Mediaboss Marketing

How do we make autonomous cars safer?

That question, which is critical as self-driving cars are increasingly found on American roads, is just one that NAU researcher Truong Nghiem hopes to answer with a new project that looks at ways to integrate machine learning and physical principles into large-scale cyber-physical systems.

Nghiem, an assistant professor in the School of Informatics, Computing, and Cyber Systems, received an NSF CAREER grant for this project, which aims to develop a comprehensive and flexible framework for effective and efficient machine learning with physical constraints, which can fundamentally change how we apply machine learning to complex systems like smart energy systems, industrial automation systems and autonomous robots and cars. The CAREER award is the National Science Foundations most prestigious award for early-career faculty.

A critical challenge is how to guarantee the performance and safety of these systems, as they are typically performance- and/or safety-critical, where any failure could have devastating consequences, Nghiem said. Our approach is to tightly integrate machine learning and physical principles. The framework developed in this project will be a foundation for such an integration and will be a stepping stone toward solving the challenge. It will help make future autonomous cyber-physical systems reliable and safe.

A cyber-physical system (CPS) is an engineered system that is built from, and depends on, seamless integration of computational and physical components. They are the foundation of many modern engineering systems that make up our daily life, including cars, robots, medical devices, power grids and more, and they are becoming even more common as our lives become more automated.

Many of these systems employ machine learning and, increasingly, artificial intelligence. However, machine learning, which isnt always informed by physics, doesnt always provide the best way to teach these systems. Nghiems research focuses on physics-informed machine learning (PIML), which is capable of developing methods that seamlessly embed knowledge of a physical system into machine learning, leading to robust, accurate and consistent models.

In autonomous cars, rovers, drones and similar systems, that means fewer system errors and a safer experience for the vehicle and nearby people. However, current PIML methods are functionally too small to meet those needs.

Enter composite physics-informed machine learning, or CPIML. Nghiems project aims to advance the data-driven learning of complex, large-scale systems by synthesizing many PIML and physical component modelsits the physics equivalent of LEGO blocks that can be put together to build much larger, more complex models, with each block being an already-developed model or piece of machine learning.

This groundbreaking solution will require integrating the cyber world (machine learning, AI and computing) and the physical world (dynamic and control systems) in engineered systems, so that each world is aware of and can integrate with the other. The result will be a safer world through which people move.

Smart and autonomous cyber-physical systems will tremendously impact our lives in the near future, Nghiem said. Our productivity will substantially increase with autonomous helper robots, advanced industrial automation (Industry 4.0) and many autonomous systems in our work and personal life. Our energy infrastructures will be more efficient and reliable, and our transportation will be safer and faster. These all depend on modern technologies, including cyber-physical systems and recent advancements in machine learning and AI.

Nghiems research will also offer valuable opportunities for graduate and undergraduate students to engage in software development and real-world applications.

Heidi Toth | NAU Communications (928) 523-8737 | heidi.toth@nau.edu

Go here to see the original:
How NAU is making self-driving cars safer and smarter The NAU ... - NAU News

Machine learning startup Tecton has entered into a strategic partnership with Google Cloud to make its Tecton Feature Platform available to Google Cloud users. The platform automates the process of collecting, preparing, managing, and updating high-quality data required for training machine learning models. It ensures that the models have access to real-time predictive and generative AI applications. Tectons partnership with Google Cloud will help solution providers speed up the development of machine learning models while keeping costs under control.

Tecton was founded in 2019 by the developers behind Ubers Michelangelo machine learning platform. The company has raised $160 million through multiple funding rounds. Its platform is used for various applications, such as pricing, customer scoring, recommendation engines, automated loan processing, and fraud detection systems. These applications involve making complex decisions at scale and with high reliability. Tectons platform automates the process of creating machine learning features that power these models.

Google Cloud offers its Vertex AI system for training and deploying machine learning models and customizing large language models. Its data processing infrastructure services like DataProc and BigQuery are also commonly used in machine learning projects. The Tecton platform serves as a connective fabric, integrating these systems to build production-ready ML features. It automates the entire ML feature lifecycle, from definition and data transformation to online serving and operational monitoring.

Using the Tecton platform helps developers build better machine learning models by leveraging high-quality data. By automating data transformation and management, ML systems can be deployed into production faster. The platform also provides enterprise management and collaboration features that are often missing in ML initiatives.

Solution providers and strategic service providers performing AI and machine learning development work can use the Tecton-Google Cloud combination to work more efficiently. This partnership offers advanced machine learning feature engineering capabilities and accelerates the building of machine learning applications. It provides solution providers with another option to help their customers succeed in their ML initiatives.

Visit link:
Tecton Partners with Google Cloud to Accelerate Machine Learning ... - Fagen wasanni

Maximizing Efficiency in Brewery Wastewater Treatment through Machine Learning

In recent years, the brewing industry has been grappling with the challenge of wastewater management, a critical issue that has significant implications for both the environment and the cost of production. However, the advent of machine learning technology is proving to be a game-changer, transforming the way breweries handle wastewater treatment and significantly enhancing efficiency.

Traditionally, breweries have relied on manual monitoring and control systems to manage their wastewater treatment processes. This approach is not only labor-intensive but also prone to human error. Moreover, it often fails to optimally utilize resources, leading to unnecessary waste and increased operational costs.

Enter machine learning, a subset of artificial intelligence that enables computers to learn from data and make predictions or decisions without being explicitly programmed. In the context of brewery wastewater treatment, machine learning algorithms can analyze vast amounts of data from the brewing process, identify patterns and trends, and use this information to optimize the treatment process.

One of the key ways machine learning is enhancing efficiency in brewery wastewater treatment is through predictive analytics. By analyzing historical data, machine learning models can predict future outcomes with remarkable accuracy. For instance, they can forecast the amount of wastewater that will be produced in a given period, allowing breweries to plan their treatment processes more effectively. This not only reduces the risk of overloading the treatment system but also helps breweries save on treatment costs.

Furthermore, machine learning can optimize the use of treatment chemicals. By analyzing data on the composition of the wastewater and the effectiveness of different treatment methods, machine learning models can determine the optimal amount of chemicals to use. This not only minimizes chemical waste but also ensures that the treated water meets environmental standards.

Another significant benefit of machine learning in brewery wastewater treatment is its ability to detect anomalies. By continuously monitoring the treatment process, machine learning algorithms can identify deviations from the norm, such as sudden changes in the composition of the wastewater or malfunctions in the treatment equipment. This allows breweries to address issues promptly, preventing costly disruptions and ensuring the consistency of the treatment process.

Moreover, machine learning can facilitate the reuse of wastewater in breweries. By analyzing data on the quality of the treated water, machine learning models can determine if it is suitable for reuse in non-critical processes, such as cleaning or cooling. This not only conserves water but also reduces the brewerys water footprint.

In conclusion, machine learning is revolutionizing brewery wastewater treatment, driving efficiency in multiple ways. From predictive analytics and chemical optimization to anomaly detection and water reuse, this cutting-edge technology is enabling breweries to manage their wastewater more effectively and sustainably. As machine learning technology continues to evolve, its impact on brewery wastewater treatment is likely to grow, offering even more opportunities for efficiency and sustainability.

See the original post:
How Machine Learning is Improving Efficiency in Brewery ... - EnergyPortal.eu

Overview

The incorporation of Artificial Intelligence (AI) and Machine Learning (ML) in the healthtech industry has sparked an innovation in patient care, medical research, and healthcare efficiency. These pioneering technologies are strengthening the healthcare providers and researchers with several treatment options. However, as the healthtech segment continue to evolve, maintaining a balance between innovation and security is extremely important in order to protect sensitive patient data and ensure ethical AI practices. Here, we explore five leading brands that leverage Artificial Intelligence and Machine Learning to drive innovation in healthtech while prioritizing data privacy and security.

IBM Watson Health stands at the forefront of AI and ML-driven healthtech innovation. Their flagship project, Watson for Oncology, harnesses cognitive computing to analyze vast volumes of medical literature, clinical trials, and patient data to offer personalized treatment options for cancer patients. The system can suggest evidence-based treatment plans, helping oncologists make well-informed decisions. With a strong emphasis on data security and privacy, IBM Watson Health adheres to regulatory standards, ensuring the protection of patient data and compliance with HIPAA (Health Insurance Portability and Accountability Act) guidelines. The brands commitment to transparency in AI decision-making processes fosters trust among healthcare providers and patients alike.

NVIDIA Clara is a comprehensive AI platform designed explicitly for healthcare. Leveraging the power of NVIDIAs high-performance GPUs, Clara provides healthcare professionals with advanced imaging and visualization tools. These tools enable faster and more accurate medical imaging diagnosis, surgical planning, and drug discovery.

Recognizing the sensitivity of medical data, NVIDIA has implemented strong security measures within the Clara platform, ensuring data encryption, access control and audit trails. Additionally, the platform adheres to industry standards, such as DICOM (Digital Imaging and Communications in Medicine), to facilitate seamless integration with existing healthcare systems while safeguarding patient privacy.

Noventiq is a leading global provider of solutions and services in the realms of digital transformation and cybersecurity. Noventiqs expertise lies in facilitating and enabling digital transformation processes, empowering their customers to adapt to the evolving digital landscape. It provides cloud protection services and AI algorithms, ensuring that customer data and applications hosted in the cloud are secure and protected from unauthorized access to health related data to maintain patient privacy.

Siemens Healthineers combines AI and ML technologies to enhance medical imaging, diagnostics, and precision medicine. Their AI-Rad Companion platform assists radiologists by automating image analysis, facilitating faster diagnosis, and reducing the chance of human error.

Recognizing the importance of data security in the healthcare domain, Siemens Healthineers adheres to international data protection standards and implements state-of-the-art encryption protocols to protect patient data at all stages of processing and transmission. Their robust compliance measures assure both healthcare providers and patients that their data remains secure and private.

Cerner Corporation is a global leader in electronic health record (EHR) systems and clinical information solutions. Through their AI-enabled HealtheDataLab, they empower healthcare researchers with access to vast amounts of anonymized patient data for population health studies and medical research.

Cerner Corporation places utmost importance on data privacy and compliance with healthcare regulations, ensuring that all data is de-identified and anonymized before use in research. Their commitment to patient data security has gained the trust of healthcare institutions worldwide, enabling valuable AI-driven insights without compromising patient privacy.

AI and Machine Learning have undoubtedly ushered in a new era of innovation in healthtech, promising improved patient care, faster diagnoses, and groundbreaking medical research. The five brands mentioned above illustrate the balance between innovation and security, setting the gold standard for responsible AI deployment in healthcare. As technology continues to advance, these brands serve as beacons, guiding the healthtech industry toward a future that respects patient privacy, complies with regulations, and harnesses the full potential of AI to revolutionize healthcare for the better.

Read more:
Advancing Patient Care: 5 Brands Harnessing AI and Machine ... - Microbioz India

The new application, TargetSelector, streamlines target-protein discovery and enables researchers in various industries to identify novel targets for innovative products

REHOVOT, Israel, July 25, 2023 /PRNewswire/ --Evogene Ltd. (Nasdaq: EVGN) (TASE: EVGN), a leading computational biology company targeting to revolutionize life-science product discovery and development across multiple market segments, is proud to announce the latest addition to its ChemPass AI tech-engine a breakthrough technology for target-protein discovery. The integration of TargetSelector, a new application that streamlines target-protein discovery for active molecule identification, assists researchers in finding suitable target proteins for new products while reducing development time, resources and most importantly, increasing the probability of success.

Proteins play a fundamental role in a wide array of biological processes and serve as the primary targets for developing innovative therapeutics, ag-chemical, ag-biological, and other life science solutions. The precise identification of these protein targets is pivotal in advancing research and discovery across various domains, including pharmaceuticals, agriculture, and environmental applications.

The challenge of finding a target-protein that is novel, safe, and druggable from the thousands of proteins in a relevant organism is enormous. Leveraging predictive machine learning algorithms and genomic data, users gain valuable insights into product requirements such as homology, druggability, essentiality, and biological pathways, efficiently narrowing down the list of potential target-protein, thus optimizing the discovery process.

"ChemPass AI tech-engine is a cutting-edge platform for the identification of small molecules. The addition of the TargetSelector application now enables a broader scope of finding the optimal target-protein for these molecules," said Dr. Nir Arbel, CPO at Evogene. "Our subsidiary AgPlenus, which focuses on developing ag chemicals, will be the first to benefit from this new improvement, applying it to identify novel mechanismsof action for pesticides. I believe that this significant advancement in Evogene's ChemPass AI tech-engine, positions us to forge strategic partnerships with industry leaders, unlocking innovation, expediting product development, and delivering groundbreaking solutions that tackle pressing global challenges."

About ChemPass AI:

ChemPass AI tech engine is a cutting-edge computational platform for discovering and optimizing small molecules for various life-science products, such as therapeutics and ag-chemicals. Developed at the intersection of docking techniques and machine learning, ChemPass AI brings together the power of artificial intelligence, predictive biology, and molecular interactions to accelerate target-protein and active molecule discovery processes like never before.

ChemPass AIhas been trained on vast repositories of molecular data encompassing diverse chemical structures and biological targets. This wealth of knowledge empowers the platform to recognize intricate patterns, subtle interactions, and complex relationships between small molecules and their target-proteins. As a result, ChemPass AI can rapidly evaluate an organism's protein set (proteome) as well as billions of potential candidates, ranking them according to their likelihood of success and shortening the time needed to identify promising target-proteins and leads (small molecules).

About Evogene:

Evogene Ltd. (Nasdaq: EVGN) (TASE: EVGN) is a computational biology company leveraging big data and artificial intelligence,aiming to revolutionize the development of life-science based products by utilizing cutting-edge technologies to increase the probability of success while reducing development time and cost.

Evogene established three unique tech-engines - MicroBoostAI,ChemPass AIandGeneRator AI. Each tech-engineis focused on the discovery and development of products based on one of the following core components: microbes (MicroBoost AI), small molecules (ChemPass AI), and genetic elements (GeneRator AI).

Evogene uses its tech-engines to develop products through strategic partnerships and collaborations, and its five subsidiaries including:

For more information, please visit: http://www.evogene.com.

Forward-Looking Statements: This press release contains "forward-looking statements" relating to future events. These statements may be identified by words such as "may", "could", "expects", "hopes" "intends", "anticipates", "plans", "believes", "scheduled", "estimates", "demonstrates" or words of similar meaning. For example, Evogene and its subsidiaries are using forward-looking statement in this press release when it discusses TargetSelector's ability to assist researchers in finding suitable target proteins for new products while reducing development time, resources and increasing the probability of success, TargetSelector's ability to enable a broader scope of finding the optimal protein target for hit small molecules, AgPlenus' success in identifying novel mechanism of action pesticides, and ChemPass AI's ability to accelerate drug discovery processes by reducing the time and resources required. Such statements are based on current expectations, estimates, projections and assumptions, describe opinions about future events, involve certain risks and uncertainties which are difficult to predict and are not guarantees of future performance. Therefore, actual future results, performance or achievements of Evogene and its subsidiaries may differ materially from what is expressed or implied by such forward-looking statements due to a variety of factors, many of which are beyond the control of Evogene and its subsidiaries, including, without limitation, those risk factors contained in Evogene's reports filed with the applicable securities authority. In addition, Evogene and its subsidiaries rely, and expect to continue to rely, on third parties to conduct certain activities, such as their field-trials and pre-clinical studies, and if these third parties do not successfully carry out their contractual duties, comply with regulatory requirements or meet expected deadlines, Evogene and its subsidiaries may experience significant delays in the conduct of their activities. Evogene and its subsidiaries disclaim any obligation or commitment to update these forward-looking statements to reflect future events or developments or changes in expectations, estimates, projections, and assumptions.

Logo - https://mma.prnewswire.com/media/1947468/Evogene_Logo.jpg

Contact: Rachel Pomerantz Gerber Head of Investor Relations at Evogene [emailprotected] +972-8-9311901

SOURCE Evogene

Read the rest here:
Evogene's ChemPass AI Tech-Engine is Introduced with New ... - PR Newswire