Top 10 Real Time Engineering Projects for Students 2023

INTRODUCTION

Diabetes affects a significant portion of the global population, especially young people. The 5G-Smart Diabetes plan aims to improve treatment and reduce complications by incorporating 5G frameworks, AI, and personalized data usage. It emphasizes cost-effective, user-friendly, tailored, sustainable, and valuable insights.

Objective

The 5G-Smart Diabetes project uses 5G technology and advanced algorithms to enable personalized monitoring and prediction of diabetes conditions. Utilizing wearable devices and cloud-based solutions, it uses decision trees, SVM, ANN, and Ensemble algorithms to predict diabetes indicators. This approach aims for cost-effective, automated, and accurate insights, improving diabetes management and early intervention.

Methodology

1. Upload Files: In this module, we can upload the required datasets, such as diabetes data, to the cloud server. These datasets serve as the basis for training and testing various algorithms for diabetes prediction.
2. Pre-process Dataset: This step involves cleaning and preparing the uploaded dataset for analysis. It includes handling missing values, normalizing data, and converting categorical variables. Clean data ensures accurate and reliable results from subsequent algorithms.
3. Pre-process Dataset: This step involves cleaning and preparing the uploaded dataset for analysis. It includes handling missing values, normalizing data, and converting categorical Run Decision Tree Algorithm: Decision trees are utilized here to build a predictive model for diabetes. This algorithm creates a tree-like structure of decisions based on features from the dataset, aiding in classifying patients into different diabetes categories. Decision trees are interpretable and useful for understanding the factors influencing predictions.l variables. Clean data ensures accurate and reliable results from subsequent algorithms.
4. Run SVM Algorithm: A Support Vector Machine (SVM) is employed to separate diabetes patients from non-diabetic individuals by finding an optimal hyperplane in a high-dimensional space. SVM is well-suited for binary classification tasks and can handle complex relationships in data.
5. Run ANN Algorithm: Artificial Neural Networks (ANN) simulate the human brain’s functioning and are excellent for capturing intricate patterns in data. The ANN algorithm in this module learns from the dataset to predict diabetes conditions based on patient features, contributing to accurate predictions.
6. Run Ensemble Algorithm: The Ensemble Algorithm combines the outputs of Decision Tree, SVM, and ANN algorithms to enhance overall prediction accuracy. By leveraging the strengths of multiple algorithms, the ensemble approach aims to reduce individual algorithm biases and improve the reliability of predictions.
7. Accuracy Graph: This module generates a graphical representation of the accuracy achieved by each algorithm—Decision Tree, SVM, ANN, and Ensemble. The graph provides a comparative view of their performance, helping to choose the most suitable algorithm for diabetes prediction in this context.
8. Start Cloud Server: The Cloud Server module initiates the cloud-based infrastructure, which acts as a central hub for data storage and analysis. The server communicates with user applications, processes incoming data, and applies the trained models to predict diabetes conditions.

Output Explanation Video

Conclusion

The 5G-Smart Diabetes project integrates 5G technology, AI algorithms, and wearable devices for a cost-effective, user-friendly diabetes management solution. It predicts high-accuracy indicators, enhances data sharing and analysis, and provides personalized insights. This innovative approach has the potential to revolutionize diabetes care, promoting timely interventions and improving patient well-being worldwide.

Result Analysis

In this paper author is using today’s 5G technology to monitor condition of diabetic patients with low cost. Now-a-days many people’s are suffering with diabetic disease due to work stress or unhealthy life styles and peoples will not know about the current health condition till symptoms appear or diagnosis through medical check-up and the condition of disease will be severe by that time and there is no possible way to get that intimation prior.

Diabetes will be of two type’s diabetes 1 and diabetes 2. Diabetes 2 require hospitalization and in diabetes 1 condition we can monitor patient and alert him or doctors about his current condition using below techniques.

1. Cost: this technique requires no cost compare to hospitalization as users will be having wearable device which will read his condition and inform to patients and hospitals using his smart phone.
2. Comfortable: as these wearable devices are small and patients can wear it and keep working on his daily activities.
3. Sustainability: Devices can be in contact with hospital servers which will have complex data mining algorithms running on it. After receiving patient data server will run those algorithms to predict patient condition and send report back to devices.

   In propose paper we are using Decision Tree, SVM, Artificial Neural Network algorithms from python to predict patient condition from his data. To train these algorithms we are using diabetes dataset. To predict data efficiently author is using Ensemble Algorithm which is combination of Decision Tree, SVM and ANN algorithm. Training model of all this three algorithms will be merging inside Ensemble Algorithm to get better accuracy and prediction.

4. Personalization: In this technique one patient can share his data with other patient based on distance between cloud servers they are using to store data. Here we are using dataset so sharing is not possible but i am making all predicted test data values to be open so all users can see or share it.
5. Smartness: this technique will be consider as smart as its require no human effort to inform patient about current condition.

Here I design two applications to implement above technique

1. Cloud Application: This application act like a cloud server and storage and train dataset model with various algorithms such as decision tree, SVM and ANN and Ensemble algorithms.
2. User Application: In this application we will upload some test data and will be consider as user sense data and this data will be send to cloud server and cloud server will apply decision and SVM and ANN model on test data to predict patient condition and send resultant data to this application. As we don’t have sensors to sense data so we consider uploaded test data as sense data. Here we don’t have user details to share data so i am keeping all predicted data to be open so all users can see and share.

Pregnancies,Glucose,BloodPressure,SkinThickness,Insulin,BMI, DiabetesPedigreeFunction,Age,Outcome
6,148,72,35,0,33.6,0.627,50,1
1,85,66,29,0,26.6,0.351,31,0
8,183,64,0,0,23.3,0.672,32,1
1,89,66,23,94,28.1,0.167,21,0

In above dataset values first record contains dataset column names and other records are the dataset values. All dataset records in last column contains class values as 0 and 1. 1 values indicates patient values show diabetes 1 symptoms and 0 value indicates patient has normal values but indicates diabetes 1 symptoms. Above dataset is used for training and test data will have only patient data but no result values such as 0 or 1. This test data will be applied on train model to predict as 0 or 1.

Below are test values and this values are inside ‘users.txt’ file inside User/data folder
6,148,72,35,0,33.6,0.627,50
1,85,66,29,0,26.6,0.351,31
8,183,64,0,0,23.3,0.672,32
1,89,66,23,94,28.1,0.167,21

In above test records we can see there is no 0 and 1 values and cloud server will receive and predict values for above test records

Screen shots

Double click on ‘run.bat’ file from ‘Cloud’ folder to start cloud server and to get below screen