In a breakthrough development, researchers have developed a machine-learning method to determine how to improve the outcomes of existing medications for diseases these are not prescribed. The method involves crunching massive amounts of data.
In fact, the objective of the work is to expedite drug repurposing – a concept not new in the pharma sector. For example, Botox injections that were first used to treat crossed eyes now find use to treat migraine, and are a top cosmetic strategy to lessen the appearance of wrinkles.
However, to discover new uses of existing medication is a mix of few things. It is time-consuming, involves expensive randomized clinical trials, and serendipity. The success of such efforts ensure a drug deemed effective for one medical condition will be useful for some other condition as well.
Meanwhile, researchers at the Ohio State University developed a framework that combines massive datasets pertaining to patient care with high-powered computation. This leads to arrive at repurposed drug molecules and estimated effects of existing medications on predefined outcomes.
Whilst the focus of the study is to propose repurpose of drugs to prevent stroke and heart failure in patients with coronary artery disease- the flexible nature of the framework enables its application for most diseases.
“Besides this, the work showcases how artificial intelligence can be used to examine how a drug works on a patient. In addition, the framework expedites hypothesis generation and speeds up clinical trials,” said a scientific associate at the Ohio State University.
Nonetheless, drug decisions will remain with clinicians.
Notably, drug repurposing is an attractive vocation. This is because it could lower the risk related with safety testing of new medications.
Consumption of heat pumps is on the rise. As more households install them, their importance in the market gains weight. More than 50% new homes in Switzerland have advanced heat pumps. These pumps use thermal energy stored inside the ground, or in the air, to generate heat. Further, heat pumps in houses function at near-optimal values. However, there is tremendous scope for improvement. Manufacturers can improve their efficiency replacing conventional compression systems with micro-turbo-compressors. The latter can reduce power requirement of a heat pump 25%.
Conceptualization of Turbo Compressors
The small size and high efficiency of turbo compressors is responsible for their contribution to pump performance. However, it is difficult to incorporate such a small device into the heat pump. The small diameter of turbo compressors, coupled with their fast rotation speed, makes it difficult to affix them. The Laboratory for Applied Mechanical Design at EPFL’s Microcity campus has made a key breakthrough in this regard. The research team at the laboratory developed a viable method to attach turbo compressors in heat pumps. They used machine-learning techniques to calculate the correct dimensions of turbo compressors required for different pumps. Researchers used symbolic regression to calculate the diameters.
Future Research and Predictions
The research can help in simplifying the design of heat pumps as well as turbo chargers. Cyril Picard and Violette Mounier of EPFL lead the research, using around 500,000 simulations. The research could open new doors towards the manufacture of high-efficiency heat pumps. Furthermore, the new turbo chargers would serve greater advantages as against conventional ones. The newly developed turbo-compressors could run 1,500 times faster than other types of compressors. It is expected that the use of micro-turbo-chargers would increase in the years to follow. Furthermore, conventional heat pumps could gradually move out of sight.
Based on the current reports published by McAfee, financial fraud and cybercrime cases are costing a great sum of around US$600 billion. This is equal to the 0.8% of the overall GDP and creates an urgent need for more effective security and safety techniques.
Well-known financial organizations are dominating from the front end, by incorporating the advancement and upgraded cyber-security services. This helps in securing the information and customer privacy. Small scale players are trailing the pack in an IT industry which is around the worth of US$153 billion, internationally.
Insight into Strategy:
With the rapid change in financial scenario, the market view is also changing. The advanced technologies are providing the platforms and tools for the high paced changes in upcoming tiems. This upgradation is highly supported by Big Data that is penetrating broder and deeper since [past few years. Financial insititues and banks have the right to access more data regarding their customers and their pattern of expenditure. Even though this has resulted in the emergence of chatbots for resolving the customer issues, still, the banks are now focusing on the advanced technologies for example machine learning and artificial intelligence to reduce the financial risks.
A survey carried out in 2018, by PwC calculated that around 49% of the international firms have gone through financial crimes in last two years. The chances of electronic fraud has risen due to increased online transactions. Moreover, cyber criminals can now use the cryptocurrency exchange to withdraw or transfer the money from their fraudulent activities.
Researchers have now shown how to interpret what the human brain is observing with the help of the artificial intelligence to decode the fMRI scans from people watching videos, making it a kind of a technology for mind-reading.
These advances in technology could help the efforts to enhance the artificial intelligence and direct to newer insights into the functioning of human brain. Important to the research is a kind of algorithm known as the convolutional neural network, which has been vital in making smartphones and computers able to identify objects and faces.
Convolutional neural networks, a type of ‘deep learning’ algorithm, have been chiefly utilized to understand how the human brain interprets and processes static pictures and different visual stimuli. However, these new discoveries can be seen as the novel approach used for the first time to understand how the human brain processes movies of natural scenes, a huge step towards interpreting the brain while people are trying to grasp and make sense of the dynamic as well as complex visual surroundings.
This new research has been led Haiguang Wen who is also the lead author and the findings were published in the October issue of Cerebral Cortex Journal.
The researchers gathered 11.5 hour long fMRI data from of each of the three subject women who were made to watch 972 video clips which included clips of people or animals in nature or action scenes. The information was used to train and instruct convolutional neural network model to project the activity in the visual cortex of brain while the women were watching the videos.