Mediaboss Marketing

Many call this the age of information said Rajive Ganguli, the Malcolm McKinnon Professor of Mining Engineering at the University of Utah. It is perhaps more accurate to call it the age of data since not everyone has the ability to truly gain from all the data they collect. Many are either lost in the data or misled by it. Yet, the promise of being informed by data remains.

Ganguli, who is also the College of Mines and Earth Sciences associate dean, is launching UteAnalytics, a free analytics software which makes artificial intelligence (AI) or machine learning (ML) accessible to all.

Founder of the ai.sys group at the U, Ganguli said that as long as a client knows their data, they can use UteAnalytics to understand better the problems they are trying to solve. The research groups mission is to seek insight from data, models systems and to develop computational tools for education and research.

At various points in time, Ganguli has developed ML tools that his students could use in class. Years ago, it occurred to him that more could benefit from ML if only his workflow and tools were more user-friendly. Graduate student Lewis Oduro brought his vision to tuition by leveraging the numerous public domain ML tools available to programmers and converting them into Windows-based software.

The tool is problem agnostic, Ganguli said. Hence it can have a broad group of users. I have used it for a variety of projects I am involved in, including mining, atmospheric sciences/air quality and COVID/hospital admissions.

PHOTO CREDIT: Rajive Ganguli

Lewis Oduro (right) and Rajive Ganguli (left).

He reports that tens of subject matter experts (SMEs) who are non-coders have already subscribed to receive the software in advance of its formal release. Many are professionals across a broad spectrum of fields from social science to business, along with scientists and engineers.

Designed to empower the domain expert, UteAnalytics allows a client to clean their data and conduct exploratory data analysis in various ways.The software also allows users to estimate the effect of each input on the output, as well as develop models in advance of predicting on a new dataset.

Daniel Mendoza, who holds faculty appointments in the Department of Atmospheric Sciences and elsewhere at the U, is an early adopter of the software. Through his work with air quality monitors on UTA trains and electric buses in Salt Lake Valley, he and his team have successfully collected more than 8 years of data for particulate matter and ozone levels, and recently, for nitrogen oxides.

When we look at neighborhood-specific data we can drill in and really see some social justice impacts, Mendoza reported last year. Today, he is using UteAnalytics to quickly and efficiently analyze the temperature data that well be collecting in real-time from our mobile and stationary sensors. UA gives researchers the power to look at data in a very streamlined way without endless hours of coding. The included tools facilitate a thorough interpretation of data and save time without compromising reliability.

The difference that dataassisted by UteAnalytics tools make in Mendozas work on air quality is most recently seen in the Urban Heat Watch campaign, involving citizen scientists who are helping collect data along the streets of Salt Lake Valley. As one of the top three urban heat islands in the nation, the Salt Lake City metropolitan area features a groundbreaking monitoring programnowhere else the world does an initiative exist at the density and scale than in Utahs capital city and environs.

UteAnalytics is just the latest deliverable for Ganguli, who has led approximately $13 million in projects as primary investigator. He is currently involved in several projects in five different countries U.S., Denmark/Greenland, Mongolia, Saudi Arabia and Mexico on topics ranging from ML to training.

Meanwhile, graduate student Lewis Oduro, who defended his thesis this past spring, has since taken a job near Phoenix, Arizona as a mining engineer at Freeport-McMoRan, a leading international mining company. A native of Ghana, Oduro said of his mentor, He gave me the chance to work under him and provided me with the kind of relationship only evident between a father and a son.

Under Gangulis tutelage and support, Oduro was the principal player in building UteAnalytics as desktop software used for data analytics and building predictive ML models.

I will forever be indebted to him and to the entire faculty at the University of Utahs Mining Engineering Department, the young scientist said on his LinkedIN page.

Visit link:
Making machine learning accessible to all @theU - @theU

July 26, 2023 -A new study described that despite the continued threat of infectious diseases on public health, the capabilities of artificial intelligence (AI) and machine learning (ML) can help handle this issue and provide a framework for future pandemics.

Regardless of research and biological advancements, infectious diseases remain an issue. To keep up with the conflict, common methods that are applied include therapies and diagnostics. Often, synthetic biology approaches provide a platform for innovation. Research indicated that synthetic biology is often divided into two development categories: quantitative biological hypotheses and data from experimentation, and the comprehension of the factors such as nucleic acids and peptides, which allow for the control of biology.

According to research, advancements in AI have considered these factors. Given the complexities of biology and infectious disease, there is a high level of potential. Thus, researchers reviewed how the relationship between AI and synthetic biology can battle infectious diseases.

The review described three uses of AI in infectious diseases: anti-infective drug discovery, infection biology, and diagnostics.

Despite the pre-existence of various anti-infective drugs, drug resistance often outmatches their effectiveness. AI and ML can play a large role in developing new drugs by searching small-molecule databases while using training models to define new drugs or apply existing drugs.

The complications of infection biology are extensive, largely due to the activity of bacterial, eukaryotic, and viral pathogens. These factors can affect host responses, and, therefore, the course of infection.

ML models, however, can analyze nucleic acid, protein, and other variables to determine the aspects of hostpathogen interactions and immune responses. Research also indicates they can define genes and interactions between proteins that link to host cell changes, immunogenicity prediction, and other activities.

Also, gene expression optimization and antigen prediction has assisted the development of vaccines and drugs through supervised models.

AI and ML have applications in diagnostics. As prior instances have shown, the speed of infectious disease detection plays a large role in how spreading takes place. However, through AI and ML, researchers can identify infections and foresee drug resistance. This is primarily because of its ability to program elements well and highlight essential information from biomolecular networks.

Regardless of the opportunities and challenges that these methods may pose, they are essential to the future of infectious disease treatment. As the development of AI continues, it is critical to consider a wide range of datasets to avoid bias.

Various research efforts have also showcased the capabilities of AI and how it may advance healthcare.

Research from April 2022, for example, involved the creation of an AI model that uses non-contrast abdominal CT images to analyze factors related to pancreatic health, determining type 2 diabetes risk.

Using hundreds of images and various measurements, researchers defined the factors that correlated with diabetes. Consistent and accurate results allowed researchers to determine this analysis was an effective approach to detecting diabetes.

This study is a step towards the wider use of automated methods to address clinical challenges, said study authors Ronald M. Summers, MD, PhD, and Hima Tallam, an MD and PhD student, in apress release.It may also inform future work investigating the reason for pancreatic changes that occur in patients with diabetes.

Research efforts such as these are integral examples of how AI continues to play a role in healthcare.

Read the original post:
AI and Machine Learning Hold Potential in Fighting Infectious Disease - HealthITAnalytics.com

Nunes, L. J. R., Causer, T. P. & Ciolkosz, D. Biomass for energy: A review on supply chain management models. Renew. Sustain. Energy Rev. 120, 109658 (2020).

Article Google Scholar

Wang, G. et al. A review of recent advances in biomass pyrolysis. Energy Fuels 34, 1555715578 (2020).

Article CAS Google Scholar

Osman, A. I. et al. Conversion of biomass to biofuels and life cycle assessment: A review. Environ. Chem. Lett. 19, 40754118 (2021).

Article CAS Google Scholar

Bakhtyari, A., Makarem, M. A. & Rahimpour, M. R. Bioenergy Systems for the Future 87148 (Woodhead Publishing, 2017).

Book Google Scholar

Testa, M. L. & Tummino, M. L. Lignocellulose biomass as a multifunctional tool for sustainable catalysis and chemicals: An overview. Catalysts 11, 125 (2021).

Article CAS Google Scholar

Lin, C.-Y. & Lu, C. Development perspectives of promising lignocellulose feedstocks for production of advanced generation biofuels: A review. Renew. Sustain. Energy Rev. 136, 110445 (2021).

Article CAS Google Scholar

Wang, C. et al. A review of conversion of lignocellulose biomass to liquid transport fuels by integrated refining strategies. Fuel Process. Technol. 208, 106485 (2020).

Article CAS Google Scholar

Yamaguchi, A., Sato, O., Mimura, N. & Shirai, M. Catalytic production of sugar alcohols from lignocellulosic biomass. Catal. Today 265, 199202. https://doi.org/10.1016/j.cattod.2015.08.026 (2016).

Article CAS Google Scholar

Erian, A. M. & Sauer, M. Utilizing yeasts for the conversion of renewable feedstocks to sugar alcohols: A review. Bioresour. Technol. 346, 126296. https://doi.org/10.1016/j.biortech.2021.126296 (2022).

Article CAS PubMed Google Scholar

da Costa Lopes, A. M., Joo, K. G., Morais, A. R. C., Bogel-ukasik, E. & Bogel-ukasik, R. Ionic liquids as a tool for lignocellulosic biomass fractionation. Sustain. Chem. Process. 1, 131 (2013).

Article Google Scholar

Abbasi, A. R. et al. Recent advances in producing sugar alcohols and functional sugars by engineering Yarrowia lipolytica. Front. Bioeng. Biotechnol. 9, 648382 (2021).

Article PubMed PubMed Central Google Scholar

Fickers, P., Cheng, H. & SzeKiLin, C. Sugar alcohols and organic acids synthesis in Yarrowia lipolytica: Where are we?. Microorganisms 8, 574 (2020).

Article CAS PubMed PubMed Central Google Scholar

Park, Y.-C., Oh, E. J., Jo, J.-H., Jin, Y.-S. & Seo, J.-H. Recent advances in biological production of sugar alcohols. Curr. Opin. Biotechnol. 37, 105113 (2016).

Article CAS PubMed Google Scholar

Grembecka, M. Sugar alcoholstheir role in the modern world of sweeteners: A review. Eur. Food Res. Technol. 241, 114 (2015).

Article CAS Google Scholar

Amarasekara, A. S. Ionic liquids in biomass processing. Isr. J. Chem. 59, 789802 (2019).

Article CAS Google Scholar

Tan, S. S. Y. & MacFarlane, D. R. Ionic liquids in biomass processing. Ionic Liquids 1, 311339 (2009).

Article Google Scholar

Rajamani, S., Santhosh, R., Raghunath, R. & Jadhav, S. A. Value-added chemicals from sugarcane bagasse using ionic liquids. Chem. Pap. 75, 56055622 (2021).

Article CAS Google Scholar

Parvaneh, K., Rasoolzadeh, A. & Shariati, A. Modeling the phase behavior of refrigerants with ionic liquids using the QC-PC-SAFT equation of state. J. Mol. Liq. 274, 497504. https://doi.org/10.1016/j.molliq.2018.10.116 (2019).

Article CAS Google Scholar

Singh, S. K. & Savoy, A. W. Ionic liquids synthesis and applications: An overview. J. Mol. Liq. 297, 112038 (2020).

Article CAS Google Scholar

Sedghamiz, M. A., Rasoolzadeh, A. & Rahimpour, M. R. The ability of artificial neural network in prediction of the acid gases solubility in different ionic liquids. J. CO2 Util. 9, 3947. https://doi.org/10.1016/j.jcou.2014.12.003 (2015).

Article CAS Google Scholar

Rasoolzadeh, A. et al. A thermodynamic framework for determination of gas hydrate stability conditions and water activity in ionic liquid aqueous solution. J. Mol. Liq. 347, 118358 (2022).

Article CAS Google Scholar

Setiawan, R., Daneshfar, R., Rezvanjou, O., Ashoori, S. & Naseri, M. Surface tension of binary mixtures containing environmentally friendly ionic liquids: Insights from artificial intelligence. Environ. Dev. Sustain. 23, 1760617627 (2021).

Article Google Scholar

Rasoolzadeh, A., Javanmardi, J., Eslamimanesh, A. & Mohammadi, A. H. Experimental study and modeling of methane hydrate formation induction time in the presence of ionic liquids. J. Mol. Liq. 221, 149155. https://doi.org/10.1016/j.molliq.2016.05.016 (2016).

Article CAS Google Scholar

Welton, T. Ionic liquids: A brief history. Biophys. Rev. 10, 691706 (2018).

Article CAS PubMed PubMed Central Google Scholar

Brandt, A., Grsvik, J., Hallett, J. P. & Welton, T. Deconstruction of lignocellulosic biomass with ionic liquids. Green Chem. 15, 550583 (2013).

Article CAS Google Scholar

Reddy, P. A critical review of ionic liquids for the pretreatment of lignocellulosic biomass. S. Afr. J. Sci. 111, 19 (2015).

Article Google Scholar

Tu, W.-C. & Hallett, J. P. Recent advances in the pretreatment of lignocellulosic biomass. Curr. Opin. Green Sustain. Chem. 20, 1117 (2019).

Article Google Scholar

Usmani, Z. et al. Ionic liquid based pretreatment of lignocellulosic biomass for enhanced bioconversion. Biores. Technol. 304, 123003 (2020).

Article CAS Google Scholar

Roy, S. & Chundawat, S. P. S. Ionic liquid-based pretreatment of lignocellulosic biomass for bioconversion: A critical review. BioEnergy Res. 1, 116 (2022).

Google Scholar

Xia, Z. et al. Processing and valorization of cellulose, lignin and lignocellulose using ionic liquids. J. Bioresour. Bioprod. 5, 7995 (2020).

Article CAS Google Scholar

Carneiro, A. P., Rodrguez, O. & Macedo, E. A. Solubility of monosaccharides in ionic liquids: Experimental data and modeling. Fluid Phase Equilib. 314, 2228 (2012).

Article CAS Google Scholar

Carneiro, A. P., Rodrguez, O. & Macedo, E. A. Solubility of xylitol and sorbitol in ionic liquids: Experimental data and modeling. J. Chem. Thermodyn. 55, 184192 (2012).

Article CAS Google Scholar

Carneiro, A. P., Held, C., Rodriguez, O., Sadowski, G. & Macedo, E. A. Solubility of sugars and sugar alcohols in ionic liquids: Measurement and PC-SAFT modeling. J. Phys. Chem. B 117, 99809995 (2013).

Article CAS PubMed Google Scholar

Carneiro, A. P., Rodrguez, O. & Macedo, E. N. A. Fructose and glucose dissolution in ionic liquids: Solubility and thermodynamic modeling. Ind. Eng. Chem. Res. 52, 34243435 (2013).

Article CAS Google Scholar

Mohan, M., Goud, V. V. & Banerjee, T. Solubility of glucose, xylose, fructose and galactose in ionic liquids: Experimental and theoretical studies using a continuum solvation model. Fluid Phase Equilib. 395, 3343 (2015).

Article CAS Google Scholar

Mohan, M., Banerjee, T. & Goud, V. V. Solid liquid equilibrium of cellobiose, sucrose, and maltose monohydrate in ionic liquids: Experimental and quantum chemical insights. J. Chem. Eng. Data 61, 29232932 (2016).

Article CAS Google Scholar

Paduszynski, K., Okuniewski, M. & Domanska, U. Sweet-in-green systems based on sugars and ionic liquids: New solubility data and thermodynamic analysis. Ind. Eng. Chem. Res. 52, 1848218491 (2013).

Article CAS Google Scholar

Paduszyski, K., Okuniewski, M. & Domaska, U. Solidliquid phase equilibria in binary mixtures of functionalized ionic liquids with sugar alcohols: New experimental data and modelling. Fluid Phase Equilib. 403, 167175 (2015).

Article Google Scholar

Paduszyski, K., Okuniewski, M. & Domaska, U. An effect of cation functionalization on thermophysical properties of ionic liquids and solubility of glucose in themmeasurements and PC-SAFT calculations. J. Chem. Thermodyn. 92, 8190 (2016).

Article Google Scholar

Teles, A. R. R. et al. Solubility and solvation of monosaccharides in ionic liquids. Phys. Chem. Chem. Phys. 18, 1972219730 (2016).

Article CAS PubMed PubMed Central Google Scholar

Yang, X., Wang, J. & Fang, Y. Solubility and solution thermodynamics of glucose and fructose in three asymmetrical dicationic ionic liquids from 323.15 K to 353.15 K. J. Chem. Thermodyn. 139, 105879 (2019).

Article CAS Google Scholar

Abbasi, M., Pazuki, G., Raisi, A. & Baghbanbashi, M. Thermophysical and rheological properties of sorbitol+([mmim](MeO)2PO2) ionic liquid solutions: Solubility, density and viscosity. Food Chem. 320, 126566 (2020).

Article CAS PubMed Google Scholar

Zarei, S., Abdolrahimi, S. & Pazuki, G. Thermophysical characterization of sorbitol and 1-ethyl-3-methylimidazolium acetate mixtures. Fluid Phase Equilib. 497, 140150 (2019).

Article Google Scholar

Ruiz-Aceituno, L., Carrero-Carralero, C., Ramos, L. & Sanz, M. L. Selective fractionation of sugar alcohols using ionic liquids. Sep. Purif. Technol. 209, 800805 (2019).

Article CAS Google Scholar

Jeon, P. R. & Lee, C.-H. Artificial neural network modelling for solubility of carbon dioxide in various aqueous solutions from pure water to brine. J. CO2 Util. 47, 101500 (2021).

Article CAS Google Scholar

Amar, M. N. Modeling solubility of sulfur in pure hydrogen sulfide and sour gas mixtures using rigorous machine learning methods. Int. J. Hydrogen Energy 45, 3327433287 (2020).

Article Google Scholar

Hemmati-Sarapardeh, A., Amar, M. N., Soltanian, M. R., Dai, Z. & Zhang, X. Modeling CO2 solubility in water at high pressure and temperature conditions. Energy Fuels 34, 47614776 (2020).

Article CAS Google Scholar

Vanani, M. B., Daneshfar, R. & Khodapanah, E. A novel MLP approach for estimating asphaltene content of crude oil. Pet. Sci. Technol. 37, 22382245 (2019).

Article CAS Google Scholar

Daneshfar, R., Keivanimehr, F., Mohammadi-Khanaposhtani, M. & Baghban, A. A neural computing strategy to estimate dew-point pressure of gas condensate reservoirs. Pet. Sci. Technol. 38, 706712 (2020).

Article CAS Google Scholar

Bakhtyari, A., Mofarahi, M. & Iulianelli, A. Combined mathematical and artificial intelligence modeling of catalytic bio-methanol conversion to dimethyl ether. Energy Convers. Manag. 276, 116562. https://doi.org/10.1016/j.enconman.2022.116562 (2023).

Article CAS Google Scholar

Read more here:
Application of machine learning techniques to the modeling of ... - Nature.com

As we continue to rely more on AI-powered technologies, its mandatory to address the issue of bias in machine learning. Bias can be present in many different forms, ranging from subtle nuances to more obvious patterns. Unfortunately, this bias can easily seep into machine learning algorithms, creating significant challenges when it comes to developing fair, transparent, and impartial decision-making procedures.

The challenge of bias is particularly acute in industries that are already prone to bias and discrimination, such as those related to hiring, finance, and criminal justice. For example, if a machine learning algorithm is trained on data that is biased against a certain group of people, it will inevitably produce biased results. This can have serious consequences, such as perpetuating discrimination and injustice.

To address these issues, its important to develop machine learning algorithms that are designed to be as impartial as possible. This requires careful attention to the data used to train the algorithms, as well as the algorithms themselves.

Bias in machine learning refers to the systematic and unjust favoritism or prejudice shown by algorithms towards certain groups or outcomes. The foundation of bias lies in societys visions and values, which can unintentionally taint the data used to train AI models.

This unintentional influence from human biases can result in the perpetuation of discriminatory practices, hindering the true potential of AI in advancing society.

There are different types of machine learning bias to be aware of including:

Sample bias: Occurs when the training dataset is not representative of the real-world population, leading the model to perform poorly on certain groups.

Prejudice bias: Arises when data contains prejudiced attitudes or beliefs that favor one group over another, perpetuating inequalities.

Measurement bias: Results from incorrect or skewed data measurements, leading to inaccurate conclusions.

Aggregation bias: Emerges when different datasets are combined without accounting for variations in data sources, leading to distortions in the models understanding.

The first step to completely solving any problem is to understand the absolute underlying cause. Bias is a concept that rightly plagues many minorities today, and many researchers are trying to understand how it is rooted in human psychology.

Research in social psychology has shown that individuals may hold implicit biases, which are unconscious attitudes and stereotypes that influence their judgments and behaviors. Studies have demonstrated that people may exhibit implicit racial biases, where they associate negative or positive traits with specific racial or ethnic groups. Implicit bias can influence decision-making, interactions, and behavior, leading to unintentional discrimination and perpetuation of stereotypes.

It is quite possible that this fallacy in human psychology is at the root of bias in machine learning. If an AI developer intentionally or unintentionally excludes certain groups from the master dataset used to train ML algorithms, the result will be that the AI will struggle to interpret them. Machine learning is growing exponentially and while this is a correctable error in the early stages, this mistake will gradually be accepted as a fact by AI, ultimately leading to bias in machine learning.

The presence of bias in machine learning can have far-reaching consequences, affecting both the very foundation of AI systems and society itself. At the core of machine learning lies the ability to make accurate predictions based on data analysis. However, when bias seeps into the training data, it compromises the accuracy and reliability of machine learning models. Biased models may produce skewed and misleading results, hindering their capability to provide trustworthy predictions.

The ethics and risks of pursuing artificial intelligence

The consequences of bias in machine learning go beyond just inaccurate predictions. Biased models can produce results that misrepresent future events, leading people to make decisions based on incorrect information and potentially causing negative consequences.

When bias is unevenly distributed within machine learning models, certain subgroups may face unfair treatment. This can result in these populations being denied opportunities, services, or resources, perpetuating existing inequalities.

Transparency is key in building trust between users and AI systems. However, when bias influences decision-making, the trustworthiness of AI is called into question. The obscurity introduced by bias can make users question the fairness and intentions of AI technologies.

One of the most concerning impacts of bias in machine learning is its potential to produce unjust and discriminatory results. Certain populations may be subjected to biased decisions, leading to negative impacts on their lives and reinforcing societal prejudices.

Bias in training data can hinder the efficiency of the machine learning process, making it more time-consuming and complex to train and validate models. This can delay the development of AI systems and their practical applications.

Interestingly, bias can lead to overcomplicated models without necessarily improving their predictive power. This paradox arises when machine learning algorithms try to reconcile biased data, which can ultimately inflate model complexity without any significant improvements in performance.

Evaluating the performance of biased machine learning models becomes increasingly difficult. Distinguishing between accuracy and prejudice in the outputs can be a daunting task, making it hard to determine the true effectiveness of these AI systems.

As bias infiltrates machine learning algorithms, their overall performance can be negatively impacted. The effectiveness of these algorithms in handling diverse datasets and producing unbiased outcomes may suffer, limiting their applicability.

Bias in machine learning can significantly impact the decisions made based on AI-generated insights. Instead of relying on objective data, biased AI systems may make judgments based on prejudiced beliefs, resulting in decisions that reinforce existing biases and perpetuate discriminatory practices.

The discovery of bias in machine learning models raises critical questions about the possibility of recovery. Is it feasible to salvage a biased model and transform it into an equitable and reliable tool?

To address this crucial issue, various strategies and techniques have been explored to mitigate bias and restore the integrity of machine learning algorithms.

A fundamental step in recovering a biased model is to identify the root cause of bias. Whether the bias originates from biased data collection or the algorithm design, pinpointing the sources of bias is crucial for devising effective mitigation strategies.

By understanding the underlying reasons for bias, researchers and developers can adopt targeted approaches to rectify the issue at its core.

To effectively tackle bias, it is essential to quantify its extent and severity within a model. Developing metrics that can objectively measure bias helps researchers grasp the scale of the problem and track progress as they implement corrective measures.

Accurate measurement is key to understanding the impact of bias on the models performance and identifying areas that require immediate attention.

Bias in machine learning can have varying effects on different groups, necessitating a comprehensive assessment of its real-world implications. Analyzing how bias affects distinct populations is vital in creating AI systems that uphold fairness and equity.

This assessment provides crucial insights into whether certain subgroups are disproportionately disadvantaged or if the models performance is equally reliable across various demographics.

High-quality data forms the bedrock of accurate and unbiased machine learning models. Ensuring data is diverse, representative, and free from biases is fundamental to minimizing the impact of prejudice on the models predictions.

Rigorous data quality checks and data cleaning processes play a vital role in enhancing the reliability of the model but if the degree of bias in machine learning is too high, starting with a new root dataset must be the way to go.

To cultivate fairness and inclusivity within machine learning models, expanding the training dataset to include a wide range of examples is paramount. Training on diverse data enables the model to learn from a variety of scenarios, contributing to a more comprehensive understanding and improved fairness across different groups.

Machine learning offers a plethora of algorithms, each with its strengths and weaknesses. When faced with bias, exploring alternative algorithms can be an effective strategy to find models that perform better with reduced bias.

By experimenting with various approaches, developers can identify the algorithms that align most closely with the goal of creating unbiased AI systems.

We have repeatedly mentioned how big a problem bias in machine learning is. What would you say if we told you that you can make AI control another AI?

To ensure your ML model is unbiased, there are two approaches: proactive and reactive. Reactive bias detection happens naturally when you notice that a specific set of inputs is performing poorly. This could indicate that your data is biased.

Alternatively, you can proactively build bias detection and analysis into your model development process using a tool. This allows you to search for signs of bias and gain a better understanding of them.

Several tools can help with this, such as:

These tools provide features like visualizing your dataset, analyzing model performance, assessing algorithmic fairness, and removing redundancy and bias introduced by the data collection process. By using these tools, you can minimize the risk of bias in machine learning.

Addressing bias in machine learning models is a significant challenge, but it is not impossible to overcome. A multifaceted approach can help, which involves identifying the root cause of bias, measuring its extent, exploring different algorithms, and improving data quality.

Featured image credit: Image by Rochak Shukla on Freepik.

The rest is here:
Bias In Machine Learning: Concepts, Causes, And How To Fix It - Dataconomy

For fusion reactions to become practical, parameters such as plasma density and shape must be monitored in real time and impending disruptions responded to instantly.

Nuclear fusion is widely regarded as one of the most promising sources of clean and sustainable energy of the future. In a fusion reaction, two light atomic nuclei combine to form another, whose mass is less than the total mass of the original pair, and according to Einsteins famous formula E = mc2, this mass difference gets transformed into energy that can be utilized.

The problem with this source of energy is that for positively charged nuclei to fuse, they have to overcome the electrical repulsion between them. For this, the velocity of colliding nuclei must be very high, which is achieved by heating the substance in which the reaction takes place to an enormous temperature, at least tens of millions of degrees Kelvin.

Of course, no material can withstand contact with matter at such temperature, so in all prototype fusion reactors, a magnetic field is used to contain the hot plasma, limiting its movement and preventing it from coming into contact with the walls of the reactor. However, in a hot plasma instabilities constantly arise, which can force it to leave the region of the magnetic container and collide with the walls of the reactor, damaging them. Such contacts also guarantee the cooling of the plasma and the termination of the fusion reaction.

In order to prevent these violent plasma disruptions, it is necessary to monitor plasma parameters such as its density and shape in real time and respond instantly to impending disruptions. To achieve this, a team of American and British scientists led by William Tang of Princeton University, has developed a machine learning-based software that can predict the disruptions and analyze the physical conditions which result in them.

In their work, the physicists used a large amount of data from the British JET facility and the American DIII-D machine, which are tokamaks, fusion reactors in which the plasma has the shape of a donut. To be more precise, the researchers used some of the data they had on the state of the plasma in the reactors during their operation to train the program. This training allows the software to to predict when a disruption would occur. The accuracy of these predictions could then be tested using real world data not used in the training set.

The team not only trained their software to correctly predict the disruptions, but also to analyze the physical processes occurring in the plasma that led to these events. This property of the algorithm is essential, since in the operation of a real fusion reactor it is important not only to understand that a disruption is approaching, but also to be able to prevent it by changing the parameters of the plasma in the reactor within milliseconds.

With a larger dataset and more powerful supercomputers, such as those currently being built at Oak Ridge National Laboratory, Lawrence Berkeley National Laboratory, and Argonne National Laboratory, the researchers hope they can make their algorithm even more sensitive to the processes occurring in the plasma, and hence more accurately predict and respond to impending disruptions.

They expect that the software they have developed will be implemented on the current prototype tokamaks, whose data they used in their study, as well as on future more powerful machines such as ITER, currently under construction in France. If this happens, then this may lead to earlier stable energy production from fusion reactions.

References: William Tang et al, Implementation of AI/DEEP learning disruption predictor into a plasma control system, Contributions to Plasma Physics (2023), DOI: 10.1002/ctpp.202200095.

Julian Kates-Harbeck, et al, Predicting disruptive instabilities in controlled fusion plasmas through deep learning, Nature (2019), DOI: 10.1038/s41586-019-1116-4.

Feature image credit: TheDigitalArtist on Pixabay

Read more:
Using machine learning to tame plasma in fusion reactors - Advanced Science News