Tech

http://www.metivity.com/ The Traveling Salesman Problem TSP is defined as finding the minimum length of a cyclic path that runs through a list of known cities say n cities. This problem is NP-Hard which means there is no efficient algorithm that finds the shortest path except for the one that checks all or too many of the possible paths. It is very popular today to solve this problem by using genetic algorithms and many nice demos can be found over the internet. Problems begin when stochastic hillside climbing gets stuck because too many correct mutations need to appear in order to reach new solutions. This problem can only be partially solved by the use of Transposons or Retrotransposons (Jumping sequences of code or Jumping Genes) and by continuous reduction of the TSP problem to simpler TSP problems. This reduction is unmatched in Nature because multiple evolution environments in the presented model simultaneously exist. Moreover, it is evident that in one out of five simulations, large scale Transposon mutations are insufficient and more complex large scale mutations are required. These were called Insertion Rotation mutations. here is some sample of using the regular GA vs. complex large scale mutations GA (GA1-GA2).

http://metivity.com evolution of fish. each fish is a neural net. The purpose of this application is to develop a "killer fish" - a fish that eats maximum pieces of food in a constant time period. The world is populated by 20 fish and 40 pieces of food. every time a generation begins. the food is scatted in a random distribution on a certain random location on the screen. (random piles of food). When being eaten, the food shows up in a new random pile in the screen. Every fish has a brain - Neural Net. It has 2 inputs: the direction and velocity of the fish. (himself). the relative location of the closest food. and two outputs: velocity of right wheel. velocity of left wheel. You can refer to the movement as a tank with two chains, and the output as the velocity of each chain. the target is to find weights for the neural net that will give the fish a "killer-brain"... When running the application you will see the generations go by. In each generation we select the best fish in generation and breed them to form new 20 fish. the brains (Neural Nets) of the initial 20 fish are created randomly. This explains why they are so "stupid". look how they improve as time goes by. their logic is being build by evolution, without interference. http://metivity.com

myairbase.com

AirBase ( http://www.myairbase.com/ ) developed a multi-sensors monitoring unit incorporating the most advanced Nano-Tech sensors technology. These tiny sensors carry unique characteristics; low electricity consumption, excellent sensing capabilities, no maintenance and most importantly: they are very low cost. AirBase is offering a breakthrough in air pollution monitoring! Our system is currently equipped to measure levels of pollution caused by transportation: Ozone, NO2, Total VOC, TSP (Total Suspended Particles), noise, relative humidity and temperature. Other pollutants sensors can be added per request -- SO2, Odor, Light, P.M 2.5 and more. The highly compact sensors are stored in a "home router" like box that is simply powered-in and hooked to the internet (Wi-Fi or GSM) - just plug & play. Immediately after it is connected, the sensors are operative, sending a pulse of information every 20 second. Any deviation from the allowed (or inputted) exposure standard will generate an immediate alert.

This video is about Metivity deep dive