Python World Map Geovisualization Dashboard Using Covid DataLast Updated on May 3, 2021
1) Learn a cool hack using one line of code to convert a jupyter nootebook into a dashboard.
2) Work with "COVID-19 Data Repository by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University"
3)After you complete this project, you get a jupyter notebook of all the work you covered (including gifs). It acts as a useful learning tool that you can refer to at any time in the future.
4) Important terminology and definitions are explained.
Share with someone who needs it
Customer Management SystemLast Updated on May 3, 2021
Customer Management System (CMS) deals with the collection and storage of contact information of customers, addresses, phone numbers and other contact details. Computerized system poses high speed of processing precision, storage, its versatility and high retrieval system makes possible the completion of task that could never have been achieved with manual system because of the difficulty of completing them on time for the results to be useful. In the present world it is very important for the organizations, shops etc. to maintain their customers data. This project will help the them to maintain their customers data. With the help of this project such firms will be able keep record of their customers. Since all the work is done through the system, there will be no usage of paper. Data about the customers will be stored in a secured way in order to avoid the misuse of information. Python programming language is used in the project. We will save the data in the database as well as in pickle format in the file. This project tends to use latest advancements in information technology and provide a CRUD operation. This will help many stakeholders of these firms to quickly do some basic operations instead of doing same manually.
Dog And Cat Image ClassificationLast Updated on May 3, 2021
Dog and cat image classification
The project classifies an image into a dog or a cat. The model has been built by using Convolutional Neural Network or also known as CNN. CNN is a part of deep learning which deals with analysing images. It is widely used for image recognition and classification. This project was developed by using Python. Python is an interpreted, high-level and general-purpose programming language. Python was implemented on Jupyter Notebook.
Libraries and Functions used-
Various Python libraries were used while developing the ML model. The tools used were:
1. tensorflow- It focusses on training of neural networks
2. load_model- This library is used to load a model and construct it identically
3. tkinter- It is a python GUI toolkit
4. PIL- It is Python Image Library that supports in doing operations with images
5. Filedialog- It is used for selecting a file/directory
6. Playsound- It is used for playing audios
7. ImageDataGenerator- It is a class of Keras library used for real-time data augmentation
8. Flow_from_directory- It is an image augmentation tool
9. keras Preprocessing- It is the data preprocessing module of keras which provides utilites for working with image data.
10. load_img- It loads the image in PIL format.
11. img_to_array- It changes the image into a numpy array.
12. expand_dim- It expands the dimension to add an extra dimension for a batch of only one image with axis=0.
In this neural network 2 activation functions were used-
The methods followed were:
1. Pre-processing of data
1.1 Training data
1.2 Testing data
2. Building CNN
2.1 Adding the first convolution layer
2.3 Adding the second convolution layer
2.5 Full connection
2.6 Output layer
The accuracy of last(50) epoch was 97%
This function loads the ML model and take the image input given by the user and then pre-process it. Later the pre-processed image goes as an input to ML model which gives the prediction. For our output, this code plays a sound corresponding to the prediction.
The final page asks the user to select an image from the local computer. The tab’s name is ‘Image Classifier’.
Once the user selects the image, the model successfully predicts whether the image is of a dog or a cat. The model also plays a sound stating about the prediction.
Predicting Employees Under Stress For Pre-Emptive Remediation Using Machine Learning AlgorithmLast Updated on May 3, 2021
With the ongoing COVID-19 pandemic, businesses and organizations have acclimated to unconventional and different working ways and patterns, like working from home, working with limited employees at office premises. With the new normal here to stay for the recent future, employees have also adapted to different working environments and customs, which has also resulted in psychological stress and lethargy for many, as they adapt to the new normal and adjust their personal and professional lives. In this work, data visualization techniques and machine learning algorithms have been used to predict employees stress levels. Based on data, we can develop a model that will assist to predict if an employee is likely to be under stress or not. Here, the XGB classifier is used for the prediction process and the results are presented showing that the method facilitates getting a more reliable model performance. After performing interpretation utilizing XGB classifier it is determined that working hours, workload, age, and, role ambiguity have a significant and negative influence on employee performance. The additional factors do not hold much significance when associated to the above discussed. Therefore, It is concluded that concluded that increasing working hours, role ambiguity, the workload would diminish employee representation in all perspectives.
Link for paper: https://ieeexplore.ieee.org/document/9315726?denied=
Vehicle Density Based Traffic Optimization/ Management (Ml And Iot)Last Updated on May 3, 2021
As the vehicle population is rapidly increasing day by day, the cities are facing a huge traffic issue. We know how a traffic system work in current days. Even though there are no vehicles on the green side at the junction, a vehicle on the red side has to wait till the given time. This system has a drawback of traffic delay. On an average most of the junctions in the cities and towns facing this issue
To overcome this problem of over delaying in the traffic, IoT plays a major role. Our idea is: placing IoT sensors at a distance of 100 meters range from the junction we can calculate an average count of vehicles on all the sides. Using this count as main characteristic the traffic light works dynamically that is the roads having high to low count of vehicles has green signal in decreasing order. To increase efficiency of vehicle count we implemented vehicle count using image processing
1. Raspberry Pi
2. Camera (web cam)
Vehicle count using image processing
• At the junction the vehicles coming from different directions may face traffic issues.
• By image processing technique we can capture the video of number of vehicles coming in different directions.
• By connecting raspberry pi we can get the count of vehicles in different directions at the junction.
• Based on the count obtained from different directions the traffic is cleared as per the maximum count of vehicles.
• The traffic system is prioritized in decreasing order of the count of vehicles ie, the road with high vehicle count will be given first priority and so on.
• The input in the form of video is captured by web cam, After the vehicle count is done, the control of traffic lights is done using Raspberry Pi
Advantages in real life:
1.Optimizing traffic inconsistency
2.Reducing air pollution
3.Reducing noise pollution
4.Priority traffic control
My role in the project:
This is a project for HACKATHON where we team of 8 members worked for 2 days. I worked mostly on the coding part for video processing in the project, I also developed an optimized code for prioritizing the traffic lights, this project contains various code segments one for image processing using cv module in python, one for vehicle count and other for prioritization.
Hospital ReadmissionLast Updated on May 3, 2021
Hospital readmissions of diabetic patients are expensive as hospitals face penalties if their readmission rate is higher than expected and reflects the inadequacies in health care system. For these reasons, it is important for the hospitals to improve focus on reducing readmission rates.
We have to Identify the key factors that will influence readmission for diabetes and to predict the probability of patient readmission.
A leading hospital in the US is suddenly seeing increase in the patient readmission in less than 30 days. This is serious concern for the hospital as it may indicate insufficient treatment or diagnosis when the patient was admitted first and later released under clean bill of health. Hence it is in Hospital’s interest to support their diagnosis by a better predictive model which we are going to build.
Here the objective is: Classify the patients treated by this hospital into two primary categories:
· Readmitted within 30 days
· Not readmitted
The dataset chosen is that available on the UCI website which contains the patient data for the past 10 years for 130 hospitals. The code has been written in Python using different libraries like scikit-learn, seaborn, matplotlib etc. Different machine learning techniques for classification and regression like Logistic regression, Random forest etc .have been used to achieve the objective.