CAJ | 학술논문

构建科学合理的水产养殖物联网应用评价指标体系和评价方法，是保证水产养殖物联网系统发挥最大能效的基础。为解决指标设置随意、冗余、交叉及技术指标过剩的问题，该文构建了指标筛选模型，将水产养殖物联网应用评价指标体系从40个优化到14个，用35%的指标表达了88.45%的信息，保证了指标体系的完备性和简洁性。同时，基于模糊评价法构建了水产养殖物联网应用评价模型，可对水产养殖物联网应用水平进行总体评价以及功能、性能、效益方面的评价。最后，以江苏宜兴河蟹养殖物联网和广东湛江南美白对虾养殖物联网为实例进行了验证，宜兴物联网的评价结果为优，而湛江物联网的评价结果为良，与实际情况相符，表明该研究构建的指标体系科学合理，评价方法可行，可为水产养殖物联网应用评价提供参考。
구건과학합리적수산양식물련망응용평개지표체계화평개방법，시보증수산양식물련망계통발휘최대능효적기출。위해결지표설치수의、용여、교차급기술지표과잉적문제，해문구건료지표사선모형，장수산양식물련망응용평개지표체계종40개우화도14개，용35%적지표표체료88.45%적신식，보증료지표체계적완비성화간길성。동시，기우모호평개법구건료수산양식물련망응용평개모형，가대수산양식물련망응용수평진행총체평개이급공능、성능、효익방면적평개。최후，이강소의흥하해양식물련망화엄동담강남미백대하양식물련망위실례진행료험증，의흥물련망적평개결과위우，이담강물련망적평개결과위량，여실제정황상부，표명해연구구건적지표체계과학합리，평개방법가행，가위수산양식물련망응용평개제공삼고。
Internet of things for Aquaculture is an integrated modern system based on computing and communications technology like smart sensor technology, reliable telecommunication, intelligent information processing, which can collect data and images, transmit and process data intelligently, forecast future trend and early-warning for decision support. First of all, it is a key issue to establish scientific and rational index system and evaluation method for internet of things for aquaculture to guarantee its effectiveness. With the rapid development of information technology in China, the internet of things for aquaculture has been promoted and applied in Jiangsu, Shandong, Hunan, Hubei, Zhejiang and Guangdong. However, the internet of things for aquaculture in China is at an early stage and there are some problems, which cause negative impact on the promotion and application of the system, for examples, redundant functions, high cost, unstable performances, and so on. Secondly, in order to assess internet of things for aquaculture system, index system to assess internet of things for aquaculture was built in this paper by indicator optimization model to solve randomicity, redundancy, cross-connection and overlap caused subjective selection. Three steps composed of the selection process: 1) first round selection, three categories indices of function indicator, performance indicator and effectiveness indicator, targeted to 40 indicators were selected; 2) second round selection, 40 indicators representing perception layer, transmission layer and application layer, were optimized to 26 by method proposed by Dale and Beyeler, in which the standard conformity degree of each indicator was checked one by one and indicators need to meet at least 5 standards, otherwise they will be eliminated; 3) indicator screening model, by which 26 indicators were reduced to 14, with only 35% of total indicators representing 88.45% of total information, capturing the requirements of completeness and simplicity. Thirdly, fuzzy comprehensive evaluation approach, which comprise of three levels fuzzy comprehensive evaluation, was established to assess the application of internet of things for aquaculture. Most of the 14 indicators got in the first phase are qualitative factors and difficult to be quantified. That is why fuzzy comprehensive evaluation approach was used in this paper. Meanwhile, it is better to adopt multi-level factors as weights are not easy to be assigned reasonably when factors are too many, which leads unreasonable and wrong results. Multi-level fuzzy comprehensive method works well to solve this problem and can be applied to assess function characteristics, performance and effectiveness of the system of internet of things for aquaculture. Multi-level fuzzy comprehensive was built by steps of establishing comment set, membership and got quantitative scoreA, which can fall into five levels of excellence (A≥82.5), good (82.5>A≥67.5), satisfactory (67.5>A≥52.5), barely adequate (52.5>A≥35) and fail (A<35). Finally, case studies were carried out in Yixing of crab cultivation, Jiangsu province and Zhanjiang of white shrimp cultivation, Guangdong province, in which the index system and multi-level fuzzy comprehensive method were tested based on the internet of things for aquaculture system developed independently by China Agricultural University (CAU). Results showed that the score in Yixing was 87.371 indicating application of internet of things for aquaculture system in Yixing is excellent, meanwhile, the score in Zhanjiang is 74.921, which is good. Both of the two results are consistent with the actual situation of two bases, showing that index system and multi-level fuzzy comprehensive method proposed in this paper are feasible and reasonable for evaluation of application of internet of things for aquaculture and can guide its construction and improvement.