تعیین برخی از پارامترهای کیفی آب استخر پرورش ماهی با استفاده از پردازش تصویر

نوع مقاله: مقاله پژوهشی

نویسندگان

1 گروه مهندسی مکانیک بیوسیستم، دانشگاه رازی، کرمانشاه، ایران

2 گروه مهندسی مکانیک بیوسیستم، دانشکده کشاورزی، دانشگاه رازی، کرمانشاه، ایران

چکیده

در این تحقیق، برخی از پارامترهای کیفی آب استخر پرورش ماهی شامل pH، هدایت الکتریکی (EC)، کل مواد محلول (TDS) و کدورت (Turb) به کمک روش‌های استاندارد اندازه‌گیری شده و با استفاده از پردازش تصاویر گرفته شده توسط گوشی تلفن همراه هوشمند و شبکه‌های عصبی مصنوعی پیش‌بینی شدند. همه آزمایش‌ها در استخر پرورش ماهی کپور در شهرستان سنقر واقع در استان کرمانشاه انجام شد. نمونه‌ها از سه عمق مختلف جمع آوری شدند. دوازده مولفه شامل 6 مولفه رنگی ( قرمز، سبز، آبی، سیاه، خاکستری و سفید) و 6 مولفه بافت (میانگین، انحراف معیار، نرمی، گشتاور سوم، یکنواختی و آنتروپی) از نمونه تصاویر گرفته شده استخراج و به عنوان ورودی مدل شبکه عصبی انتخاب شدند. بر اساس نتایج، شبکه با ساختار 4-15-12 (12 نرون در لایه ورودی، 15 نرون در لایه مخفی و 4 نرون در لایه خروجی) به عنوان بهترین مدل برای پیش‌بینی پارامترهای pH، TDS، EC و Turb به ترتیب با ضرایب تبیین 913/0،  993/0، 994/0 و 958/0 و مقادیر RMSE به ترتیب برابر 054/0، 835/1، 766/3 و 262/0 انتخاب شد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Determining of Some Water Quality Parameters in Fish Pond Using Image Processing

نویسندگان [English]

  • Sajad Heydari 1
  • Esmaeil Mirzaee Ghaleh 2
  • Hekmat Rabbani 2
  • Farshad Vesali 2
1 Mechanical Engineering of Biosystem Department, Razi University, Kermanshah, Iran
2 Biosystems Department, razi University, Kermanshah, Iran
چکیده [English]

     In this research some water quality parameters in fish pond includes pH, Electrical Conductivity (EC), Total Dissolved Solids (TDS) and Turbidity (Turb) were determined by standard methods and predicted by image processing using smart phone and artificial neural network. All experiments carried out in Kappur ponds in Sonqor city, Kermanshah province. Samples collected from three different depths. The 12 parameters consisted of 6 color features (red, green, blue, black, gray and white), and 6 tissue features (mean, standard deviation, softness, third torque, uniformity and entropy) were extracted from image samples and were selected as inputs to the neural network model. Based on the results, network with structure of 12-15-4 (12 neurons in the input layer, 15 neurons in the hidden layer and 4 neurons in the output layer) was the best model for predicting the parameters with R2 of 0.913, 0.993, 0.994 and 0.958 for pH, TDS, EC and Turb, respectively. These values for RMSE were 0.054, 1.835, 3.766 and 0.262, respectively.

کلیدواژه‌ها [English]

  • Artificial Neural Network
  • Fish pond
  • Smart phone mobile
  • Quality
  • Water

Abdanan Mehdizadeh, S. Nouri, M. Soltani Kazemi, M. and Amraie, S. (2017). None-destructive investigation of the quality factors in citrus juice during storage using digital image processing. Iranian Food Science and Technology
Research Journal. 13(2), 362-272.

Askari Sari, A. and Velayatzadeh, M. (2010). Applied Hydrochemicals in Aquatic: Azad Islamic University. Ahvaz: 224. (In Farsi).

Bosma, R., Thi, A. A. and Jose, P. (2011). Life cycle assessment of intensive striped catfish farming in the Mekong Delta for screening hotspots as input to environmental policy and research agenda. The International Journal of Life Cycle Assessment, 16(9), 903-915.

Boyd, C. E. (1990). Water quality in ponds for aquaculture. Agriculture Experiment Station, Auburn University, Alabama, 482 p.

Chen, X. D. and Mujumdar, A. (2008). Drying Technologies in Food Proessing. Blackwell Publishing Ltd. 9600 Road, Oxford, OX4 2DQ, United Kingdom. 350 p.

Delince, G. (1992). The ecology of fish pond ecosystem. Springer_Siece. 205 p.

Esmaeilisari, A. (2004). Hayderochemistry and aquaculture. Aslani Publishers. (In Farsi).

Farzanfar, A. (2005). Duplication and breeding of free fish Tehran. Iranian Fisheries Research Institute. (In Farsi).

Gonzalez RC, Woods RE.  (2008). Digital Image Processing (3rd ed.), Prentice Hall.

Kalbasi, M. and Mousavi, F. (1996). Seven-year study of mineral nitrogen changes, phosphorus, electrical conductivity and pH in Zayandehrood water. International Conference on Water Resources. Isfehan: 75-86. (In Farsi).

Keremah, R.I., Davies O. A. and Abezi, I. D. (2014). Physico-Chemical Analysis of Fish Pond Water in Freshwater Areas of Bayelsa State. Nigeria.Greener Journal of Biological Sciences. 4(2): 33-38.    

Khalaji, M., Ebrahimi, E., Hashemenejad, H., Motaghe, E. and Asadola, S. (2016). Water quality assessment of the Zayandehroud Lake using WQI index. Iranian Scientific Fisheries Journal. 25(5): 51-64. (In Farsi).

Maier, H. R., Morgan, N. and Chow, W. K. (2004). Use of Artificial Neural Networks for Predicting Optimal Alum Doses and Treated Water Quality Parameters. Environmental Modeling & Software, 19, 485–494.    

Omid, M., Teimuri, N., Mollazadeh, K. and Rajabi Pour, A. (2016). Isolation of interconnected almonds and their qualitative classification by combining image processing techniques and artificial neural networks. . Iranian Journal of Biosystems Engineering. 46(4). 355-362.

Roosen, J., Marette, S., Blanchemanche, S. and Verer, S. (2009). Dose Health Information Matter For Modifing Consumption Afield Expriment Measuring The Impact of Risk Information on Fish Consumption. Review of Agricultural Economics. 31(1): 2-20. 

Salari, M., Salami Shahid, E., Afzali, S. H., Ehteshami, M., Conti, G. O., Derakhshan, Z. and Sheibani, S. N. (2018). Quality assessment and artificial neural networks modeling for characterization of chemical and physical parameters of potable water. Food and Chemical Toxicology. 118, 212-219.

   Sandh, N., and Finch, R. (1995). Methodology for flow and salinity estimation in the Sacramento-San Joaquin Delta and Suisun Marsh. Chapter 7: Artificial neural networks and their applications, 16th Annual Progress Report. New York: pp: 85.

Taheri Gravand, A., Fattahi, S. and Shahbazi, F. (2017). Estimation freshness of chicken meat Based on Image Processing Techniques and Artificial Intelligence. Iranian Journal of Biosystems Engineering. 48(4). 491-503.

Toosi, A. (2007). The construction and operation of a closed circuit system for semi-dense and dense Trout fish. Faculty of new sciences and technologies. Islamic Azad University. North Tehran Branch. (In Farsi).

Usman, D., Bingari, M., Danba, E. P., David, D. L., Tukur, K. U., Buba, U. N. and Wahedi, J. A. (2015). Physicochemical analysis and fish pond conservation in Kano State. Nigeria. Archives of Applied Sience Research. 7(6): 28–34.

Vanacker, M., Wezel, A., Payet, V. and Robin, J. (2015). Determining tipping points in aquatic ecosystems: The case of biodiversity and chlorophyll α relations in fish pond systems. Ecological Indicators. 52: 184-193.    

Velayatzadeh, M. and Hamidinejad, M. (2012). Importance and position of Indian carp grove in the Iranian fishery industry. First Aquatic Science Conference. Bushehr, 272-276. (In Farsi).

Vesali, F., Omid, M., Kaleita, A. and Mobli, H. ( 2015). Development of an android app to estimate chlorophyll content of corn leaves based on contact imaging. Computers and Electronics in Agriculture. 116: 211-220.

Vosoughi, A. R., Mahdavi, M. M., Salehi, M. and Golkari, M. A. (2012). Intelligent management of qualitative water conditions in the cultivation of common carp (Cyprinus carpio) in experimental tanks. Marine Science and Technology: 11-25. (In Farsi).

Zhongneng, x. and Claude, E (2016). "Reducing the monitoring parameters of fish pond water quality." Aquaculture 465(Supplement C): 359-366.