No abstract

This paper presents a new user experience for online apartment search using functionality and comfort as query items. Specifically, it has three technical contributions. First, we present a new dataset on the perceived functionality and comfort scores of residential floor plans using nine question statements about the level of comfort, openness, privacy, etc. Second, we propose an algorithm to predict the scores from the floor plan images. Lastly, we implement a new apartment search system and conduct a large-scale usability study using crowdsourcing. The experimental results show that our apartment search system can provide a better user experience. To the best of our knowledge, this is the first work to propose a highly accurate machine learning model for predicting the subjective functionality and comfort of apartments.

Design of universal components that can tolerate technological, environmental, and circumstantial changes over time is a challenge for an architect. In this paper, I would like to propose a scaled prototype of architectural components that can reconfigure themselves into globally functional configurations based on feedback from locally distributed intelligence embedded inside the component. The project aims at demonstrating a design system that can respond to dynamically changing environment over time without imposing a static blueprint of the structure in a top-down manner from the outset of design processes. The control of the subunits are governed by the logic of a distributed system simulated by the use of multiple microcontrollers, and appropriate geometrical configurations will be computationally derived based on physical-environmental criteria such as solar radiation from various sensors and social-programmatic issues.

No abstract

ThiS pAper inTrOduCeS A pOTenTiAl AppliCATiOn OF COnSTruCTiOn SySTemS Seen in biOlOGiCAl SySTemSTO OverCOme vAriOuS ShOrTCOminGS in humAn ArChiTeCTure. unlike human constructions, some social insects can produce habitable structures with simple rules without predetermined blueprints or central leaders to gain more adaptability. Active application of logics from self-organizing systems can possibly enhance our conventional centralized methods by designing artificial distributed systems. A conceptual case study is presented that involves a notion of the collective construction.