Image Captioning BotLast Updated on May 3, 2021
This image captioning generator is used to caption the image which takes the image as input and generates the caption of the image as output. It uses CNN and LSTM Units. For training the model, Flickr 8k Dataset is used and for text preprocessing NLTK Library is used. Apart from this Glove Vectors, Encoders and Decoders, Language Models, and VGG16 as Transfer Learning techniques are used to train the model
Skills Used: Python, CNN, LSTM, NLTK, Language Models, Encoders, and Decoders
Share with someone who needs it
Breast Cancer Analysis And Prediction Using MlLast Updated on May 3, 2021
Done by using module called Pandas Profiling
Data Set Information:
Features are computed from a digitized image of a fine needle aspirate (FNA) of a breast mass. They describe characteristics of the cell nuclei present in the image. n the 3-dimensional space is that described in: [K. P. Bennett and O. L. Mangasarian: "Robust Linear Programming Discrimination of Two Linearly Inseparable Sets", Optimization Methods and Software 1, 1992, 23-34].
This database is also available through the UW CS ftp server: ftp ftp.cs.wisc.edu cd math-prog/cpo-dataset/machine-learn/WDBC/
Also can be found on UCI Machine Learning Repository: https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Diagnostic%29
- ID number
- Diagnosis (M = malignant, B = benign) 3-32)
Ten real-valued features are computed for each cell nucleus:
a) radius (mean of distances from center to points on the perimeter) b) texture (standard deviation of gray-scale values) c) perimeter d) area e) smoothness (local variation in radius lengths) f) compactness (perimeter^2 / area - 1.0) g) concavity (severity of concave portions of the contour) h) concave points (number of concave portions of the contour) i) symmetry j) fractal dimension ("coastline approximation" - 1)
The mean, standard error and "worst" or largest (mean of the three largest values) of these features were computed for each image, resulting in 30 features. For instance, field 3 is Mean Radius, field 13 is Radius SE, field 23 is Worst Radius.
All feature values are recoded with four significant digits.
Missing attribute values: none
Class distribution: 357 benign, 212 malignant
Long Term ToolLast Updated on May 3, 2021
My previous project was shear project project that is Long term tool .This tool is used by wind farm owners who want to know in which location it is going to give best profits.
Suppose A wants to start a wind farm business A is having money but he is not aware of wind speeds at particular location ,so he took help from B (The wind pioneers) wind pioneers uses sensor for every wind station to find the wind speed and wind direction. Here wind pioneers role is to record the data which contain wind speeds and wind directions for every hour.
wind pioneers measuring wind speeds at various heights of sensor like ws_120m,ws_100m. For each minute we have some observations ,for every hour the number of observations will increases ,so it is very large data to deal. so we cannot do manual calculations for analyzing this big data. So here we come up with one tool that is long term tool.
I worked on this project along with team this tool provide you interactive software for performing all the analysis like plots, correlation values, scatter plots for finding relationship between two variables. You can just simply download the files that you are working for. It will going to give you everything in detail.
Here we are taking Reference data as NASA data of past 30 years which contains wind speed and wind direction In order to predict the wind speeds of particular location for next 30 years by making use of linear regression model .
Here we are predicting wind speeds of next 30 years for particular location by taking reference data as NASA data.
We are performing linear model for various time periods 1hr,6hr,1 day,3day,7day,10 day,1 month. Again sometimes your weather file and climate file may be differ with time In order to compensate time period we are using time shifting for reference file.
Web AppLast Updated on May 3, 2021
In this project I developed a web app using JSP and Html.
I've also used various styling using CSS.
This was a part of my academic project wherein I created a web app like pinterest .
I added a login page using JSP and if the password is incorrect it directs back to login page and if its correct it will direct to the main page where I've splitted the screen into various frameset using html .
In the main frame I've added marquee of html and at the top I've added various links like home page , know about us , show us our interest.
In the home page options it always directs us to the main page if we are at some other page and click at home page. I've used response.sendRedirect of JSP for the directing options to other pages.
In show us our interest I've added various interest options Using JSP using form of JSP which takes input of interest of the visitors.
On the left side of the main frame there are various options like photography , travel , hairstyle etc.
clicking upon them will direct to the page showing various pictures of that interest.
The main page is login.html used for opening the site.
The website runs of Local host .
The server used for the deployment is APACHE-TOMCAT.
The project was done under the guidence of our JAVA professor , through this we also learned various JAVA scriptlet concepts.
Identifying Water Sources For Smallholder Farmers With AgriLast Updated on May 3, 2021
CIAT and The Zamorano Pan-American Agricultural School, in coordination with the United States Agency for International Development (USAID)/Honduras, began in March the validation and dissemination process of the geographic information system (GIS) tool AGRI (Water for Irrigation, by its Spanish acronym).
What is AGRI?
AGRI was developed in ArcGIS 10.1® for western Honduras with the aim of providing support for decision making in identifying suitable water sources for small drip irrigation systems. These systems cover areas of up to 10 hectares and are part of the U.S. government initiative Feed the Future in six departments of western Honduras (Santa Bárbara, Copán, Ocotepeque, Lempira, Intibucá, and La Paz).
AGRI identifies surface-water sources and sites suitable for rainwater harvesting for agriculture. In addition, AGRI maps the best routes for installing water pipes between the first parcel of the irrigation system and the identified water source. The tool is complemented by deforestation analyses of upstream areas, as an indicator of watershed conservation status.
How was AGRI developed?
Developing this tool required the implementation of a complex framework of spatial analysis that included correcting the terrain Digital Elevation Model (DEM), using weather information derived from remote sensors, hydrological analysis such as estimation of runoff and water balance, and modeling the path with lower costs or fewer difficulties in installing pipes across the landscape. Additionally, it was necessary to do digital soil mapping for some variables.
What does AGRI offer to its users?
AGRI was developed based on the following needs identified by USAID-Honduras in relation to the implementation of small irrigation systems in the country:
- To find the closest water source that permits transportation of the water by gravity to parcels.
- To search for “permanent and sufficient” water sources to establish water outlets.
- To find suitable sites for building reservoirs for the harvest of runoff water.
- To take into account the protection of water sources for human consumption and other protected zones and avoid possible conflicts on water use.
- The tool needs to be easy to use for technicians and agronomists.
- The tool should use information that is readily available in the country.
This application was developed at the request of USAID-Honduras and it responds to the implementation needs of its programs. This implementation was led by the Decision and Policy Analysis (DAPA) area of CIAT with the participation of the soil area, which contributed with the digital soil mapping for the project. Likewise, Zamorano University supported the field validation and the analysis of the legal context related to water use, which serves as a basis for the application of this tool.
Car Price PredictionLast Updated on May 3, 2021
It is a complete end to end project from starting stage of Data preprocessing till the last stage i.e. Model Deployment. In this project first I have done data wrangling which includes data cleaning phase in order to make our dataset more organized. Some of the common steps which I have included in my data cleaning phase are removing of outliers , handling missing values . After that I split my dataset into training and testing dataset with the help of train_test_split function . After that I have passed my training dataset to train my model , In this case I have used Random Forest Regressor as my model and GridSearchCV for the hyperparameter tuning. GridSearchCV helps us to find out the best parameters for our model which ultimately increases the accuracy of our model. After performing all these operations I have tested my model on my testing dataset and Fortunately my model is producing amazing result . I have calculated my accuracy score with the help of a function named accuracy_score. We can also use confusion matrix, classification report to see our model's performance. Accuracy of my model is 98.5%. Now at the end I deployed my model with the help of my basic web development knowledge. It includes some of the files like pickle file, app.py, requirements.txt. Now If I talk about working of my model It is used to predict selling price of a car by taking some of the features like cost price, km driven, type of fuel etc.