Browsing by Author "Sharmin, Israt"

Now showing 1 - 3 of 3

A Machine Vision Approach for Recognizing Coastal Fish
(Scopus, 22) Raihan, Afiq; Sharmin, Israt; Khan, B M Marjan; Jabiullah, Md. Ismail; Habib, Md. Tarek
t Coastal fish is one of the prominent marine resources, which takes a necessary role in the economic growth of a country. Because of environmental issues along with other reasons, not only most of the marine resources are diminishing but also many coastal fishes are getting extinct gradually. As a result, the young peoples have insufficient knowledge of coastal fish. This issue can be solved with the use of vision-based technologies. To deal with this situation, a coastal fish recognition system based on machine vision is conceived, which can be approached by the images of coastal fish that are captured with a portable device and identify the fish to recognize fish. Numerous experimental analyses are executed to exhibit the benefit of this proposed expert system. In the beginning, the conversion of a color image into a gray-scale image occurs and the gray-scale histogram is developed. Using the histogram-based method, image segmentation is conducted. After that, a set of sixteen features comprising four classes is extracted to be fed to a classifier. For reducing the number of features, PCA is applied. To recognize coastal fish, five classical machine learning classifiers are performed, where k-NN provides a potential accuracy of up to 98.89%.
Machine Vision Based Local Fish Recognition
(SN Applied Sciences, Springer, 2019-11-01) Sharmin, Israt; Islam, Nuzhat Farzana; Jahan, Israt; Joye, Tasnem Ahmed; Rahman, Md. Riazur; Habib, Md. Tarek
Bangladesh has its own abundance of water resources which helps to identify its customs that are related to freshwater fish. Due to environmental issues along with some other reasons, the amount of water resources of Bangladesh is reducing day-by-day. Consequently, many of our territorial freshwater fishes are getting abolished. Thus, the new generation people of Bangladesh lacks the knowledge of local freshwater fish. For this problem, a solution has been found with the collaboration of vision-based technology. As a solution, a machine-vision based local freshwater fish recognition system is presented that can be proceed with an image of fish captured with a mobile or handheld device and recognize the fish in order to introduce the fish. To demonstrate the utility of the proposed expert system, several experiments are performed. At first, a set of fourteen features, which consists of four types of features, are presented. Then the color image has been converted into gray-scale image and the gray-scale histogram is formed. Image segmentation takes place using histogram-based method and then the features are extracted. PCA is used for decreasing the feature numbers. Three classifiers are used for recognizing fish, where SVM gives the highest accuracy showing a value of 94.2%.
Preparation and evaluation of carbon nano tube based nanofluid in milling alloy steel
(Department of Industrial and Production Engineering, 2020-01-04) Sharmin, Israt; Dhar, Dr. Nikhil Ranjan
In machining, there is always a problem with heat generation and friction produced during the process as they consequently affect cutting force and surface finish. In the present decade, CNT water based nanofluids have become a promising new solution in high production machining because of its good fluidity and high thermal conductivity. This research work evaluates the performance of nano fluid using 0.3% volume of Single Walled Carbon Nano Tubes and 0.6% volume of Sodium Dodecyl Sulphate surfactant in deionized water for milling operation on 42CrMo4 steel material. Milling was performed without any fluid, with conventional Aquatex 3180 oil based cutting fluid and with nano fluid. The fluid was delivered through a specially designed and developed rotary liquid applicator designed in such a way so that it can deliver fluid at critical zones during surface milling. Cutting parameters in the machining process were cutting speed, table feed and depth of cut. Cutting forces and surface finish on work piece were measured as responses while turning under the three conditions and responses obtained in three different conditions of milling are compared. It is found that application of SWCNT based nano fluid resulted in maximum 33% lesser surface roughness than machining without any fluid whereas conventional cutting fluid resulted in 16% lesser surface roughness. The use of nano fluid also reduced cutting force by49% but conventional cutting fluid reduce the cutting force only by 26% with respect to dry milling. Thus, CNT-water based nano fluid performed better than the conventional, oil based cutting fluid for milling of 42CrMo4 steel. Finally, both ANN and RSM models were developed for prediction of cutting force and surface roughness as a function of cutting parameters. The models were proved to be successful in terms of agreement with experimental results and can be used in cutting process for efficient and economic production by forecasting the cutting force and surface roughness in surface milling operations.