Machine Learning and AI development laboratory
INGENIX
Create complex AI allied solutions based on machine learning,
computer vision, image recognition and expert systems integration
Both pictures and video stream recognition systems including One-shot Image Recognition. Strong competence in creating computer vision apps and integrating image-recognition ai-solutions.
Text generating systems, recommendation systems based on text recognition, classification and clusterization algorithms. Our work covers areas such as sentence understanding, syntactic parsing and tagging, sentiment analysis, and models of text and visual scenes.
Create prediction and classification models using both traditional and deep learning. Develop deep configuration architecture and unsupervised feature learning mechanism that can handle a large amount of data.
AI can rapidly analyze large amounts of data and detect abnormalities, thus it is very well suited for monitoring applications, such as detecting credit-card fraud, cybersecurity intrusions, early warning signs of illnesses, or important changes in the environment.
AI can extract valuable insights from large datasets, often referred to as data mining.
In particular, because AI uses dynamic models that learn and adapt from data, it is
very effective at uncovering abstract patterns and revealing novel insights.
AI can forecast or model trends, thereby enabling systems to predict and personalize responses. These types of applications, such as Netflix’s recommendation algorithm, analyze users’ viewing histories and suggest new titles that they might like.
Until recently, most data analytics was focused on structured data.
Because AI can learn and identify patterns, it can interpret unstructured data,
such as images and text.
AI allows autonomous systems to engage directly with the physical environment. It enables robotic systems that can navigate and manipulate the world around them.
AI can allow humans to interact more easily with computer systems. With AI
computer systems can respond to speech, gestures, and even facial expressions.
AI can automatically coordinate compli- cated machine-to-machine interactions e.g.
data center computing activity and environmental conditions control.
Autonomous indoor farming system can use networked sensors and machine learning to constantly monitor a farm’s environment and plants condition and adjust lighting, temperature, humidity, water, and soil nutrient levels or notify the farmer about the plant’s diseases e.g. mold, bacteria, or insect damage. The system learns from historical data and refines its predictions to maximize the farm’s productivity.
A start-up called One Concern has developed a system that uses AI to model a town’s buildings, based on factors such as building age, density, and construction materials, and predict how they would react to seismic activity.70 If an earthquake hits, One Concern can plug in the new seismic data to estimate which areas are likely the most damaged.71 Using these predictions, first responders can prioritize disaster response efforts to target the hardest hit areas after an earthquake.
Researchers at Stanford University have developed a machine-learning system that can predict M- and X-class solar flares, which produce dangerously high levels of radiation that could harm airline passengers, damage power grids, and disrupt communication satellites.80 The system analyzes data about the sun, such as the topology of its magnetic field and its atmosphere, and can identify regions of the sun likely to produce solar flares.81 More advanced warning of when and where a solar flare could occur will allow airlines, power grid operators, and others to take precautionary measures to avoid danger.
The ability to predict the stock market is, as any Wall Street trader will tell you, a license to print money. So stock analytical systems are of no small interest to anyone, who develops machine learning. System of this kind work by ingesting large quantities of financial news along with minute-by-minute stock price data, and then using the former to figure out how to predict the latter. The algorithm buys, or shorts, every stock it believes will move more than 1% of its current price in the next 20 minutes - and it never holds a stock for longer. The results are quite impressive: such an algorithm performs at least on parity with the 10 top rated funds (S&P top 500 rating).
Autonomous recycling system uses a robotic arm, an array of sensors, and AI to identify recyclable items in waste and separate them for recycling, removing the need for manual sorting. It analyzes trash on a conveyer belt using 3-D scanning, spectrometer analysis, and other methods to determine what a piece of trash is made of, and, if recyclable, a robotic arm will pick it up and move it to a separate container.
Virtual-assistant service can analyze employee calendars and emails to automatically schedule meetings and adjust calendar appointments. Users can copy the virtual assistant in emails when they want to set up meetings, and it will analyze email text to determine the topic and time of a meeting, determine if there are any conflicts, and automatically schedule calendar appointments. The app can also search for and add relevant phone numbers, reschedule meetings by conversing with users, and learn users’ preferences over time.
As part of the Dutch government’s European Truck Platooning Challenge, a fleet of autonomous trucks has successfully traveled over 2,000 kilometers by platooning — monitoring each other’s speed, proximity, and the road to drive close together to improve efficiency, much like bicyclists drafting off each other. It is difficult for human truck drivers to platoon, given the level of coordination required to do it safely, but platooning autonomous trucks can reduce fuel consumption by up to 15 percent and can also reduce congestion.
Autonomous indoor farming system can use networked sensors and machine learning to constantly monitor a farm’s environment and plants condition and adjust lighting, temperature, humidity, water, and soil nutrient levels or notify the farmer about the plant’s diseases e.g. mold, bacteria, or insect damage. The system learns from historical data and refines its predictions to maximize the farm’s productivity.
Continue reading
Machine learning based systems are very efficient in predicting consumers’ behavior and prompt business whenever it is at risk of losing a customer. AI based systems can be useful for customers themselves by helping to walk through the enormous amounts of information currently available in the web and choose exactly what they like. ML algorithms can do it processing the user’s preferences history and constantly improving the accuracy of forecast by learning and adjusting over time.
Continue reading
AI algorithms develop tremendous opportunities for early diagnostic, drug development research, clinical trials, health state monitoring or even surgery. For example, image-recognition algorithm can analyze retinal scans of diabetes patients and learn to identify subtle signs of diabetes-linked retinal damage with 85 percent accuracy. Another AI based system analyzes large amounts of oncological data, creates a complete model of how the cancer functions, and find a way to target the specific metabolic processes that contribute to its rapid growth to make cancer cells more responsive to chemotherapy.
Continue reading
Educational software uses machine learning to analyze users’ activity and progression to develop personalized lesson plans, as well as regularly tests new strategies for instruction to evaluate their effectiveness. It structures particular lesson plans differently for various users to learn how the differences correspond to improved outcomes and implement the most effective strategies.
Continue reading
AI has found a wide application in improving the efficiency of telecommunication networks. The AI based systems combine massive amounts of real-time network and business data in a way not previously possible. Analytical systems incorporate machine learning, fraud threat scoring, profit threat analytics etc. The safety of telecommunications infrastructure is another important implementation for AI currently, while the further development of technology reveals even more exiting services like real time translation of conversations.
Continue reading
Well-deployed AI prediction tools have the potential to provide new kinds of transparency about data and inferences, and may be applied to detect, remove, or reduce human bias and violence. Drones, with AI systems applied, are the part of AI application for public safety and security. The same software applied to cameras records from public places and will allow the government to rely on AI to assess the behavior and public safety.
Continue reading
Transportation is likely to be one of the first domains in which the general public will be asked to trust the reliability and safety of an AI system for a critical task. Autonomous transportation will soon be commonplace and, as most people’s first experience with physically embodied AI systems, will strongly influence the public’s perception of AI. Once the physical hardware is made sufficiently safe and robust, its introduction to daily life may happen so suddenly as to surprise the public, which will require time to adjust.
Continue reading
Industrial managers, engineers, and technologists have many expectations from AI and its application to knowledge-based systems. AI is expected to be applied by integrating it into a full chain of production. Vision for better grasping and identify desirable/undesirable items, reinforcement learning to easily adapt the system (and may be even make the learning also use vision and identify casual link by looking at an employee and map it to him), then scheduling and optimization for managing the chain from raw products to the delivery and reduce the costs. This is the kind of factory we may see emerge sometime in the future.
Continue reading
Certain areas of business will feel the impact of AI first – whenever data needs to be analyzed, AI is the perfect vehicle to achieve this. Another acceptable definition of artificial intelligence in business is the simulation of skills that are considered innate in people. Those skills include the use of reason and logic to make simple and complicated decisions. They also include the capability to recognize speech, speak and understand natural language, respond to verbal and written messages and recognize patterns.
Continue reading
In line of principle, there are very few activities in the Engineering field that cannot be performed by an “automated” tool working under the paradigms of Artificial Intelligence. In the specific area of energy systems, possible AI applications can be: intelligent mass and power control; temperature, pressure and phase composition control; fault detection and alarming; sensor diagnostic; implementation of complex control, decision-based on flexible, non-deterministic strategies, analysis of critical events and the others.
Continue readingWe invent the next generation of computer infrastructure through innovations in software design, enabling new applications for mobile, cloud and data-intensive computing.
Our work ranges from basic research in AI algorithms to key applications in banking, retail, insurance and automotive industries. A distinguishing feature of the Ingenix team is an effective combination of classic software development with innovative probabilistic, machine learning, and deep learning approaches.
INFO at INGENIX.AI
