http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Classifying Indian Medicinal Leaf Species Using LCFN-BRNN Model
( Kiruba Raji I ),( Thyagharajan K. K ),( Vignesh T ),( Kalaiarasi G ) 한국인터넷정보학회 2021 KSII Transactions on Internet and Information Syst Vol.15 No.10
Indian herbal plants are used in agriculture and in the food, cosmetics, and pharmaceutical industries. Laboratory-based tests are routinely used to identify and classify similar herb species by analyzing their internal cell structures. In this paper, we have applied computer vision techniques to do the same. The original leaf image was preprocessed using the Chan-Vese active contour segmentation algorithm to efface the background from the image by setting the contraction bias as (v) -1 and smoothing factor (μ) as 0.5, and bringing the initial contour close to the image boundary. Thereafter the segmented grayscale image was fed to a leaky capacitance fired neuron model (LCFN), which differentiates between similar herbs by combining different groups of pixels in the leaf image. The LFCN’s decay constant (f), decay constant (g) and threshold (h) parameters were empirically assigned as 0.7, 0.6 and h=18 to generate the 1D feature vector. The LCFN time sequence identified the internal leaf structure at different iterations. Our proposed framework was tested against newly collected herbal species of natural images, geometrically variant images in terms of size, orientation and position. The 1D sequence and shape features of aloe, betel, Indian borage, bittergourd, grape, insulin herb, guava, mango, nilavembu, nithiyakalyani, sweet basil and pomegranate were fed into the 5-fold Bayesian regularization neural network (BRNN), K-nearest neighbors (KNN), support vector machine (SVM), and ensemble classifier to obtain the highest classification accuracy of 91.19%.
K. Kalaiarasi,N. Sindhuja 한국전산응용수학회 2024 Journal of applied mathematics & informatics Vol.42 No.2
This study proposes a fuzzy inventory model for managing large-scale production, incorporating cost considerations. The model accounts for two types of expenditure scenarios—parametric and exponential. Uncertainty surrounds holding costs, setup costs, and demand rates. The approach considers a supply chain system with a complex manufacturing process, factoring in transportation costs based on the quantity of goods and distance between the supplier and retailer. The initial crisp model is then transformed into a fuzzy simulation, incorporating specific fuzzy variables affecting inventory costs. The proposed method significantly reduces overall inventory costs for the entire supply chain. Retailer demand is linked to inventory levels, and vendor/distributor storage deteriorates over time. The fuzzy condition assumes hexagonal variables for all associated factors. The study employs the signed distance method for defuzzification to determine the optimal order quantity with hexagonal fuzzy numbers. Mathematical examples are provided to illustrate the practicality of the proposed approach.
Co-Normal Product For Intuitionistic AntiFuzzy Graphs
K. Kalaiarasi,L. Mahalakshmi,Nasreen Kausar,A. B. M. Saiful Islam 한국지능시스템학회 2023 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.23 No.1
This study introduces and analyzes the conormal product of intuitionistic anti-fuzzy graphs (IAFGs) and analyzes certain fundamental theorems and applications. Further, new notions on complete and regular IAFGs were introduced, and the conormal product operation was applied to these IAFGs. We showed that the conormal product of two IAFGs could be used and analyzed important results showing that the conormal product of complete, regular, and strong IAFGs is an IAFG.