Haseeb Y. Profile | Freelancer

Kuinka se toimii

Kirjaudu sisään

Ilmoita projekti

LÖYDÄ

C++ Programming

Machine Learning (ML)

5,0

(40 arvostelua)

undefined

Seuraat nyt käyttäjää .

Virhe seurattaessa käyttäjää.

Tämä käyttäjä ei salli käyttäjien seurata häntä.

Seuraat jo tätä käyttäjää.

Jäsenyystasosi mahdollistaa vain 0 seurausta. Päivitä tästä.

Poistit käyttäjän seurannan onnistuneesti.

Virhe poistettaessa käyttäjän seurantaa.

Olet onnistuneesti suositellut käyttäjää

Virhe suositeltaessa käyttäjää.

Jokin meni vikaan. Päivitä sivu ja yritä uudelleen.

Sähköposti vahvistettu onnistuneesti.

$20 USD / tunti

Maan PAKISTAN lippu

sheikhupura,

$20 USD / tunti

Kello on tällä hetkellä 10:12 ip. täällä

Liittynyt maaliskuuta 5, 2017

1 Suositus

Haseeb Y.

@HaseebYounis

5,0

(40 arvostelua)

5,4

5,4

$20 USD / tunti

Maan PAKISTAN lippu

sheikhupura,

$20 USD / tunti

98 %

Suoritetut työt

99 %

Budjetin mukaisesti

99 %

Aikataulussa

32 %

Uudelleenpalkkausaste

Machine Learning| Data Science| Web Development

I am a Data Scientist, Passionate Software Engineer, and Research Officer in the fields of Machine Learning, Deep Learning, Natural Language Processing (NLP), Computer Vision, and Bioinformatics. I hold a Masters's Degree as well as a Bachelors's Degree in Computer Science. My Master's thesis was in Bio-NLP. I have Research Publications related to my work and strong skills in the implementation of research articles and improving results. I believe in hard work and honesty. I complete my work on time. It'll be great fun to work with me.

Katso kaikki Machine Learning Experts paikassa Pakistan

Ota yhteyttä käyttäjään Haseeb Y. työhösi liittyen

Kirjaudu sisään keskustellaksesi yksityiskohdista chatin välityksellä.

Portfoliokohteet

Human eye can adjust to a wide range of light conditions, most imaging devices use 8-bits per channel, so we are limited to only 256 levels. In this project, we Generated and displayed HDR image from an exposure sequence by using exposure fusion to merge an exposure sequence. We also build the web application using Django

Image Processing and High Dynamic Image Ranging

Human eye can adjust to a wide range of light conditions, most imaging devices use 8-bits per channel, so we are limited to only 256 levels. In this project, we Generated and displayed HDR image from an exposure sequence by using exposure fusion to merge an exposure sequence. We also build the web application using Django

Image Processing and High Dynamic Image Ranging

We have integrated reinforcement learning-based different AI algorithms like Monte Carlo tree search and it variants, and Minimax algorithm in computer games like tic tac toe that enable to play us games with bots.

Artificial Intelligence Based Games

In this project, we have used transfer learning to classify the COVID, Pneumonia and Normal Lung images. We achieved 98.53% accuracy and build a web application using flask.

COVID Classification using Transfer Learning

In this project, we have used transfer learning to classify the COVID, Pneumonia and Normal Lung images. We achieved 98.53% accuracy and build a web application using flask.

COVID Classification using Transfer Learning

In this project, we have used transfer learning to classify the COVID, Pneumonia and Normal Lung images. We achieved 98.53% accuracy and build a web application using flask.

COVID Classification using Transfer Learning

We perform lung segmentation from the 3d image of lungs using deep learning. Optimized the image quality using reduced the distortion using Hopefield Neural Networks.

Lung Cancer Segmentation and Optimization via Deep Learning

We perform lung segmentation from the 3d image of lungs using deep learning. Optimized the image quality using reduced the distortion using Hopefield Neural Networks.

Lung Cancer Segmentation and Optimization via Deep Learning

We proposed a deep learning-based model for the early prognosis and classification of plant diseases. We have tuned a deep learning-based pretrained model in 2 folds over a publicly available dataset that contains images of different plants suffering from different diseases as well as healthy plants. We are envisioned to classify each instance as healthy or the name of the disease, the plant is being suffered. This transfer learning method has achieved remarkable results on this data-set of 38 plants diseases and achieved 98.89% accuracy.

Plant Disease Classification using Deep learning

We have Proposed A New Sequential Forward Feature Selection (SFFS) Algorithm for Mining Best Topological and Biological Features to Predict Protein Complexes from Protein–Protein Interaction Networks (PPINs). Our proposed SFFS, i.e., random forest-based Brouta feature selection in combination with decision trees, linear discriminant analysis and Gradient Boosting Classifiers outperforms other state of art algorithms by achieving precision, recall and F-measure rates, i.e. 94.58%, 94.92% and 94.45% for MIPS, 96.31%, 93.55% and 96.02% for CYC2008, 98.84%, 98.00%, 98.87 % for CORUM humans and 96.60%, 96.70%, 96.32% for CORUM mouse dataset complexes, respectively.

Machine Learning and Bioinformatics Research

We have Proposed A New Sequential Forward Feature Selection (SFFS) Algorithm for Mining Best Topological and Biological Features to Predict Protein Complexes from Protein–Protein Interaction Networks (PPINs). Our proposed SFFS, i.e., random forest-based Brouta feature selection in combination with decision trees, linear discriminant analysis and Gradient Boosting Classifiers outperforms other state of art algorithms by achieving precision, recall and F-measure rates, i.e. 94.58%, 94.92% and 94.45% for MIPS, 96.31%, 93.55% and 96.02% for CYC2008, 98.84%, 98.00%, 98.87 % for CORUM humans and 96.60%, 96.70%, 96.32% for CORUM mouse dataset complexes, respectively.

Machine Learning and Bioinformatics Research

Arvostelut

Muutokset tallennettu

Näytetään 1 - 5 / 40 arvostelua

Suodata arvosteluja:

5,0

$220,00 AUD

Project for Haseeb Y. -- 7

He is very professional in Deep Learning. I highly recommended.

Matlab and Mathematica

Machine Learning (ML)

+1 enemmän

J

Joseph A.

@Joseph1401

•

10 kuukautta sitten

5,0

$60,00 AUD

Project for Haseeb Y. -- 6

Best freelancer for machine learning and deep learning projects, Highly Recommended!

Matlab and Mathematica

Machine Learning (ML)

+1 enemmän

J

Joseph A.

@Joseph1401

•

10 kuukautta sitten

5,0

$50,00 AUD

Project for Haseeb Y. -- 5

Expert in machine learning and deep learning. Has strong knowledge of his field. Good to work with him. Highly Recommended.

Matlab and Mathematica

Machine Learning (ML)

+1 enemmän

J

Joseph A.

@Joseph1401

•

10 kuukautta sitten

5,0

$200,00 AUD

Project for Haseeb Y. -- 3

Haseeb is proficient in Deep Learning and he delivered on time. Highly recommended.

Matlab and Mathematica

Machine Learning (ML)

+1 enemmän

J

Joseph A.

@Joseph1401

•

10 kuukautta sitten

5,0

$60,00 AUD

Project for Haseeb Y. -- 4

Thank you so much Haseeb. goood work.

Matlab and Mathematica

Machine Learning (ML)

+1 enemmän

J

Joseph A.

@Joseph1401

•

11 kuukautta sitten

Kokemus

ITRIG

elok. 2017 - Voimassa

I am working here in projects related to data science, machine learning, computer vision, natural language processing and bioinformatics.

Koulutus

MSCS

COMSATS Institute of Information Technology,

Pakistan

2017 - 2019

(2 vuotta)

Pätevyydet

IEEE and Springer

2019

6 Research paper publications in the field of Machine Learning, Bioinformatics, Deep Learning, Natural Language Processing (NLP) and Computer Vision.

Julkaisut

A New Sequential Forward Feature Selection (SFFS) Algorithm for mining best features ... PPIN

Springer

Our proposed SFFS, i.e., random forest-based Brouta feature selection in combination with decision trees, linear discriminant analysis and Gradient Boosting Classifiers outperforms other state of art algorithms by achieving precision, recall and F-measure rates, i.e. 94.58%, 94.92% and 94.45% for MIPS, 96.31%, 93.55% and 96.02% for CYC2008, 98.84%, 98.00%, 98.87 % for CORUM humans and 96.60%, 96.70%, 96.32% for CORUM mouse dataset complexes, respectively.

Robust Optimization of MobileNet for Plant Disease Classification with Fine Tuned Parameters

IEEE

In this paper, we proposed a deep learning-based model for the early prognosis and classification of plant diseases. We have tuned a deep learning-based pretrained model in 2 folds over a publicly available dataset that contains images of different plants suffering from different diseases as well as healthy plants. This transfer learning method has achieved remarkable results on this data-set of tomato plants and achieved 98.89% accuracy.

Wheat Disease Recognition through One-shot Learning using Fields Images

IEEE

We have used the MobileNetv3 network as a feature extractor which is extremely fast and accurate classification. This network is fine-tuned on the PlantVillage dataset, while the last two dense layers are fine-tuned on the plant images of 11 wheat disease, those images are taken from the CGIAR Crop Disease dataset and Google images.It assigns 1 score to similar images, while 0 to dissimilar images. Our Mobilenetv3 model has achieved around 98% training and 96% validation accuracy.

Classification of Skin Cancer Dermoscopy Images using Transfer Learning

IEEE

In this paper, We have tuned the pre-trained MobileNet convolution neural network and trained over the HAM1000 skin lesion dataset. This transfer learning method has shown remarkable categorical accuracy, the weighted average of precision and recall 0.97, 0.90 and 0.91 respectively. This model is lightweight, fast and reliable. It will be helpful for dermatologists to prognosis the skin cancer at its early stage.

Wheelchair Training Virtual Environment for People with Physical and Cognitive Disabilities

IEEE

This paper introduces the virtual reality and Brain Computer Interface based environment for the powered wheelchair training of paralyzed persons. In this study, we have developed the environments that are configured with virtual reality and EEG devices (Emotiv Epoc+). Our results revealed that virtual reality based training of wheelchair controlled by EEG signal gives significantly positive feedback and results

Object Segmentation in Video Sequences by using Single Frame Processing

IEEE

Object segmentation, detection and tracking in videos is one of the most important task of computer vision. It is necessary in all of the real time deployed surveillance systems. Various unsupervised and semi-supervised video object segmentation techniques have been implemented and shown efficient results. But all of these techniques process all of the frames of a video sequence, which requires a huge training data and results in a large computational time.

Ota yhteyttä käyttäjään Haseeb Y. työhösi liittyen

Kirjaudu sisään keskustellaksesi yksityiskohdista chatin välityksellä.

Varmennukset

Suositeltu freelanceri

Henkilöllisyys varmennettu

Maksutapa varmennettu

Puhelinnumero varmennettu

Sähköpostiosoite varmennettu

Facebook yhdistetty

Todistukset

Preferred Freelancer Program SLA 1

100%

Basic Numeracy 1

85%

US English 1

77%

US English 2

77%

UK English 1

75%

Parhaat taidot

Machine Learning (ML)

31

29

15

4

C++ Programming

4

Selaa vastaavia freelancereita

Machine Learning Experts in Pakistan

Machine Learning Experts

Python Developers

Data Science Experts

Selaa vastaavia näyteikkunoita

Machine Learning (ML)

Edellinen käyttäjä

Seuraava käyttäjä

Kutsu lähetetty onnistuneesti!

Ladataan esikatselua

Lupa myönnetty Geolocation.

Kirjautumisistuntosi on vanhentunut ja sinut on kirjattu ulos. Kirjaudu uudelleen sisään.