官术网_书友最值得收藏!

  • Machine Learning in Java
  • AshishSingh Bhatia Bostjan Kaluza
  • 200字
  • 2021-06-10 19:29:56

Generating data

An alternative approach is to generate the data by you, for example, with a survey. In survey design, we have to pay attention to data sampling; that is, who the respondents are that are answering the survey. We only get data from the respondents who are accessible and willing to respond. Also, respondents can provide answers that are in line with their self-image and researcher's expectations.

Alternatively, the data can be collected with simulations, where a domain expert specifies the behavior model of users at a micro level. For instance, crowd simulation requires specifying how different types of users will behave in a crowd. Some of the examples could be following the crowd, looking for an escape, and so on. The simulation can then be run under different conditions to see what happens (Tsai et al., 2011). Simulations are appropriate for studying macro phenomena and emergent behavior; however, they are typically hard to validate empirically.

Furthermore, you can design experiments to thoroughly cover all of the possible outcomes, where you keep all of the variables constant and only manipulate one variable at a time. This is the most costly approach, but usually provides the best quality.

主站蜘蛛池模板: 安新县| 嘉善县| 镇康县| 镇安县| 濉溪县| 项城市| 奉新县| 陇川县| 雷山县| 瑞丽市| 弥渡县| 阳西县| 崇信县| 明水县| 隆子县| 清丰县| 民和| 固始县| 肃宁县| 荣成市| 随州市| 屏山县| 平阳县| 田林县| 德保县| 丰都县| 治县。| 郯城县| 嘉祥县| 蓬莱市| 安陆市| 陈巴尔虎旗| 新宁县| 同德县| 绥江县| 肥东县| 宕昌县| 涡阳县| 额敏县| 侯马市| 广河县|