mohebbihr

bcb-crater-ception

Crater-ception is a sub-kilometer crater detection framework using Inception model.

bcb-crater-detection

This project proposes a new crater detection framework named BCB-Crater-Detection that learns bidirectional context-based features from both crater and non-crater ends. This framework utilizes both craters and its surrounding features using deep convolutional classification and segmentation models to identify efficiently sub-kilometer craters in high-resolution panchromatic images.

catgan

chainer catgan

crater-detection-survey

This repository contains the code, models, data, and results of the crater detection survey.

cs697_term_project_phaseI

FDJD

Here, we describe a fusion detection method using RNA-Seq data which takes advantage of both these two approaches. This method aligns RNA-Seq input data to the reference genome to identify discordantly mapping reads like a mapping-first approach. Additionally, it converts discordant reads into a novel binary fingerprint format which makes it possible to quickly and accurately search the reference human genome for fusions. This fusion detection pipeline contains three steps: general alignment, fusion candidate generation, and refinement.

Genetic-Mutation-Discovery

The goal of this project is to discover genetic mutation patterns for specific tumor types using unsupervised learning method. In this project we used matrix factorization technique descibed by Brunet in his paper entitled "Metagenes and molecular pattern discovery using matrix factorization".

Parallel-BMA

The Berlekamp-Massy algorithm finds the shortest linear feedback shift register (LFSR) for a binary input sequence. This research uses different parallel mechanisms offered by heterogeneous hardward in order to achieve the best possible performance for BMA.

Recognition-of-Driver-behavior-using-Smartphone

The goal of this project was to build a smartphone application that can recognize hazardous behavior of a car driver. The driver actions divided into several categories and the smart scoring system recognize unsafe actions. The android application has been developed for this project using Java

zivm

This repository contains the source of Hamidreza Mohebbi's M.Sc. thesis project entitled "ZIVM: A Zero-Copy Inter-VM Communication Mechanism

mohebbihr/Recognition-of-Driver-behavior-using-Smartphone

The goal of this project was to build a smartphone application that can recognize hazardous behavior of a car driver. The driver actions divided into several categories and the smart scoring system recognize unsafe actions. The android application has been developed for this project using Java

mohebbihr/bcb-crater-detection

This project proposes a new crater detection framework named BCB-Crater-Detection that learns bidirectional context-based features from both crater and non-crater ends. This framework utilizes both craters and its surrounding features using deep convolutional classification and segmentation models to identify efficiently sub-kilometer craters in high-resolution panchromatic images.

mohebbihr/zivm

This repository contains the source of Hamidreza Mohebbi's M.Sc. thesis project entitled "ZIVM: A Zero-Copy Inter-VM Communication Mechanism

mohebbihr/FDJD

Here, we describe a fusion detection method using RNA-Seq data which takes advantage of both these two approaches. This method aligns RNA-Seq input data to the reference genome to identify discordantly mapping reads like a mapping-first approach. Additionally, it converts discordant reads into a novel binary fingerprint format which makes it possible to quickly and accurately search the reference human genome for fusions. This fusion detection pipeline contains three steps: general alignment, fusion candidate generation, and refinement.

mohebbihr/Genetic-Mutation-Discovery

The goal of this project is to discover genetic mutation patterns for specific tumor types using unsupervised learning method. In this project we used matrix factorization technique descibed by Brunet in his paper entitled "Metagenes and molecular pattern discovery using matrix factorization".

mohebbihr/Parallel-BMA

The Berlekamp-Massy algorithm finds the shortest linear feedback shift register (LFSR) for a binary input sequence. This research uses different parallel mechanisms offered by heterogeneous hardward in order to achieve the best possible performance for BMA.

mohebbihr/bcb-crater-ception

Crater-ception is a sub-kilometer crater detection framework using Inception model.

mohebbihr/catgan

chainer catgan

mohebbihr/crater-detection-survey

This repository contains the code, models, data, and results of the crater detection survey.

mohebbihr/cs697_term_project_phaseI

mohebbihr/datascience_learning

datascience_learning

mohebbihr/dcgan_code

Deep Convolutional Generative Adversarial Networks

mohebbihr/github-slideshow

A robot powered training repository :robot:

mohebbihr/MindSumo-ColdFusion-Challenge

I contirubuted to an online programming challenges that requires us to design a fantastic website with ColdFusion.

mohebbihr/n-queens-mpi

Backtracking algorithms are used to methodically and exhaustively search a solution space for an optimal solution to a given problem. A classic example of a backtracking algorithm is illustrated by finding all solutions to the problem of placing N-queens on an N × N chess board such that no two queens attack each other. This repository contains source code of my B.Sc. final project which I used MPI to implement the n-qeens problem more efficiently.

mohebbihr/Radio-Stream-Music-Player

This music player have several capabilities including connecting to online radios, playing and recording music and streaming the music online. This project implemented by C#.NET language and its use the BASS audio library.

mohebbihr/TDJD

In this work, we proposed a method called TDJD that identifies the location of inter-chromosomal breakpoints corresponding to large scale structural variations, in particular translocations and insertions.

mohebbihr/tmp

mohebbihr/WDM-CUDA

This is the source codes for CUDA implementation of the new distance metric named WDM. The aim of this project was to builds a weighted-distance metric from the labeled training set and combines it with group-level information from the unlabeled test set.