N. I. Senaratna (2006). Automatic Music Composition with AMCTIES. Proceedings of the 8th International Information Technology Conference (IITC2006), Colombo, Sri Lanka.
Abstract: A wide range of approaches and techniques have been explored in attempts to build Automatic music composition (AMC) systems. However, most attempts have tended to use a single, centralized technique for the entire AMC process. This has many drawbacks. This paper proposes a solution to these drawbacks in the form of a tree-like structure made up of several interacting emergent systems. The structure which will be refered to as "A Tree of Interacting Emergent Systems" or TIES, is a context-independent framework, applicable to many applications, including AMC. The latter is demonstrated by using TIES to implement the application AMCTIES - An application capable of "Automatic Music Composition using a Tree of Interacting Emergent Systems". This paper would be of much interest to those in both the computer as well as music fields. (Download Full Paper PDF)
R. I. Senaratna and N. I. Senaratna (2006). Minimizing life cycle costs of industrial LV distribution networks. Proceedings of the 13th Annual Conference of the IET Sri Lanka Network, Colombo, Sri Lanka.
Abstract: Sizing of low voltage cables and positioning of distribution
switchgear, in industrial and commercial end-user environments have been, in
the main, based on installation environment, current carrying capacity and
voltage drop considerations for cable sizing, and, operational convenience and
aesthetic considerations for switchgear positioning. Except indirectly (as in
the case of specifying the smallest cable with the appropriate current carrying
capacity), cost considerations have rarely been factored into this decision
process.
Perhaps, the first attempt in this direction in Sri Lanka was a paper presented
by one of the authors at the First Annual IEE Sri Lanka Conference (1994) which
demonstrated how distribution switchgear could be positioned in a
cost-effective manner in three phase wiring networks typically found in
industrial environments. However, this did not take into account voltage drop
limits, nor energy losses in the wiring network over the life of the
installation.
Ideally, optimal distribution switchgear locations and cable sizes should
result in minimizing the sum of cable costs and the energy-loss costs subject
to voltage drop and current carrying capacity constraints. The innate
non-linearities in numerical relationships between factors and other
non-continuous aspects of the underlying data make a solution using
conventional methods difficult (if not impossible).
This paper proposes a Simulated Annealing based technique for finding
distribution switchgear locations and cable sizes that minimize ‘life-cycle’
costs of a part of a three phase wiring network. Simulated Annealing is a
variation of the “Hill Climbing” Algorithm and has, in the past, proved quite
successful in solving similar problems.
By applying the technique to an example environment, we demonstrate that it
results in significant cost reduction. (Download Full
Paper PDF)
My Final Year Research Project Dissertation: Automatic Music Composition using a Tree of Interacting Emergent Systems
Abstract: Automatic music composition (or AMC) is a “hot field” in computer science. It has much commercial potential and is of much interest to scientists and industrialists alike. A wide range of approaches and techniques have been explored in attempts to build AMC systems. Of these, emergent-computing techniques have proved very promising. However, most attempts have tended to use a single, centralized emergent technique for the entire AMC process. This has many drawbacks.The author proposes a solution to these drawbacks in the form of a tree-like structure made up of several interacting emergent systems. The author calls this “A Tree of Interacting Emergent Systems” or TIES. TIES is a context-independent framework, applicable to many applications, including AMC. The author demonstrates the latter by using it to implement the application AMCTIES (An application capable of Automatic Music Composition using a Tree of Interacting Emergent Systems).
AMCTIES defines a TIES framework for musical composition. Musical entities are represented as emergent entities. These are generated by emergent systems known as generators. Low-level emergent entities are used to generate high-level emergent entities, and hence form a tree of emergent systems. For example, Motifs and Rhythm are used to generate Phrases. TIES allows for complex interactions between its emergent systems and implements several additional design components in order to facilitate this. The TIES framework is independent of the implementation of the actual generators. The idea is to design a scalable, flexible and robust framework that will maximize practical results.
To demonstrate how TIES can be used for AMC, we implement several generator emergent systems. These use Fractals, Cellular Automata and Genetic Algorithms. The particular implementations have been optimized specifically for AMC. AMCTIES is delivered as a set of libraries. These have been developed on the Microsoft .NET framework. The outputs produced by AMCTIES are in the form of MIDI files. The libraries can be used to design a host of applications.
A set of music files generated by AMCTIES was subjected to the scrutiny of several experts in the music field. This scrutinization process was designed to validate the generation of each of the component musical entities. Expert responses indicate that AMCTIES can indeed generate music with a reasonable level of creativity and novelty.
This project would be of much interest to those in both the computer as well as music fields. (Download Full Paper)
Literature Survey: Genetic Algorithms: The Crossover-Mutation Debate
Abstract: Crossover and mutation are two of the most important genetic operators found in genetic algorithms. There has been much debate as to which of these is practically and theoretically more effective. This literature review highlights the principal milestones of this debate. The conclusion we reach is that there is no evidence to show that either operator is better than the other, and that both operators have their own useful qualities. We also highlight some important new trends that we think might influence the debate in the future. (Download Full Paper PDF)
IITC 2006
Dr. D. N. Ranasinghe's Webpage