I'm learning machine learning and discussing my questions and sharing insights at CppMSG
One out of every twenty people does not have access to medical facilities. Skin diseases and afflictions affect more than 80% of the world’s population and are sometimes a sign of internal problems. Skin diseases are primarily diagnosed visually, and then by more invasive procedures (dermoscopic analysis, biopsy, and histopathological examination). A similar issue arises with plants, with more than 30% of crops in less affluent areas dying due to diseases. Due to this loss of crops, one in nine people are suffering from chronic undernourishment.
Automatically detecting and diagnosing these lesions has been challenging, owing to the variable properties of each disease image. Deep convolutional neural networks (CNNs) are a new method of machine learning, one that is showing to be extremely promising at detecting images with real world variables. (lighting, focus, etc.)
In this project, I classified skin and plant ailments/diseases using a specially developed CNN, trained using only images of the conditions with only pixels and disease labels as inputs. I trained the CNN on a dataset of 200,000 clinical and horticultural images, consisting of 13 human diseases and 17 plant diseases. Outfitted on an IOS device, my application is capable of classifying skin and plant diseases will a level of competence comparable to dermatologists and plant pathologists. All the user must do is aim the camera of the smartphone towards the diseased area, and my application will provide a real-time diagnosis to the user by classifying the image using the CNN. The CNN achieves performance far above any other tested system, and its efficiency and ease of use will prove it to be a helpful tool for people around the world. There are currently 6,000,000,000 mobile subscriptions in place, so, therefore, my application could potentially provide low-cost universal access to vital diagnostics.
This project was made to enliven our communities - GameLan Booth at Bekraf Developer Day (BDD) Solo 2017. BDD is an event when many developers gathering at one place. There’s seminar, talk show, and workshop from the top Player in Indonesian Tech Industry come and join to share their knowledge to others.
The Project itself called with Ungek-Ungek Game. As the controller of this game made with Ungek-Ungek, an old children toys that always made sound “ungek ungek” when it’s swayed. We thought it would be so cute and alarming for the audience, with this unique controller that usually being played with friends in their old days, now becoming a device that can make a Ninja to jump and run.
The Game design of this is relatively simple, a one level platformer game that led by a ninja. The objective of this game is looking for a scroll. The controllers are made and customize as the higher sound the sensor’s accepted, the Ninja will jump. And the softer sound the sensor’s accepted, the ninja will run.
This Game and the controller were made with an internal game jam . The Development of this Game made with Construct 2 and Paint Tool SAI for the assets.
We would like to simulate the game of wingsuit with an iron custom construction that contain a man. The construction consist in 2 concentric centers like an Vitruvian Man (or 2 cyr wheel). INTEL Edison controls 2 motors that rotate right and left with a single hand. With 2 hands control top and down of the ather moter (Edison n.2).
Underwater experience in VR using Unity's terrain generation tool. The player can dive alongside fish and run away from dangerous sharks.
In order to achieve a good frame rate and a non-excesive number of vertices and draw calls, a short camera clipping plane was used. The terrain tool had to use a very low detail level, and a blue fog effect was used to make it look realistic while using these measures to achieve better a performance.
This experience will be used for educational and demo purposes.
Game where you have to jump in real life, and the character will jump in VR. This only works in HMD that have position tracking, so that the game can capture the person's acceleration and trigger a jump in the game.
This game will be used for educational purposes - to teach people how to make VR games and to show how VR can be used in a fitness context.
I might extend this project into a commercial game, but haven't decided yet.
C# wrapper for the cross-platform camera capture for Intel® RealSense™ F200, R200, SR300 and LR200. See the original C++ project on https://github.com/IntelRealSense/librealsense
My experience from attending Spark Summit 2016 https://software.intel.com/en-us/blogs/2016/09/09/my-experience-from-spark-summit
Astronauts (or anyone interested in experiencing zeroG) will be provided with everyday tasks facing astronauts in the space, user has to move the vive controllers in a similar way to how an astronaut will do it in the space to be able to move. Teleportation methods can be programmed into the game as well.
Upon completion of a specific task, the environment can be changed to provide the user with a more difficult task. This provides a real experience to anyone interested in experiencing spacewalks too.
Due to unpredictable movements in ZeroG, it is very hard to use a laptop inside the chamber. A backpack PC looks like the perfect solution for this application.
The MSI VR One backpack PC provide the perfect combination of high performance and portability needed for this project.
Temperature is one of the very important daily parameters. Although temperature change is a natural phenomenon, it is very important to measure it and thereby control it. There are many methods that have been put into place to measure and control temperature such as glass thermometer, thermocouples, thermistors, resistance temperature detector, and many more, with each having its own disadvantages (accuracy, small temperature range and so on); however, with the advancement of technology and science, it has become crucial to measure and control temperature using the latest, and more importantly, the most sophisticated technology.
No users to show at the moment.
No users to show at the moment.