3 new ways technology is helping to advance medicine

Imaging Cameras improving cancer surgery Every year, 14 million people are diagnosed with cancer; of those, around eight million will die. Cancer is one of the leading causes of death worldwide; across the globe, doctors and scientists are fighting to reduce the number of cancer deaths by detecting cancer early and promoting new ways of battling it. In the past, imaging technologies such as radiography, magnetic resonance imaging and computed tomography have proved vital in the fight against cancer, helping doctors to diagnose the disease quickly to increase the chance of recovery. Now, near-infrared fluorescence (NRF) has emerged as a new, powerful imaging tool in the battle against cancer. NRF imaging is used during surgery to enable surgeons to easily distinguish between healthy tissue and cancerous tissue. Surgery is a highly effective method of treating cancer patients, but its success rate depends largely on how much of the cancer is…

Continue reading

Future of Artificial Intelligence; Its Implementations and Limits

Artificial Intelligence (AI) is the field of computer science which uses mechanical and computational processes to echo almost all aspects of human intelligence. AI can perform multiple functions: sensory interaction with the environment and the ability to make decisions about events that aren’t happened yet without any human assistance whatsoever. Targeted advertising and virtual agents that recognize the patterns of your behavior are much standard in today’s online undertakings. Artificial Intelligence is used by business enterprises in data analysis algorithms which have the highest advantage of analyzing the Big Data, and it also involves customer engaging techniques. Apart from IBM which developed some of the earliest functions of AI, Google and Facebook are also using AI for the analytic purpose of the massive amount of data they receive.

Continue reading

8 Reasons Why EVs are the Future of Transportation

Electric Vehicles (EVs) are quickly becoming a leader in the automotive industry. With increasing concerns about pollution levels worldwide, and the rise and fall of gas prices, taking a greener approach to our transportation is the clear solution. If you’re intrigued by an ultra low cost, low emissions answer to our gas-guzzling vehicles, you’ll want to check out the below infographic created by Auto Loan Solutions. This informative and interesting infographic demonstrates the revolution of EVs, and how this evolved from a trend to a reality. This infographic proves that concerns about the reliability or power of these vehicles have no basis. By 2040, EVs will make up 35% of new car sales. As well, EV charging stations are becoming as readily available as gas stations – currently surpassing that of gas stations in Japan.

Continue reading

Building and evaluating Naive Bayes classifier with WEKA

This is a followup post from previous where we were calculating Naive Bayes prediction on given data set. This time I want to demonstrate how all this can be implemented using WEKA application. For those who doesn’t know what WEKA is I highly recommend visiting their website and getting latest release. It is really powerful machine learning software written in Java. You can find plenty of tutorials in youtube on how to get started with WEKA. So I wont get in to details. I’m sure you’ll be able to follow anyway.

Continue reading

Simple explanation of Naive Bayes classifier

Probably you’ve heard about Naive Bayes classifier and likely used in some GUI based classifiers like WEKA package. This is a number one algorithm used to see the initial results of classification. Sometimes surprisingly it outperforms the other models with speed, accuracy and simplicity. Lets see how this algorithm looks and what does it do. As you may know algorithm works on Bayes theorem of probability which allows to predict the class of unknown data set. Hoe you are comfortable with probability math – at least some basics.

Continue reading

Linear regression with multiple features

linear regression cost function

Single feature linear regression is really simple. All you need is to find function that fits training data best. It is also easy to plot data and learned curve. But in reality regression analysis is based on multiple features. So in most cases we cannot imagine the multidimensional space where data could be plotted. We need to rely on methods we use. You have to feel comfortable with linear algebra where matrices and vectors are used. If previously we had one feature (temperature) now we need to introduce more of them. So we need to expand hypothesis to accept more features. From now and later on instead of output y we are gonna use h(x) notation: As you can see with more variables (features) we also end up with more parameters θ that has to be learned. Before we move lets find suitable data that we could use for building…

Continue reading

USB Boost Single Multi Power Kit assembly

multiple power supply module connected

One of my projects (AVR DDS 2.0) requires multiple power supply that could supply +12V, -12V, and 5V. Back then I have constructed simple transformer based power source with few linear voltage regulators. It works fine, but is powered from mains 220V which is not safest solution to squeeze in to box enclosure. Other option was using ATX PC power supply, but it is too big. Banggood have been offering pretty neat power supply kit which has voltage boost circuit which rises voltage level either from USB or from 5-24V jack. Power supply kit has most of voltages that you may need including + 12V, -12V, + 5V, -5V , and +3.3V. It is capable to output 300mA per channel. Total power is limited to 10W which is not bad and can provide short-term high current single output, but be sure to attach included heat sinks in order to protect…

Continue reading