http://hdl.handle.net/123456789/567 2026-04-16T16:12:42Z 2026-04-16T16:12:42Z KHADER, SUMAYYA http://hdl.handle.net/123456789/9946 2022-06-27T22:28:02Z 2022-06-11T00:00:00Z

PREDICTION OF DIABETES EMPOWERED WITH FUSED MACHINE LEARNING PREDICTION OF DIABETES EMPOWERED WITH FUSED MACHINE LEARNING Done by SUMAYYA KHADER KHADER, SUMAYYA In the medical field, it is essential to predict diseases early to prevent them. Diabetes is one of the world's largest ongoing chronic metabolic disorders. In modern lifestyles, sugar and fat are typically present in our dietary habits, which have increased the risk of diabetes. To predict the disease, it is extremely important to understand its symptoms. Currently, machine-learning (ML) algorithms are valuable for disease detection. ML algorithms are currently useful for the detection of diseases, but the previous research models are less accurate because they usually focused on pre-processing techniques, data balancing, and various types of supervised and semi supervised learning models. Therefore, it is required to find new technique with decision level fusion which would be able to integrate the accuracy of multiple machine learning algorithms with high disease detection accuracy. For this purpose, a fused ML model is proposed which uses two supervised machine-learning approaches including ANN and SVM followed by weight-based decision level fusion. In the Machine Learning Fusion stage, Weight-based fusion is applied to the actual output of SVM and ANN results for final prediction. The fused trained model is then stored in the local storage for future use. Based on the user input, the fused model predicts whether the patient is diabetic or not. Through this diagnosis model, we can save several lives. Moreover, the death ratio of diabetes can be controlled if the disease is diagnosed, and preventative measures are taken in early stage.

2022-06-11T00:00:00Z A S, Subin http://hdl.handle.net/123456789/9944 2022-06-27T22:28:01Z 2022-06-11T00:00:00Z

INVENTO A S, Subin INVENTO is a web platform directed toward helping creative ideas get off the ground. It's entirely driven by crowd support. Creators set up a page to display their project's details and prototypes using text, video, and photos. The creators set a product pre-booking goal and a deadline. Each supporters needs to support the project by booking a product from the website. When each supporter buy/support a product the money will be transferred to the admin panel and if the product reaches their goal, then the money will be transferred to the innovators account by admin. When enough backers have supported the project, the creator can develop and produce their vision. Depending on the project's complexity, backers may have to wait months to see the finished product. By supporting creators on this website, the creators have a better and strong proof to submit before any sponsors or bank loans. Because of the huge number of customers to the project the sponsors nor the can cannot refuse the project from publishing. INVENTO want creative people even those who’ve never made anything before to take the wheel. INVENTO help creators connect directly with their communities, putting power where it belongs.

2022-06-11T00:00:00Z C A, Sayooj http://hdl.handle.net/123456789/9942 2022-06-27T22:27:42Z 2022-06-11T00:00:00Z

IOT Based Soil Monitoring and Automated Irrigation System C A, Sayooj India is top in the production of agricultural products and also faces many problems due to lack of soil monitoring, water supply and its usage. We here by introducing this device mainly for the farmers but also for other users who are indented to agriculture. They can even control and know the status of the soil they cultivate using the technology IOT. Internet of Things (IoT) technology has brought revolution to each and every field of common man’s life by making everything smart and intelligent. IoT refers to a network of things which make a self configuring network. The development of Intelligent Soil monitoring IoT based devices is day by day turning the face of agriculture production by not only enhancing it but also making it cost-effective, reducing wastage of water, fertilizers and time. The aim / objective of this report is to propose “IoT based Soil Monitoring and Automated Irrigation System” assisting farmers in getting Live Data (Soil Moisture, Temperature and PH) for efficient environment monitoring and for the sustainable usage of water and fertilizers. It will enable them to increase their overall yield and quality of products, We also automate the irrigation system for the farmers. The project being proposed via this report is integrated with Arduino Technology mixed with different Sensors and a WiFi module producing live data feed that can be obtained from an application developed using MIT app Inventor with Firebase. Even from the application we can control the motor driver also by setting automatic or manual modes for irrigation.

2022-06-11T00:00:00Z Saji, Sarath http://hdl.handle.net/123456789/9940 2022-06-28T01:43:44Z 2022-06-11T00:00:00Z

Agri Doctor Saji, Sarath The occurrence of plant diseases has a negative impact on agricultural pro- duction. If plant diseases are not discovered in time, food insecurity will increase. Early detection is the basis for effective prevention and control of plant diseases, and they play a vital role in the management and decision- making of agricultural production. In recent years, plant disease identification has been a crucial issue. Disease-infected plants usually show obvious marks or lesions on leaves, stems, flowers, or fruits. Generally, each disease or pest condition presents a unique vis- ible pattern that can be used to uniquely diagnose abnormalities. Usually, the leaves of plants are the primary source for identifying plant diseases, and most of the symptoms of diseases may begin to appear on the leaves. Farmers with less experience may misjudgment and use drugs blindly during the identification pro- cess. Quality and output will also bring environmental pollution, which will cause unnecessary economic losses. To counter these challenges, research into the use of image processing techniques for plant disease recognition has become a hot research topic. The general process of using traditional image recognition processing technol- ogy to identify plant diseases and use the K-means clustering method to segment the lesions regions, and combined the global color histogram (GCH) color coher- ence vector (CCV) local binary pattern (LBP), and completed local binary pat- tern (CLBP) was used to extract the color and texture features of brown spots, and three kinds of diseases were detected and identified based on improved support vector machine (SVM), and the classification accuracy reached 93percent.

2022-06-11T00:00:00Z