Clonewise - detecting package-level clones using machine learning

Developers sometimes maintain an internal copy of another software or fork development of an existing project. This practice can lead to software vulnerabilities when the embedded code is not kept up to date with upstream sources. We propose an automated solution to identify clones of packages without any prior knowledge of these relationships. We then correlate clones with vulnerability information to identify outstanding security problems. This approach motivates software maintainers to avoid using cloned packages and link against system wide libraries. We propose over 30 novel features that enable us to use to use pattern classification to accurately identify package-level clones. To our knowledge, we are the first to consider clone detection as a classification problem. Our results show our system, Clonewise, compares well to manually tracked databases. Based on our work, over 30 unknown package clones and vulnerabilities have been identified and patched.

Investigating machine learning techniques for detection of depression using structural MRI volumetric features

Structural MRI offers anatomical details and high sensitivity to pathological changes. It can demonstrate certain patterns of brain changes present at a structural level. Research to date has shown that volumetric analysis of brain regions has importance in depression detection. However, such analysis has had very minimal use in depression detection studies at individual level. Optimally combining various brain volumetric features/attributes, and summarizing the data into a distinctive set of variables remain difficult. This study investigates machine learning algorithms that automatically identify relevant data attributes for depression detection. Different machine learning techniques are studied for depression classification based on attributes extracted from structural MRI (sMRI) data. The attributes include volume calculated from whole brain, white matter, grey matter and hippocampus. Attributes subset selection is performed aiming to remove redundant attributes using three filtering methods and one hybrid method, in combination with ranker search algorithms. The highest average classification accuracy, obtained by using a combination of both SVM-EM and IG-Random Tree algorithms, is 85.23%. The classification approach implemented in this study can achieve higher accuracy than most reported studies using sMRI data, specifically for detection of depression.

Rewind, repeat: TV’s fame machine is oh-so retro

As much as the contemporary talent show appears to be different, there are qualities that relate to earlier versions of televised talent contests internationally and domestically. This article explores how the past iterations inform the present and its production of an internal - almost studio system - of fame.

A preliminary study on machinability assessment of nanobainite steel

The demand for high strength materials and improvements in heat treatment techniques has given rise to this new form of high strength steel known as nanobainite steel. The production of nanobainite steel involves slow isothermal holding of austenitic steel around 200oC for 10 days, in order to obtain a carbon enriched austenite and cooling to room temperature using austempering. The microstructure of nanobainite steel is dual phase consisting of alternate layers of bainitic ferrite and austenite. The experimental design consists of face milling under 12 combination of Depth of Cut (DoC)-1, 2 and 3mm; cutting speed-100 and 150m/min; constant feed- 0.15mm/rev and coolant on/off. The machinability of the material is assessed by means of analysis such as metallography and cutting force analysis. The results obtained are used to assess the most favorable condition to machine this new variety of steel. Future work involves study on phase transformation by quantifying the microstructural phase before and after milling using XRD.

Review of trust and machine ethics research: towards a bio-inspired computational model of ethical trust (CMET)

Recent advances in the fields of robotics, cyborg development, moral psychology, trust, multi agent-based systems and socionics have raised the need for a better understanding of ethics, moral reasoning, judgment and decision-making within the system of man and machines. Here we seek to understand key research questions concerning the interplay of ethical trust at the individual level and the social moral norms at the collective end. We review salient works in the fields of trust and machine ethics research, underscore the importance and the need for a deeper understanding of ethical trust at the individual level and the development of collective social moral norms. Drawing upon the recent findings from neural sciences on mirror-neuron system (MNS) and social cognition, we present a bio-inspired Computational Model of Ethical Trust (CMET) to allow investigations of the interplay of ethical trust and social moral norms.

Voltage stability analysis with optimum size and location based synchronous machine DG

Power loss of a distribution system can be reduced significantly by using optimum size and location of distributed generation (DG). Proper allocation of DG with appropriate size maximizes overall system efficiency. Moreover it improves the reliability and voltage profile of the distribution system. In this paper, IEEE 123 node test feeder has been considered to determine the optimum size and location of a synchronous machine based DG for loss reduction of the system. This paper also investigates the steady-state and dynamic voltage profile of that three phase unbalance distribution network in presence of DG with optimum size. This analysis shows that optimum size of DG at proper location minimizes the power loss as well as improves the dynamic voltage profile of the distribution system.

Solving DC programs using the cutting angle method

In this paper, we propose a new algorithm for global minimization of functions represented as a difference of two convex functions. The proposed method is a derivative free method and it is designed by adapting the extended cutting angle method. We present preliminary results of numerical experiments using test problems with difference of convex objective functions and box-constraints. We also compare the proposed algorithm with a classical one that uses prismatical subdivisions. © 2014 Springer Science+Business Media New York.