---

Composites usage according to their properties such as high strength to weight ratio, high resistance to corrosion and their ability to build complex shapes in different industries are increased, but due to their Vulnerability against unwanted impact loads, their usage has been limited. Relatively higher costs of carrying out low velocity impact (LVI) test and data sampling limit due to short experiment time in one side and adaptation of quasi-static impact (QSI) test results with LVI on the other, convinced researchers to use QSI instead of LVI. This research investigated the effect of different percentage of nanoclay (1%, 3%, 5% and 7%) on impact properties of glass-epoxy composite. For this purpose, QSI test was used to forecast this nano-composite’s behavior. To disperse and distribute nanoclay homogeneously inside the resin, mechanical and ultrasonic mixers have been used; EDAX photograph token from nano-resin section confirmed the success of this process. QSI test results showed that adding 3% nanoclay to glass-epoxy composite, increases absorbed energy up to 16% and stiffness up to 12%. It was also determined by perusing SEM photographs that specimens containing 7% nanoclay had a decreased in mechanical properties due to adhesion of nanoparticles.

---

Micromorphological characteristics of seed sculpturing might be effective in circumscribing the infra-specific taxa in the genus Vicia. The present study was conducted to determine whether microstructural and seed coat texture data obtained from SEM images can serve as sufficient tools for delimiting Vicia genus. Other than visual inspections, a variety of texture-based methods, including the four conventional approaches of GLCM, LBP, LBGLCM, and SFTA, and the four pre-trained convolutional neural networks, namely, ResNet50, VGG16, VGG19, and Xception models were employed to extract features and to classify the species of Vicia genus using SEM images. In a subsequent step, the four unsupervised k-means, Mean-shift, agglomerative, and Gaussian mixture classification methods were used to group the identified Vicia spices based on the underlying features thus extracted. Moreover, the three supervised classifiers of Multilayer Perceptron Network (MLP), Support Vector Machine (SVM), and k-Nearest Neighbor (kNN) were compared in terms of capability in discriminating the different visually-identified classes. SEM results showed that three classes might be identified based on the micromorphological character-species connections and that the differences among the species in the Vicia genus and the validity of Vicia sativa could be confirmed. Regarding the performance of the classifiers, SFTA textural descriptor outperformed the GLCM, LBP, and LBGLCM algorithms, but yielded a decreased accuracy compared with deep learning models. The combined Xception model and a MLP classifier was successful to discriminate the species in the Vicia genus with the best classification performances of 99 and 96% in training and testing, respectively.