Pinned Repositories
3d-reconstruction
Automatic-Number-Plate-Recognition
Emotion-Recognition
Emotion Recognition using Deep Convolutional Neural Networks: Used a Deep CNN to recognize facial expressions from images or video/camera stream out of seven basic human expression using Python.
Iforest-Machine-learning-algorithm
MRI-Based-Brain-Tumor-Detection-using-CNN-and-Image-Processing
Introduction- Brain tumor detection project This project comprises a program that gets a mind Magnetic Resonance Image (MRI) and gives a finding that can be the presence or not of a tumor in that cerebrum. Why this task? In clinical analysis, checking mind tumors among a lot of MRI pictures, as a rule, take specialists much time. For instance, in tests of this undertaking, a patient has around 200 MRI pictures, however, tumor tissues just show up in 15 pictures. Thusly, this venture intends to naturally recognize tumor tissues in a huge measure of MRI picture information. Our objectives: 1) naturally, recognize if tumor tissue shows up in the MRI picture 2) automatical mind tumor division in MRI picture The outcome when we give a picture to the program is a likelihood that the cerebrum contains a tumor, so we could organize the patients which attractive reverberation have higher probabilities to have one, and treat them first. Another objective could be to move the obligation of seeing these pictures from the specialists to the machine, which in the long run could have a greater ability of location, as it has learned by viewing an enormous amount of pictures knowing their genuine finding. This would be an away form of collaboration among people and machines. The dataset The dataset utilized in the task is a lot of pictures with and without tumors, from which we know the genuine finding. You can discover it here: https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detection Data Preprocessing 1. First, we needed to do some picture preparing, and afterward pass 80% of these pictures to a neural organization, cause it to learn and be fit for making a precise finding of another picture. 2. The other 20% of the pictures are utilized to test the model. We will contrast their genuine finding with the one that the model gives, to perceive how it performs.
Optimizing-machine-learning-algorithm
Anomaly/Outlier detection is the process of finding abnormal data points in datasets or data streams. Anomaly detection finds its application in various fields like network intrusion detection, fraud detection, fault detection, etc. There are many anomaly detection algorithms available in the literature but most of these algorithms require setting of some parameters which significantly affect the performance of the algorithm. These parameters are generally set by hit-and-trial, hence performance is compromised with default or random values. In this project, we propose a optimizing algorithm for anomaly detection based on machine learning algorithms, algorithm for anomaly detection, though the approach used in the proposed solution is different. The algorithm is implemented on Python for scalability and thus the solution can handle big data as well and provides fast results. Experiments will going to be conducted on various datasets, and the results show that the proposed solution is much accurate than the standard algorithms of anomaly detection
Parallel-Face-detection
Image segmentation is the process of dividing an image into multiple parts. It is typically used to identify objects or other relevant information in digital images. There are many ways to perform image segmentation including Thresholding methods, Color-based segmentation, Transform methods among many others. Alternately edge detection can be used for image segmentation and data extraction in areas such as image processing, computer vision, and machine vision. Image thresholding is a simple, yet effective, way of partitioning an image into a foreground and background. This image analysis technique is a type of image segmentation that isolates objects by converting grayscale images into binary images. Image thresholding is most effective in images with high levels of contrast. Otsu's method, named after Nobuyuki Otsu, is one such implementation of Image Thresholding which involves iterating through all the possible threshold values and calculating a measure of spread for the pixel levels each side of the threshold, i.e. the pixels that either fall in foreground or background. The aim is to find the threshold value where the sum of foreground and background spreads is at its minimum. Edge detection is an image processing technique for finding the boundaries of objects within images. It works by detecting discontinuities in brightness. An image can have horizontal, vertical or diagonal edges. The Sobel operator is used to detect two kinds of edges in an image by making use of a derivative mask, one for the horizontal edges and one for the vertical edges. 1. Introduction Face detection is a computer technology being used in a variety of applications that identifies human faces in digital images. Face detection also refers to the psychological process by which humans locate and attend to faces in a visual scene. Face detection can be regarded as a specific case of object-class detection. In object-class detection, the task is to find the locations and sizes of all objects in an image that belong to a given class. Examples include upper torsos, pedestrians, and cars. Face-detection algorithms focus on the detection of frontal human faces. It is analogous to image detection in which the image of a person is matched bit by bit. Image matches with the image stores in database. Any facial feature changes in the database will invalidate the matching process. 2. Needs/Problems There have been widely applied many researches related to face recognition system. The system is commonly used for video surveillance, human and computer interaction, robot navigation, and etc. Along with the utilization of the system, it leads to the need for a faster system response, such as robot navigation or application for public safety. A number of classification algorithms have been applied to face recognition system, but it still has a problem in terms of computing time. In this system, computing time of the classification or feature extraction is an important thing for further concern. To improve the algorithmic efficiency of face detection, we combine the eigenface method using Haar-like features to detect both of eyes and face, and Robert cross edge detector to locate the human face position. Robert Cross uses the integral image representation and simple rectangular features to eliminate the need of expensive calculation of multi-scale image pyramid. 3. Objectives Some techniques used in this application are 1. Eigen-face technique 2. KLT Algorithm 3. Parallel for loop in openmp 4. OpenCV for face detection. 5. Further uses of the techniques
PiForest
Stock-Price-Prediction-Machine-Learning
This is 6th and last capstone project in the arrangement of the undertakings recorded in Udacity-Machine Learning Nano Degree Program. Venture firms, mutual funds and even people have been utilizing monetary models to more readily comprehend market conduct and make beneficial speculations and exchanges. An abundance of data is accessible as chronicled stock costs and friends execution information, reasonable for AI calculations to measure. Could we really foresee stock costs with AI? Financial backers make instructed surmises by dissecting information. They'll peruse the news, study the organization history, industry patterns and different bunches of information focuses that go into making a forecast. The common speculations is that stock costs are absolutely arbitrary and unusual yet that brings up the issue why top firms like Morgan Stanley and Citigroup enlist quantitative examiners to fabricate prescient models. We have this thought of an exchanging floor being loaded up with adrenaline implant men with free ties going around hollering something into a telephone however nowadays they're bound to see columns of AI specialists unobtrusively sitting before PC screens. Truth be told about 70% of all orders on Wall Street are currently positioned by programming, we're presently living in the age of the calculation. This venture uses Deep Learning models, Long-Short Term Memory (LSTM) Neural Network calculation, to anticipate stock costs. For information with time periods intermittent neural organizations (RNNs) prove to be useful however late explores have shown that LSTM, networks are the most famous and valuable variations of RNNs. I have utilized Keras to assemble a LSTM to foresee stock costs utilizing chronicled shutting cost and exchanging volume and envision both the anticipated value esteems after some time and the ideal boundaries for the model.
Travaelling-Salesman-Problem-TSP-optimized-version
Solving the Traveling Salesman Problem using Self-Organizing Maps This repository contains an implementation of a Self Organizing Map that can be used to find sub-optimal solutions for the Traveling Salesman Problem. The instances of the problems that the program supports are .tsp files, which is a widespread format in this problem. All the source code can be found in the src directory, while a report and brief presentation slides (in Spanish) can be found in the report folder. However, for a complete read on the topic, you can read my blog post explaining this implementation and its evaluation.
jainsee24's Repositories
jainsee24/Parallel-Face-detection
Image segmentation is the process of dividing an image into multiple parts. It is typically used to identify objects or other relevant information in digital images. There are many ways to perform image segmentation including Thresholding methods, Color-based segmentation, Transform methods among many others. Alternately edge detection can be used for image segmentation and data extraction in areas such as image processing, computer vision, and machine vision. Image thresholding is a simple, yet effective, way of partitioning an image into a foreground and background. This image analysis technique is a type of image segmentation that isolates objects by converting grayscale images into binary images. Image thresholding is most effective in images with high levels of contrast. Otsu's method, named after Nobuyuki Otsu, is one such implementation of Image Thresholding which involves iterating through all the possible threshold values and calculating a measure of spread for the pixel levels each side of the threshold, i.e. the pixels that either fall in foreground or background. The aim is to find the threshold value where the sum of foreground and background spreads is at its minimum. Edge detection is an image processing technique for finding the boundaries of objects within images. It works by detecting discontinuities in brightness. An image can have horizontal, vertical or diagonal edges. The Sobel operator is used to detect two kinds of edges in an image by making use of a derivative mask, one for the horizontal edges and one for the vertical edges. 1. Introduction Face detection is a computer technology being used in a variety of applications that identifies human faces in digital images. Face detection also refers to the psychological process by which humans locate and attend to faces in a visual scene. Face detection can be regarded as a specific case of object-class detection. In object-class detection, the task is to find the locations and sizes of all objects in an image that belong to a given class. Examples include upper torsos, pedestrians, and cars. Face-detection algorithms focus on the detection of frontal human faces. It is analogous to image detection in which the image of a person is matched bit by bit. Image matches with the image stores in database. Any facial feature changes in the database will invalidate the matching process. 2. Needs/Problems There have been widely applied many researches related to face recognition system. The system is commonly used for video surveillance, human and computer interaction, robot navigation, and etc. Along with the utilization of the system, it leads to the need for a faster system response, such as robot navigation or application for public safety. A number of classification algorithms have been applied to face recognition system, but it still has a problem in terms of computing time. In this system, computing time of the classification or feature extraction is an important thing for further concern. To improve the algorithmic efficiency of face detection, we combine the eigenface method using Haar-like features to detect both of eyes and face, and Robert cross edge detector to locate the human face position. Robert Cross uses the integral image representation and simple rectangular features to eliminate the need of expensive calculation of multi-scale image pyramid. 3. Objectives Some techniques used in this application are 1. Eigen-face technique 2. KLT Algorithm 3. Parallel for loop in openmp 4. OpenCV for face detection. 5. Further uses of the techniques
jainsee24/PiForest
jainsee24/Iforest-Machine-learning-algorithm
jainsee24/Stock-Price-Prediction-Machine-Learning
This is 6th and last capstone project in the arrangement of the undertakings recorded in Udacity-Machine Learning Nano Degree Program. Venture firms, mutual funds and even people have been utilizing monetary models to more readily comprehend market conduct and make beneficial speculations and exchanges. An abundance of data is accessible as chronicled stock costs and friends execution information, reasonable for AI calculations to measure. Could we really foresee stock costs with AI? Financial backers make instructed surmises by dissecting information. They'll peruse the news, study the organization history, industry patterns and different bunches of information focuses that go into making a forecast. The common speculations is that stock costs are absolutely arbitrary and unusual yet that brings up the issue why top firms like Morgan Stanley and Citigroup enlist quantitative examiners to fabricate prescient models. We have this thought of an exchanging floor being loaded up with adrenaline implant men with free ties going around hollering something into a telephone however nowadays they're bound to see columns of AI specialists unobtrusively sitting before PC screens. Truth be told about 70% of all orders on Wall Street are currently positioned by programming, we're presently living in the age of the calculation. This venture uses Deep Learning models, Long-Short Term Memory (LSTM) Neural Network calculation, to anticipate stock costs. For information with time periods intermittent neural organizations (RNNs) prove to be useful however late explores have shown that LSTM, networks are the most famous and valuable variations of RNNs. I have utilized Keras to assemble a LSTM to foresee stock costs utilizing chronicled shutting cost and exchanging volume and envision both the anticipated value esteems after some time and the ideal boundaries for the model.
jainsee24/Travaelling-Salesman-Problem-TSP-optimized-version
Solving the Traveling Salesman Problem using Self-Organizing Maps This repository contains an implementation of a Self Organizing Map that can be used to find sub-optimal solutions for the Traveling Salesman Problem. The instances of the problems that the program supports are .tsp files, which is a widespread format in this problem. All the source code can be found in the src directory, while a report and brief presentation slides (in Spanish) can be found in the report folder. However, for a complete read on the topic, you can read my blog post explaining this implementation and its evaluation.
jainsee24/Emotion-Recognition
Emotion Recognition using Deep Convolutional Neural Networks: Used a Deep CNN to recognize facial expressions from images or video/camera stream out of seven basic human expression using Python.
jainsee24/MRI-Based-Brain-Tumor-Detection-using-CNN-and-Image-Processing
Introduction- Brain tumor detection project This project comprises a program that gets a mind Magnetic Resonance Image (MRI) and gives a finding that can be the presence or not of a tumor in that cerebrum. Why this task? In clinical analysis, checking mind tumors among a lot of MRI pictures, as a rule, take specialists much time. For instance, in tests of this undertaking, a patient has around 200 MRI pictures, however, tumor tissues just show up in 15 pictures. Thusly, this venture intends to naturally recognize tumor tissues in a huge measure of MRI picture information. Our objectives: 1) naturally, recognize if tumor tissue shows up in the MRI picture 2) automatical mind tumor division in MRI picture The outcome when we give a picture to the program is a likelihood that the cerebrum contains a tumor, so we could organize the patients which attractive reverberation have higher probabilities to have one, and treat them first. Another objective could be to move the obligation of seeing these pictures from the specialists to the machine, which in the long run could have a greater ability of location, as it has learned by viewing an enormous amount of pictures knowing their genuine finding. This would be an away form of collaboration among people and machines. The dataset The dataset utilized in the task is a lot of pictures with and without tumors, from which we know the genuine finding. You can discover it here: https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detection Data Preprocessing 1. First, we needed to do some picture preparing, and afterward pass 80% of these pictures to a neural organization, cause it to learn and be fit for making a precise finding of another picture. 2. The other 20% of the pictures are utilized to test the model. We will contrast their genuine finding with the one that the model gives, to perceive how it performs.
jainsee24/Optimizing-machine-learning-algorithm
Anomaly/Outlier detection is the process of finding abnormal data points in datasets or data streams. Anomaly detection finds its application in various fields like network intrusion detection, fraud detection, fault detection, etc. There are many anomaly detection algorithms available in the literature but most of these algorithms require setting of some parameters which significantly affect the performance of the algorithm. These parameters are generally set by hit-and-trial, hence performance is compromised with default or random values. In this project, we propose a optimizing algorithm for anomaly detection based on machine learning algorithms, algorithm for anomaly detection, though the approach used in the proposed solution is different. The algorithm is implemented on Python for scalability and thus the solution can handle big data as well and provides fast results. Experiments will going to be conducted on various datasets, and the results show that the proposed solution is much accurate than the standard algorithms of anomaly detection
jainsee24/3d-reconstruction
jainsee24/Automatic-Number-Plate-Recognition
jainsee24/Bitcoin-Price-Predictor
Anticipate Price of Bitcoin digital money utilizing AI calculations. Usage incorporate Linear/Polynomial Regression, and Recurrent Neural Networks utilizing Long Short Term Memory (LSTM) cells.
jainsee24/cheaptickets
jainsee24/Clustering-Huge-Data-using-Cube-Sampling
jainsee24/COVID-19-Contact-Tracing
As of late, the COVID-19 pandemic made an overall crisis as it is assessed that a particularly number of diseases are because of human-to-human transmission of the COVID-19. As a need, there is a need to follow client who interacted with client having travel history, asymptomatic and not yet suggestive, however they can be later on. Along these lines, this work proposes an answer for contact following dependent on GPS and distributed computing innovations. An application is created to gather every client's GPS arranges once all the clients introduce this application. This application occasionally sends GPS information (organizes) to the Cloud. To figure out which gadgets are inside the reasonable furthest reaches of 5m (tunable boundary), we perform grouping over GPS organizes and track the bunches for about t mins (tunable boundary) to permit the proportion of spread. We expect that it takes around 3-5 mins to get the infection from a tainted item. For grouping, the proposed M-way like tree information structure stores the GPS facilitates in degree, moment, and second (DMS) design. Hence, every client is planned to a leaf hub of the tree. The core of the arrangement lies at the leaf hub. We split the 'seconds' part of the GPS area into m equivalent parts (a tunable boundary), which add up to d meter in scope/longitude. Henceforth, two clients who are inside d meter reach will guide to a similar leaf hub. In this manner, by planning GPS areas each t mins (normally t = 2.5 mins), we can discover the number of clients interacted with a specific client for in any event t mins. Our work's notable component is that it runs in straight time O(n) for n clients in the static case, i.e., when clients are not moving. We additionally propose a variation of our answer for handle the powerful case, that is, when clients are moving. Also, the proposed arrangement offers potential area of interest recognition and safe-course suggestion as an extra component, and verification of-idea is introduced through investigates recreated information of 2/4/6/8/10M clients.
jainsee24/Cube-sampling
Cube sampling method implemented in python, A sampling algorithm can thus be viewed as a 'random' way of reaching a vertex of the N-cube from a vector p in such a way that the balancing equations are satisfied.
jainsee24/cvx_UI
jainsee24/Datasets
jainsee24/final_form
jainsee24/flight
jainsee24/form
jainsee24/I765-form-filler
jainsee24/Image-Segmentation-using-python
jainsee24/Landscaping-Website
Web app of garden development: We design, build, protect, and maintain exquisite model homes, expansive master-planned communities, and beautiful public spaces. We bridge what can be imagined to what can be built..
jainsee24/latent_intrinsic
jainsee24/ML4SCI-Task
jainsee24/Online-Grocery-Recommendation-using-Collaborative-Filtering
Online E-business sites like Amazon, Filpkart utilizes distinctive proposal models to give various ideas to various clients. Amazon presently utilizes thing to-thing shared separating, which scales to monstrous informational indexes and creates great proposals continuously. This kind of sifting matches every one of the client's bought and appraised things to comparable things, at that point consolidates those comparative things into a suggestion list for the client. In this task we will fabricate suggestion model for the hardware results of Amazon.
jainsee24/rrcf
🌲 Implementation of the Robust Random Cut Forest algorithm for anomaly detection on streams
jainsee24/SDGN
jainsee24/Selenium-Heroku
jainsee24/Sola-system
3D Simulation of Solar System using OpenGl: A Visualization of solar system with Functionalities such as Lighting, Texture, Sun, eight planets and moon, Axis tilt and orbit inclination, Free movement and inspection, Zooming, Possibility to read information about objects