classification (OCC) to be applied to microphone forensics; we demonstrate its capability on a corpus of audio samples collected from several microphones. Research results and analysis indicate that OCC has the potential to benefit microphone forensic practitioners in developing new tools and techniques for effective and efficient analysis.

Identifying microphone from noisy recordings by using representative instance one class-classification approach

Rapid growth of technical developments has created huge challenges for microphone forensics - a sub-category of audio forensic science, because of the availability of numerous digital recording devices and massive amount of recording data. Demand for fast and efficient methods to assure integrity and authenticity of information is becoming more and more important in criminal investigation nowadays. Machine learning has emerged as an important technique to support audio analysis processes of microphone forensic practitioners. However, its application to real life situations using supervised learning is still facing great challenges due to expensiveness in collecting data and updating system. In this paper, we introduce a new machine learning approach which is called One-class Classification (OCC) to be applied to microphone forensics; we demonstrate its capability on a corpus of audio samples collected from several microphones. In addition, we propose a representative instance classification framework (RICF) that can effectively improve performance of OCC algorithms for recording signal with noise. Experiment results and analysis indicate that OCC has the potential to benefit microphone forensic practitioners in developing new tools and techniques for effective and efficient analysis.

Towards a business analytics capability maturity model

Business analytics (BA) systems are an important strategic investment for many organisations and can potentially contribute significantly to firm performance. Establishing strong BA capabilities is currently one of the major concerns of chief information officers. This research project aims to develop a BA capability maturity model (BACMM). The BACMM will help organisations to scope and evaluate their BA initiatives. This research-in-progress paper describes the current BACMM, relates it to existing capability maturity models and explains its theoretical base. It also discusses the design science research approach being used to develop the BACMM and provides details of further work within the research project. Finally, the paper concludes with a discussion of how the BACMM might be used in practice.

Leading WIL: A distributed leadership approach to enhance work integrated learning : final report 2014

Work Integrated Learning (WIL) provides rich, relevant learning through a partnership between universities and employers. Through a collaborative approach to building knowledge, the capability and capacity of experienced WIL leaders in the university and orkplace will be enhanced for improved student outcomes. Having established how and where WIL leadership is situated, the project will identify the critical challenges to WIL leadership capabilities and structures. Through institutionally-based Master Classes that model and employ a distributed learning approach, through national Communities of Practice and a WIL Leadership Summit, a framework and guidelines to support WIL leadership capacity building nationally will be developed, trialled and validated. The project will draw upon expertise and experiences of staff from five Australian universities, each with a demonstrated strong WIL commitment. The distributive leadership approach to WIL will be developed and tested within employer-based individual disciplines. The framework and guidelines will be sustained nationally through the key WIL professional association, the Australian Collaborative Education Network.

A supply chain approach to meat goat industry development

The Victorian goat meat industry is a significant contributor to export earnings, which is derived largely from the harvest of feral goats. The potential for exports of farmed goat meat into Asian product markets is being developed in a supply chain approach with producers, processors, exporters and Asian importers. Producers have been networked in four locations to improve supply capability and participate in production and economic benchmarking. In the absence of an existing market for premium farmed goat meat, a larger group of producers are cooperating with a marketer to develop a niche market in the Asian food service sector. This presents a challenge to the group in developing commercial relationships and playing a role in the marketing of their goat meat.

On addressing the imbalance problem : A correlated KNN approach for network traffic classification

With the arrival of big data era, the Internet traffic is growing exponentially. A wide variety of applications arise on the Internet and traffic classification is introduced to help people manage the massive applications on the Internet for security monitoring and quality of service purposes. A large number of Machine Learning (ML) algorithms are introduced to deal with traffic classification. A significant challenge to the classification performance comes from imbalanced distribution of data in traffic classification system. In this paper, we proposed an Optimised Distance-based Nearest Neighbor (ODNN), which has the capability of improving the classification performance of imbalanced traffic data. We analyzed the proposed ODNN approach and its performance benefit from both theoretical and empirical perspectives. A large number of experiments were implemented on the real-world traffic dataset. The results show that the performance of “small classes” can be improved significantly even only with small number of training data and the performance of “large classes” remains stable.

Refined Jensen-based inequality approach to stability analysis of time-delay systems

© 2015 The Institution of Engineering and Technology. In this study, the authors derive some new refined Jensen-based inequalities, which encompass both the Jensen inequality and its most recent improvement based on the Wirtinger integral inequality. The potential capability of this approach is demonstrated through applications to stability analysis of time-delay systems. More precisely, by using the newly derived inequalities, they establish new stability criteria for two classes of time-delay systems, namely discrete and distributed constant delays systems and interval time-varying delay systems. The resulting stability conditions are derived in terms of linear matrix inequalities, which can be efficiently solved by various convex optimisation algorithms. Numerical examples are given to show the effectiveness and least conservativeness of the results obtained in this study.

Synthesis of a porous sheet-like V₂O₅-CNT nanocomposite using an ice-templating 'bricks-and-mortar' assembly approach as a high-capacity, long cyclelife cathode material for lithium-ion batteries

Tailoring the nanostructures of electrode materials is an effective way to enhance their electrochemical performance for energy storage. Herein, an ice-templating "bricks-and-mortar" assembly approach is reported to make ribbon-like V2O5 nanoparticles and CNTs integrated into a two-dimensional (2D) porous sheet-like V2O5-CNT nanocomposite. The obtained sheet-like V2O5-CNT nanocomposite possesses unique structural characteristics, including a hierarchical porous structure, 2D morphology, large specific surface area and internal conducting networks, which lead to superior electrochemical performances in terms of long-term cyclability and significantly enhanced rate capability when used as a cathode material for LIBs. The sheet-like V2O5-CNT nanocomposite can charge/discharge at high rates of 5C, 10C and 20C, with discharge capacities of approximately 240 mA h g-1, 180 mA h g-1, and 160 mA h g-1, respectively. It also retains 71% of the initial discharge capacity after 300 cycles at a high rate of 5C, with only 0.097% capacity loss per cycle. The rate capability and cycling performance of the sheet-like V2O5-CNT nanocomposite are significantly better than those of commercial V2O5 and most of the reported V2O5 nanocomposite.

Genotoxicity evaluation of chlorpyrifos: a gender related approach in regular toxicity testing

The oral intubation of chlorpyrifos, an extensively used organophosphate insecticide, was tested for its capability to induce in vivo genotoxic upshot in blood lymphocytes of 24 male and female Wistar rats using biomarker of genotoxicity. Rats were orally administered with daily doses 3 and 12 mg/kg body weight (BW) of chlorpyrifos (CPF). The blood lymphocytes were harvested after 7 and 14 days of treatment and subjected to bi-nucleus (BN), multi-nucleus (MN) and single cell gel electrophoresis (comet assay) to evaluate the extent of DNA damage. Other than BN and MN assay, damage to DNA was assessed through comet length, height, area, head diameter, head DNA percentage and tail DNA percentage along with tail movement. A significant boost was noticed in the frequency of BN cells formation after 12 mg/kg BW CPF treatment. However, the propensity to produce MN cells was significantly more (P ≤ 0.05) in males than that of females. Likewise, the frequency of comet formation, mean comet length, height and area were more (P ≤ 0.05) in males than females even with 12 mg/kgBW. Comet head DNA % and tail length remained non-significant. Olive movement also revealed a significant increase (P ≤ 0.05) in males than females. The study inferred that the CPF can induce DNA damage in both male and female subjects but more pronounced in the male individuals.

A transformation technique to estimate the process capability index for non-normal processes

Estimating the process capability index (PCI) for non-normal processes has been discussed by many researches. There are two basic approaches to estimating the PCI for non-normal processes. The first commonly used approach is to transform the non-normal data into normal data using transformation techniques and then use a conventional normal method to estimate the PCI for transformed data. This is a straightforward approach and is easy to deploy. The alternate approach is to use non-normal percentiles to calculate the PCI. The latter approach is not easy to implement and a deviation in estimating the distribution of the process may affect the efficacy of the estimated PCI. The aim of this paper is to estimate the PCI for non-normal processes using a transformation technique called root transformation. The efficacy of the proposed technique is assessed by conducting a simulation study using gamma, Weibull, and beta distributions. The root transformation technique is used to estimate the PCI for each set of simulated data. These results are then compared with the PCI obtained using exact percentiles and the Box-Cox method. Finally, a case study based on real-world data is presented.

Evaluation of process capability indices of linear profiles

Purpose: In profile monitoring, which is a growing research area in the field of statistical process control, the relationship between response and explanatory variables is monitored over time. The purpose of this paper is to focus on the process capability analysis of linear profiles. Process capability indices give a quick indication of the capability of a manufacturing process. Design/methodology/approach: In this paper, the proportion of the non-conformance criteria is employed to estimate process capability index. The paper has considered the cases where specification limits is constant or is a function of explanatory variable X. Moreover, cases where both equal and random design schemes in profile data acquisition is required (as the explanatory variable) is considered. Profiles with the assumption of deterministic design points are usually used in the calibration applications. However, there are other applications where design points within a profile would be i.i.d. random variables from a given distribution. Findings: Simulation studies using simple linear profile processes for both fixed and random explanatory variable with constant and functional specification limits are considered to assess the efficacy of the proposed method. Originality/value: There are many cases in industries such as semiconductor industries where quality characteristics are in form of profiles. There is no method in the literature to analyze process capability for theses processes, however recently quite a few methods have been presented in monitoring profiles. Proposed methods provide a framework for quality engineers and production engineers to evaluate and analyze capability of the profile processes. © Emerald Group Publishing Limited.

A fast malware feature selection approach using a hybrid of multi-linear and stepwise binary logistic regression

Malware replicates itself and produces offspring with the same characteristics but different signatures by using code obfuscation techniques. Current generation anti-virus engines employ a signature-template type detection approach where malware can easily evade existing signatures in the database. This reduces the capability of current anti-virus engines in detecting malware. In this paper, we propose a stepwise binary logistic regression-based dimensionality reduction techniques for malware detection using application program interface (API) call statistics. Finding the most significant malware feature using traditional wrapper-based approaches takes an exponential complexity of the dimension (m) of the dataset with a brute-force search strategies and order of (m-1) complexity with a backward elimination filter heuristics. The novelty of the proposed approach is that it finds the worst case computational complexity which is less than order of (m-1). The proposed approach uses multi-linear regression and the p-value of each individual API feature for selection of the most uncorrelated and significant features in order to reduce the dimensionality of the large malware data and to ensure the absence of multi-collinearity. The stepwise logistic regression approach is then employed to test the significance of the individual malware feature based on their corresponding Wald statistic and to construct the binary decision the model. When the selected most significant APIs are used in a decision rule generation systems, this approach not only reduces the tree size but also improves classification performance. Exhaustive experiments on a large malware data set show that the proposed approach clearly exceeds the existing standard decision rule, support vector machine-based template approach with complete data and provides a better statistical fitness.