Pages 2021-1 FInal.cdr 6571 INTRODUCTION Mobile phone possession among Indian farmers is increasing. However, internet access in rural areas remains low (NSSO 2018). Indian Council of Agricultural Research has released a wide range of mobile applica�ons for farmers u�liza�on (Singh et.al. 2018). However, the prac�cal usability of mobile applica�ons remains unknown. This study was taken up with the objec�ve to study the effec�veness of crop doctor in TNAU (Tamil Nadu Agricultural University) Paddy Expert system mobile applica�on for its usability among the respondents and to find out the rela�onship between the profile characteris�cs of the respondents and the effec�veness of Crop doctor in terms of usability. The study was carried out using a pre tested, well- structured interview schedule and the data were analysed and presented. METHODOLOGY The present study was conducted for assessing the diagnos�c usability of Crop doctor in Paddy Expert system mobile a p p l i c a � o n o f T N A U, a m o n g p a d d y cul�va�ng farmers owning smartphones. Research Article Journal of Extension Educa on Vol. 33 No.1, 2021 DOI: h�ps://doi.org/10.26725/JEE.2021.1.33.6571-6575 Effectiveness of a Mobile Paddy Expert System in Pest Diagnosis R. Janarthanan 1 and M.Senthil kumar 2 ABSTRACT 'Crop doctor' is a component in a mobile applica on developed by Tamil Nadu Agricultural University (TNAU) for diagnosing pest and diseases in paddy and aids in availing management solu ons. The study was conducted among paddy growers in Tamil Nadu through an 'a�er only' experimental design to find out the diagnos c usability of 'Crop doctor' in Paddy Expert System mobile applica on of TNAU in diagnosis of pest and disease in paddy. Diagnos c Usability of crop doctor component among the respondents revealed that overall effec veness of the mobile applica on was found to be at 73.20 percent. Keywords : ICT ; Android Mobile application; Usability study; Paddy; TNAU 1 Department of Agricultural Extension, TNAU, Coimbatore - 641 003 2 Directorate of Extension Educa�on, TNAU, Coimbatore - 641 003 Received: 14-07-2021; Accepted: 10-02-2022 Respondents were selected in three paddy growing districts of Tamil Nadu i.e., Villupuram (45), Kancheepuram (26) and Thiruvarur (82) with the help of Krishi Vigyan Kendra (KVK) and Department of Agriculture, Tamil Nadu. A sample size of 1 5 3 re s p o n d e nt s w a s d e r i ve d u s i n g Purposive Random sampling method by following 'a�er only' experimental design. Diagnos�c usability is an integrated measure to measure the usability of crop doctor and the procedure for the study was adopted with suitable modifica�ons, (Lewis, 2014). This was studied using standardized t h r e e c o m p o n e n t s v i z . d i a g n o s � c effec�veness, diagnos�c efficiency and ove ra l l u s e r s a� s f a c � o n . Di a g n o s � c effec�veness was recorded using the c o m p l e � o n of d i a g n o s i s a n d i t w a s calculated by: Four tasks set for assessing were, opera�ve task for assessing the skill to operate crop doctor successfully for any symptom randomly and followed by diagnosis of two insect and two disease diagnosis viz., Brown Plant Hopper, Stem borer, Brown spot and Blast disease. Diagnos�c efficiency was measured upon comple�on of task and was recorded based on the standard �me scale in two intervals fixed and the overall user sa�sfac�on was calculated using method adopted by Simorangkir et.al., (2018). The scores were recorded using five-point con�nuum of Likert scale. Overall user sa�sfac�on was calculated by dividing actual score and the ideal score and the result is converted to per cent through m u l � p l i c a � o n w i t h h u n d r e d . T h e collected data were tabulated and analysed using percentage analysis, mul�ple linear regression and Pearson correla�on coefficient. For this study, only 'crop doctor' of the Paddy expert system mobile app developed by TNAU, was chosen and studied. 'Crop doctor' works on the principle of picture iden�calness by matching the field affected picture on comparison with the prestored picture in the applica�on. FINDINGS AND DISCUSSION Diagnos�c Usability Among the allo�ed five tasks, the results revealed that majority (87.58 %) of t h e re s p o n d e nt s we re s u cce s s f u l i n naviga�ng the Crop doctor (Table 1). Farmers were able to operate the Crop d o c t o r b y f o l l o w i n g t h e g u i d e l i n e s instructed in the applica�on and its displayed language i.e., Tamil. Among the 6572 Diagnos�c effec�venes No.of.symptoms diagonsed successfully using Crop doctor Total no.of.symptoms given for diagonsis using Crop doctor *100= 6573 Table 1. Distribu�on of Respondents according to the Diagnos�c Effec�veness S. No. Name of the task No. Percentage (n=153) Overall effec�veness (%) 1 Crop doctor opera�on 134 87.58 73.20 2 Stem borer diagnosis 117 76.47 3 Blast diagnosis 81 52.95 4 Brown spot diagnosis 115 75.16 5 Brown Plant Hopper diagnosis 113 73.85 Overall User Sa�sfac�on of the Respondents Sa�sfac�on of the respondents was measured using the five-point con�nuum of Likert scale. The data collected were analysed by using method followed by Simorangkir et.al., (2018) Based on the above method, a respondent is measured for three contexts viz., User interface, picture iden�cality and ease of use. Based on this, the overall user sa�sfac�on was calculated and the categorized results are presented in Table 2. Effec�veness of a Mobile Paddy Expert System in Pest Diagnosis subsequent tasks high level of diagnos�c effec�veness (76.47 %) was found in the iden�fica�on of stem borer. The least diagnos�c effec�veness was observed in the iden�fica�on of blast as only half of the respondents (52.95 %) diagnosed correctly. The hindrance for diagnosis in insect pests was due to the complexity in the stages of varia�on in damage which doesn't exactly match with the available symptoms in Crop doctor. This could have led to an i n co m p l et e o r w ro n g d i a g n o s i s . In addi�on, from the above findings, it was observed that iden�fica�on of blast found to be very difficult by the respondents due to the complexity in the appearance. Sl. No. Category No. Percentage (n=153) Overall sa�sfac�on (%) 1 High sa�sfac�on 60 39.22 78.692 Medium sa�sfac�on 57 37.25 3 Low sa�sfac�on 36 23.52 Total 153 100.00 Table 2. Distribu�on of Respondents according to Overall User Sa�sfac�on SI.No. Variables ‘r’ Value Regression co- efficient(B) Standard error ‘t’ value 1 Age (X1) 0.315** 0.098 0.050 1.965 2 Educa�onal status( X2) 0.389** 0.004 0.037 0.096 3 Area under paddy cul�va�on (X3) 0.069 NS 0.143 0.073 1.955 4 Experience in paddy cul�va�on (X4) -0.205* -0.010 0.048 -0.208 5 Informa�on seeking behaviour (X5) 0.418* 0.198 0.067 2.949** (n=153) 6574 The overall user sa�sfac�on of the respondents in u�lizing the crop doctor for paddy pest diagnosis was 78.69 per cent. Further it could be inferred that 76.47%of the respondents were found to have high and medium level of sa�sfac�on and only 23.52 % of the respondents had expressed low level of sa�sfac�on. Influence of Independent Variables on Usability Mul�ple regression analysis was applied to find out the influence of independent variables to the usability 2 among the respondents. The R value was 2 0.516. The R value has shown that all the variables contributed for 51.60 per cent varia�on in usability of the crop doctor among the respondents. Therefore, the equa�on was worked out and given below. Y = -0.32 + 0.098 (X ) + 0.004(X ) 1 1 2 +0.143(X ) -0.010(X ) + 0.067 (X ) +0.117 3 4 5 (X ) + 0.085 (X ) + 0.113 (X ) +0.233 (X ) + 6 7 8 9 0.244 (X ) + 0.085 (X ) + 0.079 (X ) +10 11 12 Table 3. Rela�onship between the Independent Variables and Usability of the Respondents 6 Trainings undergone related to ICT (X6) 0.39** -0.180 0.117 -1.536 7 Mobile applica�on opera�onal ability (X7) 0.571** 0.317 0.085 3.726** 8 Extent of use mobile phone (X 8) 0.265** 0.102 0.113 0.905 9 Awareness on Agricultural mobile applica�on (X9) 0.322** -0.129 0.233 -0.553 10 U�liza�on of agricultural mobile applica�on (X10) 0.39** 0.259 0.244 1.060 Journal of Extension Educa�on 6575 R e s u l t s i n f e r r e d t h a t m o b i l e applica�on opera�onal ability, Informa�on seeking behaviour and Progressiveness had contributed at one per cent level of probability. The remaining variables did not c o n t r i b u t e t o u s a b i l i t y a m o n g t h e respondents. It is notable that one-unit increase ceteris paribus in the following i n d e p e n d e n t v a r i a b l e s v i z . , M o b i l e a p p l i c a � o n o p e r a � o n a l a b i l i t y ( X 7 ) , I n fo r m a � o n s e e k i n g b e h a v i o u r ( X 5 ) Progressiveness (X 13), would increase the Diagnos�c usability level by 3.276, 2.949 and 3.051 units respec�vely. CONCLUSION 'Crop doctor' can be more farmer friendly if farmers are trained for its u � l i z a � o n . C o n t e n t o f t h e m o b i l e applica�on has to be revalidated and steps can be taken to ensure �me to �me upda�ng of pictures. REFERENCES Lewis, J. R. (2014). Usability: lessons learned and yet to be learned. Interna�onal Journal of Human-Computer Interac�on, 30 (9), 663-684. Na�onal Sample Survey Organiza�on (NSSO). (2018). Household social consump�on. 75th round. Ministry of S t a � s � c s a n d P r o g r a m m e Implementa�on, p 1504 Simorangkir, Dhiar, G, Sarwoko, E.A, Sasongko, P.S & Endah, S.N. (2018). Usability tes�ng of corn disease and pest detec�on on a mobile applica�on. P a p e r p r e s e n t e d a t S e c o n d I n t e r n a � o n a l C o n f e r e n c e o n I n f o r m a � c s a n d C o m p u t a � o n a l Sciences. Singh, A.K., Singh, R. Adhiguru, P., Hajare, R Singh, S.K., Bhar�, V.K. & Bhasin, P. (2018). Krishi gyan (1st ed., Vol. 1) [E-book]. ICAR. Effec�veness of a Mobile Paddy Expert System in Pest Diagnosis F value = 11.413 2 R Value = 51.60 ** Significant at one percent level of probability *Significant at five per cent level of probability NS – Non significant 11 A�tude towards based extension services (X11) 0. 426NS 0.046 0.085 0.538 12 Innova�veness (X 12) 0.53** -0.060 0.079 -.0762 13 Progressiveness (X13) 0.510** 0.245 0.080 3.051** SI.No. Variables ‘r’ Value Regression co- efficient(B) Standard error ‘t’ value Page 1 Page 2 Page 3 Page 4 Page 5 Page 6 Page 7 Page 8 Page 9 Page 10 Page 11 Page 12 Page 13 Page 14 Page 15 Page 16 Page 17 Page 18 Page 19 Page 20 Page 21 Page 22 Page 23 Page 24 Page 25 Page 26 Page 27 Page 28 Page 29 Page 30 Page 31 Page 32 Page 33 Page 34 Page 35 Page 36 Page 37 Page 38 Page 39 Page 40 Page 41 Page 42 Page 43 Page 44 Page 45 Page 46 Page 47 Page 48 Page 49 Page 50 Page 51 Page 52 Page 53 Page 54 Page 55 Page 56 Page 57