Open Peer Review Any reports and responses or comments on the article can be found at the end of the article. SOFTWARE TOOL ARTICLE  ESforRPD2: Expert System for Rice Plant Disease Diagnosis [version 1; referees: 1 approved with reservations] Fahrul Agus ,     Muh. Ihsan , Dyna Marisa Khairina , Krishna Purnawan Candra 2 GIS and Environment Modelling Lab. CSIT, Mulawarman University, Samarinda, East Kalimantan, 75242, Indonesia Department of Agricultural Product Technology, Faculty of Agriculture, Mulawarman University, Samarinda, 75123, Indonesia Abstract One of the factors causing rice production disturbance in Indonesia is the lack of knowledge of farmers on early symptoms of rice plant diseases. These diseases are increasingly rampant because of the lack of experts. This study aimed to overcome this problem by providing an Expert System that helps farmers to make early diagnosis of rice plant diseases. Data of rice plant pests and diseases in 2016 were taken from Samarinda, East Kalimantan, Indonesia using an in-depth survey, and rice experts from the Department of Food Crops and Horticulture of East Kalimantan Province were recruited for the project. The Expert System for Rice Plant Disease Diagnosis, ESforRPD2, was developed based on the pest and disease experiences of the rice experts, and uses a Waterfall Paradigm and Unified Modelling Language. This Expert System can detect 48 symptoms and 8 types of diseases of rice plants from 16 data tests with an accuracy of 87.5%. ESforRPD2 is available in Indonesian at: http://esforrpd2.blog.unmul.ac.id Keywords Expert System, Rice Plant Disease, Waterfall, Unified Modelling Language   This article is included in the ICTROPS 2018 collection. 1 1 1 2 1 2  Referee Status:   Invited Referees      version 2 published 21 Feb 2019 version 1 published 06 Dec 2018 1 report , University of Georgia, USAYi Fang1  06 Dec 2018,  :1902 (First published: 7 )https://doi.org/10.12688/f1000research.16657.1  21 Feb 2019,  :1902 (Latest published: 7 )https://doi.org/10.12688/f1000research.16657.2 v1 Page 1 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 https://f1000research.com/articles/7-1902/v1 https://orcid.org/0000-0003-2983-137X https://orcid.org/0000-0003-1358-1329 http://esforrpd2.blog.unmul.ac.id https://f1000research.com/collections/ICTROPS2018 https://f1000research.com/collections/ICTROPS2018 https://f1000research.com/articles/7-1902/v2 https://f1000research.com/articles/7-1902/v1 https://orcid.org/0000-0003-2583-328X https://doi.org/10.12688/f1000research.16657.1 https://doi.org/10.12688/f1000research.16657.2 http://crossmark.crossref.org/dialog/?doi=10.12688/f1000research.16657.1&domain=pdf&date_stamp=2018-12-06    Fahrul Agus ( )Corresponding author: fahrulagus@unmul.ac.id   : Conceptualization, Funding Acquisition, Supervision, Writing – Original Draft Preparation, Writing – Review & Editing; Author roles: Agus F : Data Curation, Formal Analysis, Writing – Original Draft Preparation;  : Supervision;  : Writing – Review &Ihsan M Marisa Khairina D Candra KP Editing  No competing interests were disclosed.Competing interests:  The author(s) declared that no grants were involved in supporting this work.Grant information:  © 2018 Agus F  . This is an open access article distributed under the terms of the  , whichCopyright: et al Creative Commons Attribution Licence permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.  Agus F, Ihsan M, Marisa Khairina D and Candra KP. How to cite this article: ESforRPD2: Expert System for Rice Plant Disease Diagnosis    2018,  :1902 ( )[version 1; referees: 1 approved with reservations] F1000Research 7 https://doi.org/10.12688/f1000research.16657.1  06 Dec 2018,  :1902 ( ) First published: 7 https://doi.org/10.12688/f1000research.16657.1 Page 2 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 http://creativecommons.org/licenses/by/4.0/ https://doi.org/10.12688/f1000research.16657.1 https://doi.org/10.12688/f1000research.16657.1 Introduction Correct diagnosis of symptoms in rice plant diseases, caused by bacteria, nematodes, fungi, phythoplasmal and viruses1–4, is very critical in supporting the productivity of rice plants. However, many regions in Indonesia have a huge problem because of a limited number of rice plant pathologists. The large plan- tation area of rice plants is also a problem due to logistical issues when visiting these sites, leading to difficulty obtaining disease evidence. Along with other rapid technological developments, a technol- ogy known as Expert System (ES)5–8 has been developed to solve health9–12, education13, and business14, including agriculture15,16, problems. ES is usually designed for a specific condition, i.e. variables of climate in cases of agriculture. This article proposes a new software based on ES for the diagnosis of disease in rice plants in the Samarinda region, Indonesia. Waterfall Paradigm applied in designing this ES. The prototype, Expert System for Rice Plant Disease Diagnosis (ESforRPD2) is available at: http:// esforrpd2.blog.unmul.ac.id. Methods Data collection and ES development The ES of rice plant disease diagnosis was designed to help farmers and agricultural officials to diagnose rice plant diseases occurring in the Samarinda region, East Kalimantan province, Indonesia. Rice plant experts were recruited from the Seed Tech- nology Development Division at the Department of Food Crops and Horticulture of East Kalimantan Province and from the Department of Agro-eco-technology of Agricultural Faculty of Mulawarman University (one expert from each). The experts were the primary source for information on rice plant symptoms and diseases. The two rice plant experts have experience in diagnosing rice plant disease in the region of East Kalimantan Province for 20 years. Symptoms, diseases and their relationships (and their ranked importance) were derived from the experts by questionnaire (Supplementary File 1). This information was then used to construct the knowledge base for building the ES software. The ES software was developed using the Waterfall paradigm as recommended by Sommerville17 using five stages, i.e. (i) planning and requirement, (ii) analysis and software design, (iii) imple- mentation and unit testing, (iv) integration and (v) system test- ing and operation and maintenance. ES architecture consists of three parts, namely the user interface, the inference engine and the knowledge base as proposed by Lucas and van der Gaag7. The user interface is used as a consulting interface in order to obtain knowledge and advice from the ES, which would be like consulting an expert. In this ES, the inference engine works as a consultation system in processing input data to build a diagnosis based on the knowledge base developed. Implementation The implementation of the ESforRPD2 application is based on Unified Modelling Language (Figure 1) as proposed by Sommerville17, which consists of use case diagrams, activity diagrams, and class diagrams. We constructed two types of “Use case diagram”, namely “Use case for user” consisting of four cases (Article, Consult- ing, Choose Symptoms and Consulting Result); and “Use case for expert” consisting of three cases (Symptoms, Diseases, and Relation). The use case describes the functions of the ES inter- acting with user and expert. The activity diagram illustrates the flow of various activities being designed in the ES, i.e. how Figure 1. a. Use case diagram of user. b. Use case diagram of expert. Page 3 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 http://esforrpd2.blog.unmul.ac.id/ http://esforrpd2.blog.unmul.ac.id/ Figure 1c. Activity diagram of ESforRPD2 system application. the flow starts, the decision that might occur, and the flow end. The activity diagram also describes parallel processes that might occur in some executions. In this ES, we build four data stores (Expert, Symptoms, Relation, and Diagnosis) in the class diagram. The ESforRPD2 application uses four datasets, namely disease- and symptoms-data, knowledge base, and symptoms- disease-weight relationships table (Dataset 2). The construction of decision trees and forward-chaining tracing for diagnosing of rice plant diseases in the ES is shown in Figure 2. ESforRPD2 is the first version of ES (only in Indonesian) to make it user-friendly for Indonesian users. Users use a consul- tation page to choose the symptoms of the rice plant. The ES performs the calculation process to obtain the trust level using the Dempster-Shafer method18. The user page (Figure 3a) is the main web page for users without logging in. In the user page, there is also a home menu that displays articles about ES, rice plant diseases, and the Dempster-Shafer method. The consultation page starts the user consultation about the disease of rice plants (Figure 3b). The ES will provide an output as a display showing the symptoms, diagnosis of disease and the confidence level (Figure 3c). Operation The ESforRPD2 application is developed using CPU with specifications of Intel Core i3, 4GB RAM, and 300GB HDD. The same specification of CPU is needed to operate this application. Page 4 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 Figure 1d. Class diagram of ESforRPD2 system application. Uses case The ESforRPD2 application was tested applying symptom-data inputs by clicking the symptoms selected (Figure 5b). In a single test using the case of four symptom-data inputs selected, namely (i) Spots on leaf midrib, (ii) Little spots are dark brown or slightly purple rounded shape, (iii) Spots on oval-shaped leaves and evenly distributed on the leaf surface, (iv) The size of spots is 2–10 mm long and 1 mm wide, a display of diag- nosis page (Figure 3c) will appear following clicking of the “submit diagnose” button. The diagnosis page shows the confidence level. In this case test, the ES gave the accuracy of disease type detection of 91%. 16 tests in row were conducted using randomly selected symptoms by user in the ES. The results were approved by the two experts. In total, 14 diagnosis (87.5%) of the 16 results showed by the ES were justified by the two experts (Table 1). Discussion The ESforRPD2 application is showing good reliability. By applying 16 tests, the ESforRPD2 showed a level of performance of 87.5% (Table 1) following justification to two rice plants diseases experts. The performance of the ESforRPD2 during validation was the expected high-performance level of plant diseases diagnosis by the expert system. This performance is much higher than the performance of ES for Chili pepper pest diagnosis invented by Agus et al.16. However other Expert System could show excellent performance of 98.38%19, this evidence advice that the performance of ESforRPD2 could be improved in the next study. Currently, ESforRPD2 has only been tested with data from the Samarinda region. In a future study, we will use data from other regions of East Kalimantan, which have the same climate (tropical rainforest) and soil character as the Samarinda region. Page 5 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 Figure 2. Decision tree and forward chaining tracing. G1 G2 G3 G4 G5 G6 G7 G8 G9 G10 G11 G12 G13 G14 G15 G16 G17 G18 G19 G20 G21 G22 G23 G24 G25 G26 G27 G28 G29 G30 G31 G32 G33 G34 G35 G36 G37 G38 G39 G40 G41 G42 G43 G44 G45 G46 G47 G48 P1 P2 P3 P4 P5 P6 P7 P8 Page 6 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 Figure 3a. User main page. Figure 3b. Consultation page. Page 7 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 Figure 3c. Diagnosis results page. Table 1. System testing with expert justification. Test No. Experts Justification (English/Indonesian) Results Diagnosis of ESforRPD2 (English/Indonesian) Results 1 Blast/Blas Blas/Blast Suitable 2 Brown Spot (Bercak Coklat) Brown Spot (Bercak Coklat) Suitable 3 Narrow Brown Spot (Bercak Coklat Sempit) Narrow Brown Spot (Bercak Coklat Sempit) Suitable 4 Sheath Bligh (Hawar Pelepah) Sheath Bligh (Hawar Pelepah) Suitable 5 False Smut (Noda Palsu/Gosong Palsu) False Smut (Noda Palsu/Gosong Palsu) Suitable 6 Grassy Stunt (Kerdil Rumput) Grassy Stunt (Kerdil Rumput) Suitable 7 Bacterial leaf blight (BLB-Kresek Hawar Daun) Bacterial leaf blight (BLB-Kresek Hawar Daun) Suitable 8 Tungro (Tungro) Tungro (Tungro) Suitable 9 Blast (Blas) Blast (Blas) Suitable 10 Brown Spot (Bercak Coklat) Brown Spot (Bercak Coklat) Suitable 11 Narrow Brown Spot (Bercak Coklat Sempit) Blas/Blas Unsuitable 12 Sheath Bligh (Hawar Pelepah) Blast/Blas Unsuitable 13 False Smut (Noda Palsu/Gosong Palsu) False Smut (Noda Palsu/Gosong Palsu) Suitable 14 Grassy Stunt (Kerdil Rumput) Grassy Stunt (Kerdil Rumput) Suitable 15 Bacterial leaf blight (BLB-Kresek Hawar Daun) Bacterial leaf blight (BLB-Kresek Hawar Daun) Suitable 16 Tungro (Tungro) Tungro (Tungro) Suitable Page 8 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 References 1. Jagan Mohan K, Balasubramanian M, Palanivel S: Detection and Recognition of Diseases from Paddy Plant Leaf Images. Int J Comput Appl. 2016; 144(12): 34–41. Reference Source 2. Chapuis E, Besnard G, Andrianasetra S, et al.: First report of the root-knot nematode (Meloidogyne graminicola) in Madagascar rice fields. Australas Plant Dis Notes. 2016; 11(1): 32. Publisher Full Text 3. Qudsia H, Akhter M, Riaz A, et al.: Comparative Efficacy of Different Chemical Treatments for Paddy Blast, Brown Leaf Spot and Bacterial Leaf Blight Diseases in Rice (Oryza Sativa L.). Appl Microbiol Open Access. 2017; 3(3). Publisher Full Text 4. Kulmitra AK, Sahu N, Kumar VBS, et al.: In vitro evaluation of bio-agents against Pyricularia oryzae (Cav.) causing rice blast disease. Agric Sci Dig - A Res J. 2017; 37(3): 98–101. Publisher Full Text 5. Todd BS: An Introduction to Expert Systems. Issue 95, Oxford University Computing Laboratory, Programming Research Group; 1992. Reference Source 6. Turban E, Frenzel LE: Expert Systems and Applied Artificial Intelligence. Prentice Hall Professional Technical Reference; 1992. Reference Source 7. Lucas PJF, van der Gaag LC: Principles of Expert Systems. Amsterdam: Addison-Wesley; 1991. Reference Source 8. Gaines BR: Designing Expert Systems for Usability. Knowl Creat Diffus Util. 1986; 1–40. Reference Source 9. Gudu J, Gichoya D, Nyongesa P, et al.: Development of a medical expert system as an expert knowledge sharing tool on diagnosis and treatment of hypertension in pregnancy. Int J Biosci Biochem Bioinforma. 2012; 2(5): 297–300. Publisher Full Text 10. Abu Naser SS, Ola AZA: An expert system for diagnosing eye diseases using clips. Theor Appl Inf Technol. 2008; 923–930. Reference Source 11. Ayangbekun OJ, Jimoh IA: Expert System for Diagnosis Neurodegenerative Diseases. Int J Comput Inf Technol. 2015; 4(4): 694–698. Reference Source 12. Ayangbekun OJ, Bankole FO: An Expert System for Diagnosis of Blood Disorder. Int J Comput Appl. 2014; 100(7): 975–8887. 13. Divayana DGH: Utilization of cse-ucla model in evaluating of digital library program based on expert system at universitas teknologi indonesia: A model for evaluating of information technology-based education services. J Theor Appl Inf Technol. 2017; 95(15): 3585–3596. Reference Source 14. Arias-Aranda D, Castro JL, Navarro M, et al.: A fuzzy expert system for business management. Expert Syst Appl. 2010; 37(12): 7570–7580. Publisher Full Text 15. Ihsan M, Agus F, Khairina DM: Penerapan Metode Dempster Shafer Untuk Sistem Deteksi Penyakit Tanaman Padi. Prosiding Seminar Ilmu Komputer dan Teknologi Informasi. 2017; 2(1). Reference Source 16. Agus F, Wulandari HE, Astuti IF: Expert System With Certainty Factor For Early Diagnosis Of Red Chili Peppers Diseases. JAIS. 2017; 2(2): 52–66. Reference Source 17. Sommerville I: Software Engineering. 10th Edition. Pearson; 2016. Reference Source 18. Maseleno A, Mahmud Hasan M: Skin infection detection using Dempster-Shafer theory. In: 2012 International Conference on Informatics, Electronics and Vision, ICIEV 2012. 2012. Publisher Full Text 19. Sabzi S, Abbaspour-Gilandeh Y, García-Mateos G: A fast and accurate expert system for weed identification in potato crops using metaheuristic algorithms. Comput Ind. 2018; 98: 80–89. Publisher Full Text 20. Newbery F, Qi A, Fitt BD: Modelling impacts of climate change on arable crop diseases: progress, challenges and applications. Curr Opin Plant Biol. 2016; 32: 101–109. PubMed Abstract | Publisher Full Text 21. Xu C, Wu W, Ge Q: Impact assessment of climate change on rice yields using the ORYZA model in the Sichuan Basin, China. Int J Clim. 2018; 38(7): 2922–2939. Publisher Full Text 22. fahrulagus, Fajar MI: fahrulagus/paper: ESforRPD2 (Version V.10). Zenodo. 2018. http://www.doi.org/10.5281/zenodo.1490641 23. Agus F, Ihsan M, Khairina DM, et al.: Knowledge base for rice plant disease diagnosis [Data set]. Zenodo. 2018. http://www.doi.org/10.5281/zenodo.1490658 24. Agus F, Ihsan M, Khairina DM, et al.: Dataset for rice plant diseases expert interview [Data set]. F1000Research. Zenodo. 2018. http://www.doi.org/10.5281/zenodo.1953383 In addition, we will test data from other regions in Indonesia, which have a different climate. Newbery et al.20 showed that different climate conditions affect symptoms of arable crop disease; therefore, the ESforRPD2 will need continuous evaluation because climate change effects21. Consent Written informed consent was obtained from the two experts for participation in the study. Software availability Software application is available from: http://esforrpd2.blog. unmul.ac.id. Source code: https://github.com/fahrulagus/paper. Archived source code as at time of publication: https://doi. org/10.5281/zenodo.149064122 License: GNU GPL v3.0 Data availability Underlying data Zenodo: Knowledge base for rice plant disease diagnosis, https:// doi.org/10.5281/zenodo.149065823 Extended data Zenodo: Dataset for rice plant diseases expert interview, http:// doi.org/10.5281/zenodo.195338324 Grant information The author(s) declared that no grants were involved in supporting this work. Acknowledgements The authors are grateful to both experts in this research, the Rector of Mulawarman University and Islamic Development Bank Project. Page 9 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 https://pdfs.semanticscholar.org/8bf2/acd54720b36a1d7e9c8347b6fbd7889c13b6.pdf http://dx.doi.org/10.1007/s13314-016-0222-5 http://dx.doi.org/10.4172/2471-9315.1000138 http://dx.doi.org/10.18805/asd.v37i03.8989 https://www.cs.ox.ac.uk/files/3425/PRG95.pdf https://dl.acm.org/citation.cfm?id=573712&preflayout=flat https://www.cs.ru.nl/P.Lucas/proe.pdf https://pages.cpsc.ucalgary.ca/~gaines/reports/KBS/HFES/HFES.pdf http://dx.doi.org/10.7763/IJBBB.2012.V2.120 http://www.jatit.org/volumes/research-papers/Vol4No10/5Vol4No10.pdf https://www.ijcit.com/archives/volume4/issue4/Paper040413.pdf http://www.jatit.org/volumes/Vol95No15/17Vol95No15.pdf http://dx.doi.org/10.1016/j.eswa.2010.04.086 http://e-journals.unmul.ac.id/index.php/SAKTI/article/download/249/pdf https://publikasi.dinus.ac.id/index.php/jais/article/download/1455/1182 https://books.google.co.in/books?id=tW4VngEACAAJ&dq=Software+Engineering,+10th+Edition+PDF&hl=en&sa=X&ved=0ahUKEwij6dX544LfAhVJK48KHUvfD9sQ6AEILjAB http://dx.doi.org/10.1109/ICIEV.2012.6317330 http://dx.doi.org/10.1016/J.COMPIND.2018.03.001 http://www.ncbi.nlm.nih.gov/pubmed/27471781 http://dx.doi.org/10.1016/J.PBI.2016.07.002 http://dx.doi.org/10.1002/joc.5473 http://www.doi.org/10.5281/zenodo.1490641 http://www.doi.org/10.5281/zenodo.1490658 http://www.doi.org/10.5281/zenodo.1953383 http://esforrpd2.blog.unmul.ac.id/ http://esforrpd2.blog.unmul.ac.id/ https://github.com/fahrulagus/paper https://dx.doi.org/10.5281/zenodo.1490641 https://dx.doi.org/10.5281/zenodo.1490641 https://dx.doi.org/10.5281/zenodo.1490658 https://dx.doi.org/10.5281/zenodo.1490658 http://dx.doi.org/10.5281/zenodo.1953383 http://dx.doi.org/10.5281/zenodo.1953383   Open Peer Review Current Referee Status: Version 1 24 January 2019Referee Report https://doi.org/10.5256/f1000research.18205.r43488    Yi Fang Nano Electrochemistry Laboratory, College of Engineering, University of Georgia, Athens, GA, USA The author applied Expert System (ES) for rice plant disease and diagnosis; the background information and introduction is sufficient and well organized. The entire manuscript is also presented well. However, the author used the word “accuracy” which is not quite a scientific term. If “accuracy” is defined as sensitivity of the method, how about the specificity of the method? If a method has low specificity, it may not be able to solve the problem from false positive. For other comments, please see below: Page 1: Change “is the lack of knowledge of farmers on early symptoms…” to “is that farmers lack of knowledge of early symptoms…”.   Page 1: “accuracy of 87.5%” accuracy is not a scientific terminology, do you refer to sensitivity or specificity?   Page 3: change “… education, and business, including agriculture, problems” to “…education, business, and agriculture problems.”   Page 3: please change to “Waterfall Paradigm was applied in designing this ES.”   Page 5: “In this case test, the ES gave the accuracy of disease type detection of 91%”. Do you refer to sensitivity? Please also try to apply this comment to the other “accuracy” you mentioned in the manuscript. Is the rationale for developing the new software tool clearly explained? Partly Is the description of the software tool technically sound? Yes Are sufficient details of the code, methods and analysis (if applicable) provided to allow replication of the software development and its use by others? Yes Is sufficient information provided to allow interpretation of the expected output datasets and any results generated using the tool? Yes Page 10 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019 https://doi.org/10.5256/f1000research.18205.r43488 http://orcid.org/0000-0003-2583-328X   Are the conclusions about the tool and its performance adequately supported by the findings presented in the article? Yes  No competing interests were disclosed.Competing Interests: Reviewer Expertise: electrochemistry, plant diseases, biosensors, sensor I have read this submission. I believe that I have an appropriate level of expertise to confirm that it is of an acceptable scientific standard, however I have significant reservations, as outlined above. Author Response 12 Feb 2019 , Mulawarman University, IndonesiaFahrul Agus We agree with your judgment regarding the term of accuracy. We meant the accuracy is the sensitivity, for that reason we change the term accuracy to sensitivity. Regarding the term of specificity, we explain that this system has high specificity for rice plants because all data used in constructing the algorithm were collected specifically for rice plant diseases.   No competing interests were disclosed.Competing Interests: The benefits of publishing with F1000Research: Your article is published within days, with no editorial bias You can publish traditional articles, null/negative results, case reports, data notes and more The peer review process is transparent and collaborative Your article is indexed in PubMed after passing peer review Dedicated customer support at every stage For pre-submission enquiries, contact   research@f1000.com Page 11 of 11 F1000Research 2018, 7:1902 Last updated: 01 MAR 2019