ساخت و ارزیابی سامانه خبره تشخیص حمله زنبورخوار به کندو به منظور کاهش تلفات

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری گروه مکانیک بیوسیستم و مکانیزاسیون، دانشکده مهندسی‌ زراعی و عمران روستایی، دانشگاه علوم کشاورزی و منابع طبیعی خوزستان، اهواز، ایران

2 استادیار گروه مکانیک بیوسیستم مکانیزاسیون، دانشکده مهندسی‌ زراعی و عمران روستایی، دانشگاه علوم کشاورزی و منابع طبیعی خوزستان، اهواز، ایران

چکیده

نظارت فعالانه کندو با استفاده از یک شبکه حسگر که قادر به ثبت و ضبط تمامی شرایط کندو جهت شناخت شرایط زندگی زنبورهای درون کندو باشد، کمک شایانی به اتخاذ تصمیم توسط زنبوردار در شرایط حمله دشمنان خارجی و جلوگیری از فروپاشی جمعیت زنبورعسل می­نماید. بدین منظور در پژوهش حاضر سامانه­ای خبره جهت تشخیص حمله پرنده زنبورخوار شامل حسگرهای دما، صوت، رطوبت و اتانول توسعه یافت. پس از جمع­آوری داده­ها تحت دو شرایط نرمال و حمله پرنده زنبورخوار (سبزقبا) و استخراج ویژگی در دو حوزه زمان و فرکانس، انتخاب ویژگی با استفاده از الگوریتم ژنتیک و سپس طبقه­بندی ویژگی­ها با استفاده از K نزدیکترین همسایه[1] صورت پذیرفت. بر اساس نتایج بدست آمده از بین 19 ویژگی انتخاب شده، پنج ویژگی شامل آنتروپی طیفی، انرژی صوت، شدت بیشینه صوت، کمینه الکل و فرکانس غالب به ترتیب با 8967، 6018، 1321، 1287 و 809 وقوع به عنوان تأثیرگذارترین ویژگی­ها وارد طبقه­بند شدند. طبقه­بند KNN برای معیارهای صحت، دقت، حساسیت، نمره F، خصوصیت و میانگین هندسی بیشینه (100%) و نرخ مثبت کاذب (FPR) کمینه (صفر) شد که نشان دهنده­ی عملکرد خوب سامانه خبره تشخیص حمله پرنده به کندو است.



[1]. K-Nearest Neighborhood

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Development and Evaluation of an Expert System for Detecting Merops apiaster Attack to the Beehive in Order to Reduce Mortality

نویسندگان [English]

  • Zahra Abdolahzare 1
  • Navab Kazemi 2
  • Saman Abdanan Mehdizadeh 2
1 PhD student of Mechanization of Agricultural Engineering Department, Faculty of Agricultural Engineering and Rural Development, Agricultural Sciences and Natural Resources University of Khuzestan. Ahvaz, Iran
2 Assistant professor of Mechanics of Biosystems Engineering and Mechanization Department, Faculty of Agricultural Engineering and Rural Development, Agricultural Sciences and Natural Resources University of Khuzestan. Ahvaz, Iran
چکیده [English]

Active monitoring of beehive using sensor network that can record all of the hive conditions for  recognition of living status of beehives, could help beekeepers to make a proper decision while attacking foreign enemies, and prevent the collapse of the hive. To this end, in this study, an expert system for detection of Merops apiaster attack was developed which is including: temperature, sound, humidity and ethanol sensors. The data was collected for two conditions (i. e. normal and apiaster attack conditions) and different features in two time and frequency domains were extracted. After that, the most significant features were selected and classified using GA (Genetic Algorithm) and K-NN, respectively. According to results, among 19 selected features, 5 features namely spectral entropy, sound energy, sound maximum, alcohol minimum, and natural frequency were selected as the most effective features with 8967, 6018, 1321, 1287, and 809 occurrence, respectively. K-NN classification had 100% accuracy, precision, recall, Fscore, specificity, and Gmean and zero false positive rate which indicates proper performance of expert system fordetection of apiaster attack to the beehives.

کلیدواژه‌ها [English]

  • smart hive
  • Merops apiaster
  • Genetic Algorithm
  • K-nearest neighborhood
Abdanan Mehdizadeh, S. & Soltani Kazemi, M. (2017). Development and evaluation of a strawberry sorting system using machine vision technique. Journal of Researches in Mechanics of Agricultural Machinery. 6(1), 31-44. In Farsi.

Abdanan Mehdizadeh, S. (2015). Optimization of passive tractor cabin suspension system using ES, PSO and BA. Journal of Agricultural Technology, 11(3), 595-607.

Ahmadi, A. & Ghanbari, Gh. (2012). Growing of honey bee and silkworm. Iran education books printing and publishing company.

Anonymous. (2019). Ministry of Agriculture-Jahad. https://www.maj.ir/Index.aspx in persion

Baxter, M. (2003). Statistics in Archeology. John Wiley and Sons Journal.

Bencsik, M., Bencsik, J., Baxter, M., Lucian, A., Romieu, J. & Millet, M. (2011). Identification of the honey bee swarming process by analysing the time course of hive vibrations. Journal of Computers and Electronics in Agriculture 76,44–50.

Edwards-Murphy, F., Magno, M., M.Whelan, P., O’Halloran, J, & M. Popovici, E. (2016). b+WSN: Smart beehive with preliminary decision tree analysis for agriculture and honey bee health monitorin. Computers and Electronics in Agriculture 124: 211–219.

Ferrari, S., Silva, M., Guarino, M., & Berckmans, D. (2008). Monitoring of swarming sounds in bee hives for early detection of the swarming period. Journal of Computers and Electronics in Agriculture. 64(1), 72-77.

Gaga, V.A. & Esaulov, V.N. (2016). Innovative technologies and modern facilities in beekeeping. IOP Conference Series: Materials Science and Engineering. 142 012022 (doi:10.1088/1757-899X/142/1/012022).

Khazaee, M., Ahmadi, H., Omid, M., Banakar, A. & Moosavian, A. (2013). Feature-level fusion based on wavelet transform and artificial neural network for fault diagnosis of planetary gearbox using acoustic and vibration signals. Insight-Non-Destructive Testing and Condition Monitoring Journal. 55(6), 323-330.‏

Kridi, D. S., de Carvalho, C. G. N., & Gomes, D. G. (2014). A predictive algorithm for mitigate swarming bees through proactive monitoring via wireless sensor networks. In Proceedings of the 11th ACM symposium on performance evaluation of wireless ad hoc, sensor, and ubiquitous networks (pp. 41-47) (Montreal, Canada).

Majumdar, S. & Jayas, D. (2000). Classification of cereal grains using machine vision: II. color models. Trans. ASAE 43 (6), 1677.

Meikle, W., & Holst, N. (2014). Application of continuous monitoring of honeybee colonies. Apidologie, 1e13.

Mohamed, T.M. (2018). Pulsar selection using fuzzy knn classifier. Future Computing and Informatics Journal. 3,1-6.

Nemes, A., Rawls, W.J., & Pachepsky, Ya.A. (2006). Use of the nonparametric nearest neighbor approach to estimate soil hydraulic properties. Soil Science Society of America Journal. 70, 327-336.

Nemes, A., Roberts, R.T., Rawls, W.J., Pachepsky, Ya.A., & Van Genuchten, M.Th. (2008). Software to estimate -33 and -1500 kPa soil water retention using the non-parametric k-Nearest Neighbor technique. Environm Modell. Softw. (23: 254-255).

Purnamadjaja, A.H. & Russell, A. (2005). Pheromone communication in a robot swarm: necrophoric beebehaviour and its replication. Cambridge University Press. 23, 731-742.

Seeley, T. D., Kleinhenz, M., Bujok, B., & Tautz, J. (2003). Thorough warm-up before take-off in honey bee swarms. Naturwissenschaften, 90(6), 256e260.

Soltani Kazemi, M., Abdanan Mehdizadeh, S., Heydari, M & Faregh, S.M. (2017a). Extraction of most effective wavelength of mulberry juice (MorusAlba Var. nigra L.) spectra using different PLSR models. Uloom and Sanaye Ghazayi Journal.. 69(14), 229-241. In Farsi.

Soltani Kazemi, M., Abdanan Mehdizadeh, S., Heydari, M & Faregh, S.M. (2017b).Predict changes of some quality parameters of black mulberry juice (Morusnigra L.) during ripening using machine vision and fractal analysis. Uloom and Sanaye Ghazayi Journal. 5(13), 730-743. In Farsi.

Zacepins, A. & Karasha, T. (2013). Application of Temperature Measurements for Bee Colony. Journal of Engineering for Rural Development, Jelgava. pp. 126–131.

Zacepins, A., Brusbardis, V., Meitalovs, J., & Stalidzans, E. (2015). Challenges in the development of precision beekeeping. Biosystems Engineering Journal, 130, 60e71.

Zacepins, A., Stalidzans, E., & Meitalovs, J. (2012). Application of information technologies in precision apiculture. In Proceedings of the 13th International Conference on Precision Agriculture (ICPA 2012). Indianapolis, USA.