Computer Science ›› 2020, Vol. 47 ›› Issue (12): 42-49.doi: 10.11896/jsjkx.201200021

Special Issue: Software Engineering & Requirements Engineering for Complex Systems

Previous Articles     Next Articles

Requirements Modeling and Decision-making for Machine Learning Systems

YANG Li1, MA Jia-jia1, JIANG Hua-xi1, MA Xiao-xiao1, LIANG Geng1, ZUO Chun1,2   

  1. 1 Institute of Software Chinese Academy of Sciences Beijing 100190,China
    2 Sinosoft.CoLtd Beijing 100190,China
  • Received:2020-09-02 Revised:2020-10-29 Online:2020-12-15 Published:2020-12-17
  • About author:YANG Li,born in 1978Ph.Dassociate professoris a member of China Computer Federation.His main research interests include intelligent software engineering and blockchain.
    ZUO Chun,born in 1959professorPh.D supervisor.His main research interests include software engineering and so on.
  • Supported by:
    Strategy Priority Research Program of Chinese Academy of Sciences(XDA20080200) and National Key Research and Development Program of China(2018YFB1005002).

Abstract: The application of systems supported by machine learning is becoming more and more common.Howeverbecause the requirements of such systems are often difficult to express completely and there may be some conflicts which are hard to detectthese systems usually cannot efficiently meet the comprehensive needs of users in a real application environment.In additionfor Machine Learning Systems (MLS) used in actual scenariosuser trust usually depends on the satisfaction of comprehensive requirements including non-functional requirements such as interpretability and fairnessand application of machine learning in different fields usually has specific needswhich brings challenges to ensure the quality of requirement description and decision-making for implementation process.To solve above-mentioned problemsthis paper presents a machine learning system requirements and decision-making framework which includes a concept MLS requirements model and a Meta-Model of MLS pipeline processas well as decision making method for training datasets and algorithms selection.The purpose is to standardize the designdevelopment and evaluation of requirements for machine learning used in actual scenarios.The case study shows that the proposed MLS requirement description and implementation method is feasible and effective.

Key words: Decision making, Machine learning systems, Meta-model, Non-functional requirements, Requirements modeling

CLC Number: 

  • TP391
[1] ALPAYDIN E.Introduction to machine learning[M].MITPress,2020.
[2] TOMSETT R,BRAINES D,HARBORNE D,et al.Interpretable to whom?A role-based model for analyzing interpretable machine learning systems[J].arXiv:1806.07552,2018.
[3] AGARWAL S.Trade-Offs between Fairness,Interpretability,and Privacy in Machine Learning[D].Waterloo:University of Waterloo,2020.
[4] PERINI A,SUSI A,AVESANI P.A machine learning approach to software requirements prioritization[J].IEEE Transactions on Software Engineering,2012,39(4):445-461.
[5] ARORA C,SABETZADEH M,NEJATI S,et al.An activelearning approach for improving the accuracy of automated domain model extraction[J].ACM Transactions on Software Engineering and Methodology (TOSEM),2019,28(1):1-34.
[6] PUDLITZ F,BROKHAUSEN F,VOGELSANG A.Extractionof system states from natural language requirements[C]//2019 IEEE 27th International Requirements Engineering Conference (RE).IEEE,2019:211-222.
[7] WINKLER J,VOGELSANG A.Automatic classification of requirements based on convolutional neural networks[C]//2016 IEEE 24th International Requirements Engineering Conference Workshops (REW).IEEE,2016:39-45.
[8] MAIMON O,ROKACH L.Introduction to knowledge discovery and data mining[M]//Data Mining and Knowledge Discovery Handbook.Springer,Boston,MA,2009:1-15.
[9] CHAPMAN P,CLINTON J,KERBER R,et al.CRISP-DM 1.0 Step-by-step Data Mining Guide[OL].https://www.the-modeling-agency.com/crisp-dm.pdf (accessed on 4 August 2020).
[10] ISHIKAWA F,YOSHIOKA N.How do engineers perceive difficulties in engineering of machine-learning systems?-Questionnaire survey[C]//2019 IEEE/ACM Joint 7th International Workshop on Conducting Empirical Studies in Industry (CESI) and 6th International Workshop on Software Engineering Research and Industrial Practice (SER&IP).IEEE,2019:2-9.
[11] HORKOFF J.Non-functional requirements for machine learn-ing:Challenges and new directions[C]//2019 IEEE 27th International Requirements Engineering Conference (RE).IEEE,2019:386-391.
[12] HIRT R,KOEHL N J,SATZGER G.An end-to-end processmodel for supervised machine learning classification:from problem to deployment in information systems[C]//Designing the Digital Transformation:DESRIST 2017 Research in Progress Proceedings of the 12th International Conference on Design Science Research in Information Systems and Technology .Karlsruhe,Germany.Karlsruher Institut für Technologie (KIT),2017:55-63.
[13] ARDAGNA C A,BELLANDI V,BEZZI M,et al.Model-based big dataanalytics-as-a-service:take big data to the next level[J/OL].IEEE Transactions on Services Computing.https://ieeexplore.ieee.org/abstract/document/8319508.
[14] ZHANG X,LI T,WANG X,et al.Formal analysis to non-functional requirements of trustworthy software[J].Ruan Jian Xue Bao,2015,26(10):2545-2566.
[15] JIA Y D,LIU L.Recognition and classification of non-functional requirements in Chinese[J].Ruan Jian Xue Bao,2019,30(10):3115-3126.
[16] YANG L,LI M,REN J,et al.A Human-in-the-Loop Method for Developing Machine Learning Applications[C]//2019 6th International Conference on Systems and Informatics (ICSAI).IEEE,2019:492-498.
[17] YANG L,ZUO C,WANG Y G.Research and Implementation of Service Oriented Architecture for Knowledge Discovery[J].Chinese Journal of Computers,2005,28(4):445-457.
[18] ZHANG J M,HARMAN M,MA L,et al.Machine learning testing:Survey,landscapes and horizons[J/OL].IEEE Transactions on Software Engineering.https://ieeexplore.ieee.org/abstract/document/9000651.
[19] MAAS A,DALY R E,PHAM P T,et al.Learning word vectors for sentiment analysis[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics:Human Language Technologies.2011:142-150.
[20] TANG D,QIN B,LIU T.Document modeling with gated recurrent neural network for sentiment classification[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.2015:1422-1432.
[21] ZHANG X,ZHAO J,LECUN Y.Character-level convolutional networks for text classification[C]//Advances in Neural Information Processing Systems.2015:649-657.
[22] Sentiment140.For Academics[EB/OL].http://help.sentiment140.com/for-students/?spm=a2c4e.11153940.blogcont576274.32.1b956c9czbnj9g.
[23] BAZIOTIS C,ATHANASIOU N,CHRONOPOULOU A,et al.Ntua-slp at semeval-2018 task 1:Predicting affective content in tweets with deep attentive rnns and transfer learning[J].arXiv:1804.06658,2018.
[24] MPQA.MPQA Resources[EB/OL].http://mpqa.cs.pitt.edu/.
[25] 19Joey85.Sentiment-annotated-news-corpus-and-sentiment-lexicon-in-Slovene[EB/OL].https://github.com/19Joey85/Sentiment-annotated-news-corpus-and-sentiment-lexicon-in-Slovene.
[1] DAI Zong-ming, HU Kai, XIE Jie, GUO Ya. Ensemble Learning Algorithm Based on Intuitionistic Fuzzy Sets [J]. Computer Science, 2021, 48(6A): 270-274.
[2] WANG Tie-xin, LI Wen-xin, CAO Jing-wen, YANG Zhi-bin, HUANG Zhi-qiu, WANG Fei. Knowledge-driven Method Towards Dynamic Partners Recommendation in Inter-enterprise Collaboration [J]. Computer Science, 2020, 47(6): 210-218.
[3] YANG Jing-wei, WEI Zi-qi, LIU Lin. What Users Think about Predictive Analytics?——A Domestic Survey on NFRs [J]. Computer Science, 2020, 47(12): 18-24.
[4] ZHANG Biao, DONG Meng-yu, FAN Bei-bei. Enterprise Performance Evaluation Model Based on Triangular Fuzzy Multi-attribute Decision Making [J]. Computer Science, 2019, 46(6A): 547-549.
[5] XU Cong, PAN Xiao-dong. Linguistic Multi-attribute Group Decision Making Method Based on Normal Cloud Similarity [J]. Computer Science, 2019, 46(6): 218-223.
[6] CHEN De-jiang, WANG Jun, ZHANG Hao-wei. Dynamic Threat Assessment Model Based on Intuitionistic Fuzzy Multiple Attribute Decision Making [J]. Computer Science, 2019, 46(4): 183-188.
[7] LU Cheng-hua, KOU Ji-song. Multi-attribute Decision Making and Adaptive Genetic Algorithm for Solving QoS Optimization of Web Service Composition [J]. Computer Science, 2019, 46(2): 187-195.
[8] YUAN Wei-wei,MENG Fan-lun,PENG Jun,SUN Xiao,LIU Ri-chu. TOPSIS Based Model for Satellite Resource Selection [J]. Computer Science, 2018, 45(6A): 275-278.
[9] ZHANG Mei-jing, WANG Ying-ming. Decision Making Approach Based on Evidential Reasoning Considering SemanticRelationship among Assessment Grades [J]. Computer Science, 2018, 45(12): 166-169.
[10] PANG Ji-fang and SONG Peng. Multi-attribute Group Decision Making Method for Interval-valued Intuitionistic Uncertain Language with Completely Unknown Experts’ Weights [J]. Computer Science, 2018, 45(1): 47-54.
[11] HE Jian-ying. Canonical Basis Based on Decision Implication of Decision Context [J]. Computer Science, 2017, 44(8): 290-295.
[12] CUI Tie-jun, LI Sha-sha and WANG Lai-gui. Multi-attribute Decision Making Model Based on Attribute Circle and Application of Reliability Analysis [J]. Computer Science, 2017, 44(5): 111-115.
[13] ZHOU Wen-bo, LIU Hong-jia, LIU Lei, ZHANG Peng and LV Shuai. Meta-modeling Approach of Message Interaction in Service [J]. Computer Science, 2017, 44(4): 24-29.
[14] GUO Song-hui, GONG Xue-rong, WANG Wei, LI Qing-bao and SUN Lei. I/O Scheduling Algorithm Based on Dynamic Prioritization in Virtual Machines [J]. Computer Science, 2017, 44(1): 13-19.
[15] QIAN Ye, LI Tong, YU Yong, SUN Ji-hong, YU Qian and PENG Lin. Approach to Modeling Software Evolution Process for Synchronous Interaction [J]. Computer Science, 2016, 43(8): 154-158.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!