Nature-inspired methods for hardware and software system design and information processing

硬件和软件系统设计和信息处理的自然启发方法

• 批准号: 156900-2013
• 负责人: Boukadoum, AMounir
• 金额: $ 1.75万
• 依托单位: Université du Québec à Montréal
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=637094
• 关键词: Nature; inspired; methods; hardware; software

My research investigates the use of knowledge engineering, heuristics and nature-inspired computation for system design and analysis. Its basic postulate is that most system design, modeling, and analysis problems can be represented as classification or optimization problems for which a natural equivalent exist and have been solved over the course of evolution, or for which innovative search algorithms can be developed using heuristic search and/or data mining. In doing so, I seek alternative approaches to existing formal techniques when they are inapplicable or too slow. In the past few years, my research included the development and application of intelligent algorithms for data analysis and system design using neural networks, particle swarm optimization and data mining. This led to several original contributions at the algorithmic and applicative levels, namely in instrumentation, embedded software design, computer aided design tools, and medical image processing, In the next five years, I intend to move on to the area of design automation by investigating the development of a reuse-based framework for electronic circuit design that either recalls complete stored designs or finds and integrates fragments from different example designs in the database. I will validate my findings automated RF and microwave circuit design.I expect my research not only to advance the state of the art in intelligent system design and signal processing, and on developing efficient tools for the computer aided design of hardware and software systems, but also to contribute significant advances to rapid system prototyping, hence helping to shorten the design cycle of complex designs and reduce development cost.

我的研究调查了知识工程，启发式方法和自然风格的计算用于系统设计和分析。它的基本假设是，大多数系统设计，建模和分析问题可以表示为存在自然等效物并在进化过程中解决的分类或优化问题，或者可以使用启发式搜索和/或数据挖掘来为其开发创新的搜索算法。这样一来，我寻求替代方法，以实现现有的正式技术，当它们不适用或太慢。在过去的几年中，我的研究包括使用神经网络，粒子群优化和数据挖掘的智能算法的开发和应用。这导致了算法和应用级别的几项原始贡献，即在仪器，嵌入式软件设计，计算机辅助设计工具和医疗图像处理中，在接下来的五年中，我打算通过调查基于重复使用的电子电路设计的重复使用框架，以回想完整的示例指定和集成图表，并在不同的范围内进行了重复使用的框架设计，从而进行了设计自动化领域。我将验证我的发现自动化RF和微波电路设计。我希望我的研究不仅能够推进智能系统设计和信号处理中的最新技术，并为计算机辅助设计的硬件和软件系统开发有效的工具，还可以为快速系统的原型设计做出重大进步，从而有助于缩短复杂设计的设计周期，并降低了复杂设计的设计周期。