Dimuthu L. Profile

EXPLORE

5.0

(1 review)

You're now following

Error following user.

This user does not allow users to follow them.

You are already following this user.

Your membership plan only allows 0 follows. Upgrade here.

Successfully unfollowed

Error unfollowing user.

You have successfully recommended

Error recommending user.

Something went wrong. Please refresh the page and try again.

Email successfully verified.

$15 USD / hour

colombo,

sri lanka

$15 USD / hour

It's currently 5:56 PM here

Joined June 12, 2019

0 Recommendations

Dimuthu L.

@neominds

5.0

(1 review)

1.6

100%

$15 USD / hour

colombo,

sri lanka

$15 USD / hour

100%

Jobs Completed

100%

On Budget

100%

On Time

N/A

Repeat Hire Rate

Your Problem, Our Solution

We are Neo Minds, a team of passionate individuals pursuing modern technological innovation and its application to make lives easier for everyone. We continually use latest web and mobile development technologies and deep learning techniques to develop our innovative products. We use our creative thinking to make our innovative products and services to be more attractive and appealing to the users.

See all Javascript Developers in Sri Lanka

Contact Dimuthu L. about your job

Portfolio

5066563

This research project is conducted to estimate cultivate paddy extent and the extent affected by Brown Planthopper attacks in Sri Lanka. Government in Sri Lanka is facing huge issues on agriculture policy making procedures due to not having accurate data on paddy land usage for paddy cultivation. Remote sensing data sources can be identified as a great alternative for making accurate and timely land usage estimations. However, traditional remote sensing data resources failed to make accurate estimations on cultivate paddy extent estimations in Sri Lanka.
A novel approach has been introduced for remote sensing analysis using deep neural network technologies, particularly suitable for small scale crop lands in developing countries.

Agro AI

This mobile app is developed in order to monitor the water level, rainfall and other important environmental parameters that are gathered realtime by the sensors in Upper Kotmale Dam, Sri Lanka.

Upper Kotmale Dam Data Visualizer

These 2D games are simulating breathing exercises and allow kids to play it through a peak low meter like the product. Integrated Neural Network model built using tensorflow lite detects breathing sounds and it allows the player to control the game via breathing. The sequence of the game is planned out in a way that simulates various breathing exercises.

Inhalo Games

Creative Red

Soxplay

5060126

Inhalo App is an Asthma Management application which allows people who have this condition to keep track of its progress and optimize. This includes maintaining medication, doctor appointments, asthma attack alert send button, peak flow meter reading recording, Asthma trigger recording, and blogs with useful information on Asthma Management. This App has a highly intuitive UI with great sharing data capability to enable patients to send information to doctors instantly and effectively while doctors can monitor the progress of the patient live given the access.

Inhalo Mobile App

5066563

Agro AI

Upper Kotmale Dam Data Visualizer

Inhalo Games

Creative Red

Soxplay

5060126

Inhalo Mobile App

Reviews

Changes saved

Showing 1 - 1 out of 1 reviews

Filter reviews by:

5.0

$88.00 CAD

Form validation JavaScript

Great work.

JavaScript

HTML5

CSS3

Manjinder S.

@sohalsaabms

•

5 years ago

Experience

University of Moratuwa

Jan 2018 - Jan 2019 (1 year)

Worked under the Datasearch Center at University of Moratuwa as Graduate Research Assistant. At there I was able complete a research to estimate cultivate paddy extent and the extent affected by Brown Planthopper attacks in Sri Lanka. A novel approach has been introduced for remote sensing analysis using deep neural network technologies, particularly suitable for small scale crop lands in developing countries.

Sysco Labs

Jul 2016 - Dec 2016 (5 months, 1 day)

Worked as a software intern. I was exposed to latest technologies at that period such as React, NojeJS, Angular, MongoDB etc. I was able to gain knowledge about iOS and Android development as well.

Education

MSc. specialized in Machine Learning

University of Moratuwa,

Sri Lanka

2018 - 2019

(1 year)

BSc. Engineering

University of Moratuwa,

Sri Lanka

2014 - 2017

(3 years)

Publications

Synergistic union of Word2Vec and lexicon for domain specific semantic similarity

Institute of Electrical and Electronics Engineers

We introduce a domain specific semantic similarity measure that was created by the synergistic union of word2vec, a word embedding method that is used for semantic similarity calculation and lexicon based (lexical) semantic similarity methods. We prove that this proposed methodology outperforms both, word embedding methods trained on a generic corpus and word embedding methods trained on a domain specific corpus, which do not use lexical semantic similarity methods to augment the results.

Semi-supervised instance population of an ontology using word vector embedding

Institute of Electrical and Electronics Engineers

In this study we propose a novel way of semi-supervised ontology population through word embeddings as the basis. We built several models including traditional benchmark models and new types of models which are based on word embeddings. Finally, we ensemble them together to come up with a synergistic model with better accuracy. We demonstrate that our ensemble model can outperform the individual models.

Deriving a representative vector for ontology classes with instance word vector embeddings

Institute of Electrical and Electronics Engineers

Selecting a representative vector for a set of vectors is a very common requirement in many algorithmic tasks. This study proposes a methodology to derive a representative vector for ontology classes whose instances were converted to the vector space. We show that our methodology out-performs the traditional mean and median vector representations.

Legal Document Retrieval Using Document Vector Embeddings and Deep Learning

Springer

Domain specific information retrieval process has been a prominent and ongoing research in the field of natural language processing. The main bottleneck in these studies is the heavy coupling of domain experts, that makes the entire process to be time consuming and cumbersome. In this study, we have developed three novel models which are compared against a golden standard generated via the on line repositories provided, specifically for the legal domain.

Word Vector Embeddings and Domain Specific Semantic based Semi-Supervised Ontology Population

An ontology defines a set of representational primitives which model a domain of knowledge or discourse. The semantic sensitive word embedding has become a popular topic in natural language processing with its capability to cope with the semantic challenges. Thus, in this study we propose a novel way of semi-supervised ontology population through word embeddings and domain specific semantic similarity as the basis.