ML Journal data

Nigeria, like many nations in the world, is embattled by a housing shortage. It has a housing deficit running to 20 million. There has been a proposition that Off-Site Construction (OSC), because of its speed of erection, can help in combating the housing shortage. however, for it to be adopted in society, some factors have to be considered. what then are these factors and which of them are most critical to successfully adopting OSC within the Nigerian context? This work is researched by utilizing prediction capabilities for OSC adoption in Nigeria. Data was collected through questionnaires from industry players within the Nigerian construction industry (Boothman et al., 2014.; Brannen & Moss, 2012). First, literature relating to OSC and its adoption was sourced through scholarly search engines like Google Scholar and Scopus (Almalki, 2016; O'Neill & Organ, 2016). The literature survey used key search words and phrases such as adoption, Design for Manufacture and Assembly, Offsite Construction and Prefab Constructions, and key authors' names. Specifically, research published on the subject between 2000 to 2021 were considered. A review of these papers informed the potential critical factors responsible for low DfMA adoption in Nigeria. The questionnaire was developed in Microsoft form. Using a purposeful sampling technique (Palinkas et al., 2015), the form link was administered to relevant key players in the Nigerian construction industry through e-mails and social media platforms for responses. The targeted responders were architects, civil/structural engineers, electrical engineers, mechanical engineers, building engineers, town/urban planners, quantity surveyors, contractors, academics, real estate investors, and developers. They were considered because they are thought to be actively involved in everyday construction processes in the country and involved in making and taking decisions bordering around the choice of building materials to be used on projects. The research outcome identifies seven (7) best performing algorithms: Decision Tree, Random Forest, K-Nearest Neighbour, Extra-Trees, AdaBoost, Support Vector Machine, and Artificial Neural Network. It also reported finance, awareness, use of Building Information Modeling (BIM), attitude and belief in OSC as the main influencing factors. Availability of expertise knowledge, favourable exchange rate and skilled personnel as other underlining influencing factors. It was concluded that with detailed attention paid to the identified factors, OSC usage could find its footing in Nigeria and, consequently, Africa. The models can also serve as a template for other regions where OSC adoption is being considered.与全球诸多国家一样，尼日利亚正深陷住房短缺困境，其住房缺口规模高达2000万。有观点提出，场外施工（Off-Site Construction, OSC）因其搭建速度快的优势，可助力缓解住房短缺问题。然而，要让该技术在尼日利亚社会中得到推广应用，需考量诸多影响因素。那么，这些影响因素具体为何？在尼日利亚语境下，哪些因素对OSC的成功推广最为关键？本研究借助预测分析方法，针对尼日利亚OSC的应用推广展开研究。研究数据通过向尼日利亚建筑业从业者发放问卷收集所得（Boothman等人，2014；Brannen & Moss，2012）。首先，研究通过谷歌学术（Google Scholar）、斯高帕斯数据库（Scopus）等学术搜索引擎，检索与OSC及其应用推广相关的文献（Almalki，2016；O'Neill & Organ，2016）。本次文献调研采用了应用推广、面向制造与装配的设计（Design for Manufacture and Assembly, DfMA）、场外施工以及预制建筑（Prefab Constructions）等核心检索词与短语，同时结合关键作者姓名进行检索，最终纳入2000年至2021年间发表的相关研究成果。通过对上述文献的梳理，明确了尼日利亚境内DfMA应用推广率偏低的潜在关键影响因素。问卷通过微软表单（Microsoft Forms）制作完成。研究采用目的性抽样法（Palinkas等人，2015），通过电子邮件与社交媒体平台，将问卷链接发放给尼日利亚建筑业的相关核心从业者以收集反馈。本次调研的目标受访者涵盖建筑师、土木/结构工程师、电气工程师、机械工程师、建筑工程师、城镇/城市规划师、工料测量师、承包商、学术研究者、房地产投资者以及开发商。选择上述群体作为受访者，是因为他们均深度参与该国日常建筑施工流程，并需围绕项目建材选型等事项制定与执行相关决策。研究结果筛选出7种性能最优的算法：决策树（Decision Tree）、随机森林（Random Forest）、K近邻（K-Nearest Neighbour）、极端随机树（Extra-Trees）、自适应提升算法（AdaBoost）、支持向量机（Support Vector Machine）以及人工神经网络（Artificial Neural Network）。研究同时指出，资金状况、认知程度、建筑信息模型（Building Information Modeling, BIM）的应用、对OSC的态度与认知信念，是主要的影响因素；专业知识可及性、有利的汇率水平以及熟练技术人员，则为其他关键影响因素。研究最终得出结论：若能对上述已识别的影响因素给予充分重视，OSC的应用便可在尼日利亚乃至整个非洲站稳脚跟。本次构建的模型还可作为其他拟推广OSC应用的地区的参考模板。