An enthusiastic Machine Learning Engineer and aspiring Data Scientist
MEAT ADULTERATION DETECTION USING THE CONCEPTS OF IMAGE PROCESSING AND MACHINE LEARNING
Published in :
International Journal of Innovative Research in Applied Sciences and Engineering(IJIRASE)
Proceedings of ICCET '20
Abstract: Red meat is an excellent source of essential nutrients such as protein, iron, niacin, zinc and vitamin B12. But in certain regions at butcher shop they mix one type of red meat with other in order to make quick money. For instance in Vijayawada, the butchers allegedly mixed beef with mutton as a measure to earn quick money as beef is much cheaper than mutton. The beef is available at an affordable price of Rs. 250 to Rs. 300 per kg, in comparison to the mutton being sold at approximately Rs. 500 to Rs. 600 per kg in Vijayawada. Meat Adulteration Detector helps to solve the problem of substitution of red meat. In a particular season and region sometimes one particular red meat can be expensive. In that case the meat vendors may substitute the required red meat with some other red meat like pork, buffalo meat, etc. This can be harmful to the consumers who are allergic to certain red meat. Using the meat adulteration detector application all that the consumer will have to do is to take a picture of the raw red meat that he/she is going to purchase and the application rightly tells whether the meat is adulterated by mixing with other red meat or not. The application is based on the concepts of machine learning and computer vision. The image captured by the consumer is compared with the repository of images in the dataset containing images of unadulterated red meat. Using Tensorflow – keras libraries the captured image is converted to gray scale and partitioned into layers, based on the layering done by Keras the image is categorized as adulterated or unadulterated. The features of the source (dataset images) and the target (image captured by the consumer) are extracted and compared using openCV. The feature matching lines are plotted using matplotlib between source and target. Based on the number of feature points matched in the unadulterated labeled image the percentage of freshness of the meat is calculated. This way the customers can ensure whether they are eating the red meat they asked for.
Keywords: Meat, Adulteration, Computer Vision, Machine Learning, Tensorflow, Keras and OpenCV
RHEUMATOID ARTHRITIS DETECTION USING COMPUTER VISION AND MACHINE LEARNING
Published in:
Proceedings of 6th International Conference on Electrical Energy Systems (ICEES - 2020) organized at SSN College of Engineering
Abstract - Rheumatoid arthritis is an auto-immune disease very common disorder among people of age above 35 years. This is caused when the immune system of the human body fails to recognize the foreign cells and healthy human cells. In the case of rheumatoid arthritis the immune system attacks the joints of the human body. It causes inflammation of joints and also affects vital organs like heart, lungs, kidney, etc. Early diagnosis of disease leads to better patient care and reduces Socio-Economic impacts. With the help of the model of RA detector discussed in this paper anyone can easily detect RA at their homes with a single blood test. We have employed the Machine Learning algorithm in the RA monitoring device to detect Rheumatoid arthritis at a very early stage by a simple blood test by checking the factors like ESR, CRP, ANA, RF etc. in the blood to report the result. We deploy a machine learning model based on the measured values of these factors to predict the severity of the disease. Thus we will proceed to explore the clear contents of the detector. In this paper we have discussed the complications involved in the disease if it is failed to be diagnosed at an early stage. In the next section we have discussed about how the monitoring device gets the values of the factors and deploys it into the K-Nearest Neighbours algorithm to manipulate this data and detect the presence of RA. A python code is included to show its application. Finally we have concluded on discussing the future enhancements of this idea.
Keywords — Rheumatoid arthritis, Auto immune, Machine learning, Computer vision and Tensorflow.
DETECTION OF FOOD ADULTERATION USING THE CONCEPTS OF MACHINE LEARNING
Published in:
International Journal of Applied Engineering Research (IJAER)
Abstract -Food adulteration is a process in which the quality of food products is degraded by the addition or substitution of certain chemicals which are injurious for human health. It not only includes the intentional addition or substitution of the ingredient but also the contamination during the period of growth, storage and distribution of food products. Adulteration has become a big business. We belong to a land where our ancestors taught that “food is medicine.” But the reality is that the fruits and vegetables that we consume today no more have vitamins and minerals in them rather they are injected and polished with poisonous chemicals. Adulterants in adulterated food have resulted in a number of diseases and premature deaths. This paper focuses on the detection of adulterated food products using the techniques of image processing using the techniques of image processing using the methods of machine learning like open CV and matplotlib.
Index Terms: Machine Learning, Open CV, Matplotlib and Adulteration detection.
HARNESSING THE POWER OF MACHINE LEARNING FOR AUTOMATING THE REPETITIVE TASKS
Published in:
International Journal of Computer Sciences and Engineering (IJCSE)
Abstract—Why todo hard work? When smart work pays off! There are about 7.6 billion people in the world who do many tasks every day, in which most of the tasks are repetitive. Repetitive tasks can be assisted and done by employing machine learning. Data is generated fromthese repetitive tasks, and this voluminous data is managed by Big Data Analytics and it is analyzed by Machine Learning and provides smart solutions. First of all Machine Learning creates a study pattern based on ourdaily routines and this data will be at a level of complexity that human minds will fail to comprehend. Machine Learning will make it possible for automated system to outthink the human brain by integrating broad information sets and finding correlations. A large number of repetitive tasks that involve manual labor can be automated through Machine Learning. Advances in Machine learning signify a future when devices run on self-learning algorithms and operate independently. They may deduce their own conclusions within certain parameters and develop a context based behavior to interact with human more directly than before. This could mean automating tasks of professionals like doctors (analyzing reports), advocates (for analyzing vast number of judgments and concluding outcomes), etc., even for routine jobs Machine Learning could uncover new potentials and enable human to make the best of their talents. In this article we would focus on how to minimize the timeand energy spent on the repetitive and tedious tasks by assigning them to smart assistants using Machine Learning.
Keywords—Smart work, Machine Learning, Automating, Smart assistants.