Artificial Intelligence

Get the most out of your training, scoring, algorithms and frameworks on Intel® architecture for Deep Learning and Artificial Intelligence.

Activity Feed

Default user avatar 57012e2942

Vamshi G. created project Traffic Light Recognition using Deep Learning

Medium fc2a0897 61ed 48bf ac64 1e8ad6733b6e

Traffic Light Recognition using Deep Learning

This project is pursued as a final project for the course Neural Networks and Pattern Recognition taken at University of California, San Diego. We tried to solve the problem posed in Nexar challenge shown in the following link, (https://challenge.getnexar.com/challenge-1). Although the challenge is over by then we are able to solve to the extent we were almost there matching the 2nd rank shown in their leaderboard. Also we localized the region of traffic lights using UCSD Traffic lights dataset where data for bounding boxes is also available. Apart from this I had many other machine learning and deep learning projects to my credit. Also I am currently enrolled for graduate study at UCSD specializing in Intelligent Systems, Robotics & Control. Following is one of the reference we used for our project (Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks by Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun)

Medium 0 0noe1qqpuw fhvora9ihxyev2kxfhzxve5ghfobp2v blndziogsq0cpde1blq5vegiw mnmouxbgw5v007lxf9vwuxfgw49i07elqospnaagowxiuxwbgw9kb

Jonathan W. updated status

Medium 0 0noe1qqpuw fhvora9ihxyev2kxfhzxve5ghfobp2v blndziogsq0cpde1blq5vegiw mnmouxbgw5v007lxf9vwuxfgw49i07elqospnaagowxiuxwbgw9kb

Jonathan Wan

Race2B is the holistic & motivational digital coach to peak athletes’ performance by leveraging Artificial Intelligence. It collects and analyzes data from 1) race day performance, 2) routine training, 3) dietary consumption, 4) sleeping habits, and 5) health KPI’s, then generates personalized plans that focus on training, nutrition, & recovery. Plus, Athletes will be rewarded for their intensive training and healthy lifestyle by the incentives provided by their health care providers and corporate wellness program.

Default user avatar 57012e2942

Pratool B. created project Identifying Mosquito Species Using Smartphone Cameras

Medium 859a64ff c54d 4612 bc1a 3a6a6ed8ee55

Identifying Mosquito Species Using Smartphone Cameras

According to WHO(World Health Organization) reports, among all disease transmitting insects mosquito is the most hazardous insect. In 2015 alone, 214 million cases of malaria were registered worldwide. Zika virus is another deadly disease transmitted from mosquitoes. According to CDC report, in 2016 62,500 suspected case of Zika were reported to the Puerto Rico Department of Health (PRDH) out of which 29,345 cases were found positive. There are 3500 different species of mosquitoes present in the world out of which 175 types is found in United States. But only few of them are responsible for these above mentioned fatal disease. Therefore classification between hazardous and regular mosquitoes are very important. For regular person with no expertise in this field would be almost impossible to identify the difference. Even for the mosquito expert, identifying different species is a very tedious and time consuming job. Hence in this paper, we have tried to classify 7 different species of dead mosquitoes with total 60 samples collected from Hillsborough County Mosquito and Aquatic Weed Control Unit,Tampa Florida by capturing image from smart phone cameras. With our approach we want to enable nonexpert population to early identify the risk and act pro-actively. We pre-processed the image for removing noise and applied random forest classification algorithm to distinguish different species. Achieved good precision,recall,F1 measure and aggregate 83:3% accuracy. We are also planning to develop a smart-phone application which will leverage this learning model and help in empowering population to identify mosquito species without any knowledge in this field.

Medium test

Fredrik P. updated status

Medium test

Fredrik Präntare

Currently working on my thesis in improving computer-based players for real-time strategy (RTS) games. Currently working on improving agent collaboration in the RTS game Europa Universalis 4 using algorithms based on coalition formation.

Medium 0 00qbtkf3jpss02cyfau8qobf4sde0unaessxlafbr1ss08ujuju3kubfe23hm8zoeaux3q6frxdhjgoajnchnwq3uxdejgeydnc5ikstjoytjorcdrfk5 xmna

Emmanuel F. created project ECG Reading AI

Medium 62c62340 3a34 4574 bf81 d30cc14700ae

ECG Reading AI

An ECG (Electrocardiogram) is a representation of the electric activity around the heart. It is very useful for detecting conditions like heart failure, hypertrophy, infarction, conduction problems and many more. However due to the amount of possible diagnoses that can be made from it, it sometimes take a lot of time and focus to interpret, and for doctors working long stressful sleepless shifts, interpreting this with best accuracy is always challenging. In this project I aim to create an AI algorithm that can interpret this ECG with as much accuracy as the doctor on call, though verification will be necessary to reduce fatal errors. Also this will give the advantage of reading thousands of ECGs in a much shorter time, and hopefully saving more lives in the process and reducing human error.

Default user avatar 57012e2942

Jay B. updated status

Default user avatar 57012e2942

Jay Barbeau

I am a long time developer in multiple languages. My focus is 3D graphics and graphics APIs, (OpenGL, Direct3D, Unity) along with music technology and audio. I have been experimenting with Inverse Kinematics (IK) 3D characters driven by MIDI data in realtime animating characters. My main goals are performance technologies and education technologies. I created an AI driven piano tutor. I want to determine if AI can be used as an expert programming tool to aid my efforts and make me more productive.

Medium abstract 0021

Keoagile D. created project TicTacToe

Medium f495ee31 140b 4126 ad13 36c4ff54eb27

TicTacToe

This project is based on the development of an intelligent game agent that can play Tic-Tac-Toe. This is achieved through the use of minimax game trees, more specifically alpha-beta pruning game trees.

Default user avatar 57012e2942

Deep P. updated status

Default user avatar 57012e2942

Deep Parmar

Myself Deep Parmar. Computer Enginnering student in GTU. I am currently learning knowledge representation and reasoning and CSPs also in AI.

Medium 1

Prateek K. created project WarHammer

Medium 355b551b 3cf2 4f7d 979c d7303d310e2e

WarHammer

With modern technology becoming obsolete in cyber security, we need to come up with innovative ideas to increase the notch up in the fight against unauthorized access to our information and data. I will be taking help of Theano,Torch,Microsoft CNTKA framework to start with and then modify the implementation as i move in later stages of the project. I will be trying to modify various protection algorithms and try to come up with a ML algorithm that takes help of deep learning frameworks. I will also be taking help of Gensim to validate my data collection as efficiently as possible. The changes to encryption and decryption techniques will be studied thoroughly in later stages. In a manner where DNA cannot be replicated , similarly developing a neural network net around my algorithm against network intrusion will be the deciding factor in the efficiency of the modified algorithm. I will also taking help of Apache Hadoop in analyzing my stored data from cyber attacks and storing the result of my predicament in Apache Spark to make real-time decisions. The main problem in using machine learning algorithms in cyber security is the creation of an overhead which has an adverse effect on algorithm's performance. To eliminate it to a appreciable stage I will be taking help of BlueData without any changes to Hadoop or Spark framework. Finally the performance of the algorithm will be tested with the help of BigBench kit to get a full report on the project.

See More

Projects (52)

See All

Bigger 0 1gp1cxhoi0clkcyy8n3lhzpu 3748byvif3kf3h4 diz8up9kchzbw8jkt7anckjcf3k9o3j ufj1qgvk9syhktyqufg1qcmn9savxgottyn1a1rntgrpqtbnf
  • Projects 0
  • Followers 2

Piotr Januszewski

Studies at University of Technology in Gdansk, Computer Science. Internship at Intel Technology Poland. Lead of ML research circle.

Gdańsk, Poland

See More

Thumb f74d657d 70da 455c 893f dc8dea72f1ec
  • Collaborators 0
  • Followers 3

Follow

Reflections

Thumb paul langdon Paul Langdon

Created: 01/13/2017

MagicMirror+ for Intel Joule - Adding Face/Voice Recognition & Control using RealSense, Amazon Vo...

Thumb 8d3f9093 8bc6 40ff 8255 f5421e9631d6
  • Collaborators 0
  • Followers 0

Follow

Triton UAS

Default user avatar 57012e2942 Marco Flowers

Created: 03/03/2017

Triton UAS is an engineering student organization at UC San Diego that develops deep learning sys...

Thumb c16938dc 0b47 4631 8c54 085cf2df8645
  • Collaborators 0
  • Followers 4

Follow

IRPML

Thumb 1 Yeser

Created: 01/17/2017

ML generated model of robotic arm.

Thumb 771a9e41 7813 4f79 b307 94100eacc29e
  • Collaborators 0
  • Followers 0

Follow

ReconBot3000

Thumb qgk3r0ui Joyce Rigelo

Created: 11/06/2016

With the superpowers of the Intel Joule and the RealSense Camera, ReconBot3000 patrols your home ...

See More