{"title":"Fitness estimations for evolutionary antenna design","authors":"L. Zinchenko, S. Sorokin","doi":"10.1109/EH.2003.1217661","DOIUrl":"https://doi.org/10.1109/EH.2003.1217661","url":null,"abstract":"Evolutionary design is effective for many applications. However, a choice of the fitness function is often intuitive. In this paper, an effective approach for a comparison of fitness function properties, which uses an estimation of fitness function landscape ruggedness, is described. Penalty coefficients define the importance of each parameter for design goal and change the difficulty of the fitness function landscape significantly. A reasonable choice of objectives and penalty coefficients allows us to reduce the computational efforts because of the smoother landscape of the fitness functions. The effectiveness of the approach is illustrated for fitness functions that are used for evolutionary antenna design.","PeriodicalId":134823,"journal":{"name":"NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings.","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134403784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Self-protection maintains diversity of artificial self-replicators evolving in cellular automata","authors":"Hiroki Sayama","doi":"10.1109/EH.2003.1217673","DOIUrl":"https://doi.org/10.1109/EH.2003.1217673","url":null,"abstract":"The concept of \"self-protection\", a capability of an organism to protect itself from exogenous attacks, is introduced to the design of artificial evolutionary systems as a possible method to create and maintain diversity in the population. Three different mechanisms of self-protection are considered and implemented on a cellular automata based evolutionary system, the evoloop. Simulation results imply a positive effect of those mechanisms on diversity maintenance, especially when the self-protection is moderate so that it conserves both the attacker and the attacked.","PeriodicalId":134823,"journal":{"name":"NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings.","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116036670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An evolutionary power management algorithm for SoC based EHW systems","authors":"L. Tian, T. Arslan","doi":"10.1109/EH.2003.1217656","DOIUrl":"https://doi.org/10.1109/EH.2003.1217656","url":null,"abstract":"This paper proposes a dynamic power management algorithm based on an evolutionary algorithm for minimization of power on a system on chip (SoC) evolvable hardware (EHW) systems. The algorithm is specially designed to operate within an embedded microcontroller processor such as the ARM. The paper describes the algorithm, its implementation on an ARM based embedded processor and provides results demonstrating power consumption of the algorithm itself using different ARM instruction sets.","PeriodicalId":134823,"journal":{"name":"NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127386439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evolved reversible cascades realized on the CAM-brain machine","authors":"A. Buller, M. Perkowski","doi":"10.1109/EH.2003.1217675","DOIUrl":"https://doi.org/10.1109/EH.2003.1217675","url":null,"abstract":"This paper presents a new approach to reversible cascade evolution based on a 3D cellular automaton. As a research platform we used the ATR's CAMBrain Machine (CBM). Reversible circuits are investigated because they are expected to dissipate much less energy than their irreversible counterparts. One day they will be implemented as nano-scale 3-dimensional chips. A circuit is reversible if the number of its inputs equals the number of its outputs and there is a one-to-one mapping between spaces of input vectors and output vectors. This paper provides: (1) a brief introduction to reversible logic concentrating on definitions and properties of the Feynman, Toffoli, Fredkin gates; (2) an introduction to the 3D cellular logic machine (CLM) that is a cellular automaton with frozen and pulsing state variables; and (3) a collection of reversible structures evolved using a dedicated GA and located in the CBM using the NeuroMaze 3.0 Pro, a software tool for computer-aided design of CBM-style structures.","PeriodicalId":134823,"journal":{"name":"NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings.","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116888575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"2003 NASA/DoD Conference on Evolvable Hardware","authors":"Jiangning Xu, T. Arslan, Qing Wang, Dejun Wan","doi":"10.1109/EH.2003.1217634","DOIUrl":"https://doi.org/10.1109/EH.2003.1217634","url":null,"abstract":"The following topics are dealt with: digital systems evolution; analog systems evolution; controller evolution; real world applications; fault tolerance; biologically inspired robotics; evolvable hardware platforms; cellular automata; embryonics; and biologically inspired architecture.","PeriodicalId":134823,"journal":{"name":"NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings.","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125169233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}