• Title/Summary/Keyword: Inp

Search Result 63, Processing Time 0.031 seconds

Classification of Plants into Families based on Leaf Texture

  • TREY, Zacrada Francoise;GOORE, Bi Tra;BAGUI, K. Olivier;TIEBRE, Marie Solange
    • International Journal of Computer Science & Network Security
    • /
    • v.21 no.2
    • /
    • pp.205-211
    • /
    • 2021

  • Plants are important for humanity. They intervene in several areas of human life: medicine, nutrition, cosmetics, decoration, etc. The large number of varieties of these plants requires an efficient solution to identify them for proper use. The ease of recognition of these plants undoubtedly depends on the classification of these species into family; however, finding the relevant characteristics to achieve better automatic classification is still a huge challenge for researchers in the field. In this paper, we have developed a new automatic plant classification technique based on artificial neural networks. Our model uses leaf texture characteristics as parameters for plant family identification. The results of our model gave a perfect classification of three plant families of the Ivorian flora, with a determination coefficient (R2) of 0.99; an error rate (RMSE) of 1.348e-14, a sensitivity of 84.85%, a specificity of 100%, a precision of 100% and an accuracy (Accuracy) of 100%. The same technique was applied on Flavia: the international basis of plants and showed a perfect identification regression (R2) of 0.98, an error rate (RMSE) of 1.136e-14, a sensitivity of 84.85%, a specificity of 100%, a precision of 100% and a trueness (Accuracy) of 100%. These results show that our technique is efficient and can guide the botanist to establish a model for many plants to avoid identification problems.

  • https://doi.org/10.22937/IJCSNS.2021.21.2.24 인용 PDF KSCI

Application of IFC Standard in Interoperability and Energy Analysis

  • Hyunjoo Kim;Zhenhua Shen
    • International conference on construction engineering and project management
    • /
    • 2013.01a
    • /
    • pp.87-93
    • /
    • 2013

  • In this research, a new methodology to perform building energy analysis using Industry Foundation Classes (IFC) standard has been studied. With the help of Archicad 14 modeling software, a 3D test model is generated and then exported to IFCXML format. A ruby code program retrieves the building information from the resulting IFCXML file using Nokogiri library. An INP file is created and gets ready for next energy analysis step. DOE 2.2 program analyzes the INP file and gives a detailed report of the energy cost of the building. Case study shows when using the IFC standard method, the Interoperability of the energy analysis is greatly improved. The main stream 3D building modeling software supports IFC standard. DOE 2.2 is able to read the INP file generated by IFC file. This means almost any 3D model created by main stream modeling software can be analyze in terms of energy cost Thus, IFC based energy analysis method has a promising future. With the development and application of IFC standard, designers can do more complex and easy-to-run energy analysis in a more efficient way.

  • PDF

Fault diagnosis of a logical circuit by use of input grouping method

  • Miyata, Chikara;Kashiwagi, Hiroshi
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1996.10a
    • /
    • pp.279-282
    • /
    • 1996

  • The authors have already proposed a method for grouping of inputs of a logical circuit under test (LCUT) by use of M-sequence correlation. We call this method as input grouping (IG) method. In this paper, the authors propose a new method to estimate the faulty part in the circuit by use of IG when some information on the candidate of faulty part can be obtained beforehand. The relationship between IG and fault probabilities of a LCUT, and undetected fault ratios are investigated for various cases. Especially the investigation was made in case where the IG was calculated by use of n correlation functions (I $G_{inp}$). From the theoretical study and simulation results it is shown that the estimation error ratio of fault probabilities and undetected fault ratio of LCUT are sufficiently small even when only a part of correlation functions are used. It is shown that the number of correlation functions which are to be memorized to calculate IG can be considerably reducible from 2$^{n}$ - 1 to n by use of I $G_{inp}$. So this method would be very useful for a fault diagnosis of actual logic circuit.uit.

  • PDF