Mediaboss Marketing

With quantum machine learning, the internet of things can become even more powerful, enabling people to create more efficient and safer systems.

FREMONT, CA: The Internet of Things (IoT) is altering how people interact with their surrounding environment. From intelligent homes to autonomous vehicles, the possibilities are limitless. Researchers are investigating the possibility of merging IoT with quantum machine learning (QML) to create even more powerful and efficient systems.

QML is an artificial intelligence (AI) that processes data using quantum computing. It offers the ability to provide quicker and more precise decision-making than conventional AI. Researchers hope to create a potent new data analysis and prediction tool by merging it with the IoT.

QML and IoT could be combined to create smarter, more efficient systems for various applications. For instance, it might optimize city traffic flow by forecasting traffic patterns and modifying traffic light timing accordingly. It could also be utilized to optimize building energy consumption and monitor and predict disease spread

IoT facilitates the huge potential of QML enabled by IoT. It could transform how people interact with the environment around them and create new opportunities for data analysis and forecasting. As researchers continue to investigate the possibilities, it is evident that this technology can alter the way of life.

Using the IoT to Advance QML

The IoT is altering how people interact with their surrounding environment. IoT technology's potential applications appear limitless, from intelligent homes to self-driving vehicles. Now, scientists are investigating how IoT can transform QML.

QML is a fast-developing research topic that blends quantum computing capabilities with machine learning methods. QML can enable robots to learn more effectively and precisely than ever before by harnessing the potential of quantum computing.

The IoT is ideally suited to supporting QML applications. IoT devices can collect and communicate vast quantities of data, which can be utilized to train and optimize machine learning algorithms. In addition, IoT devices can be used to monitor and control the environment in which QML algorithms are deployed, ensuring that they operate under optimal conditions.

Also, researchers are investigating how IoT devices might be leveraged to enhance the security of QML applications. IoT devices can identify and prevent harmful attacks on QML systems by harnessing the power of distributed networks. IoT devices can also be used to monitor the performance of QML algorithms, enabling the immediate identification and resolution of any problems.

The potential uses of the IoT for QML are vast, and researchers are just beginning to investigate them. By leveraging the power of the IoT, researchers are paving the way for a new era of QML that might transform how people interact with the world.

Visit link:
Exploring the Possibilities of IoT-Enabled Quantum Machine Learning - CIOReview

A study by Swansea University has revealed how machine learning can help with the early detection of Ankylosing Spondylitis (AS) inflammatory arthritis and revolutionise how people are detected and diagnosed by their GPs.

Published in the open-access journal PLOS ONE, the study, funded by UCB Pharma and Health and Care Research Wales, has been carried out by data analysts and researchers from the National Centre for Population Health & Wellbeing Research (NCPHWR).

The team used machine learning methods to develop a profile of the characteristics of people likely to be diagnosed with AS, the second most common cause of inflammatory arthritis.

Machine learning, a type of artificial intelligence, is a method of data analysis that automates model building to improve performance and accuracy. Its algorithms build a model based on sample data to make predictions or decisions without being explicitly programmed to do so.

Using the Secure Anonymised Information Linkage (SAIL) Databank based atSwansea University Medical School, a national data repository allowing anonymised person-based data linkage across datasets, patients with AS were identified and matched with those with no record of a condition diagnosis.

The data was analysed separately for men and women, with a model developed using feature/variable selection and principal component analysis to build decision trees.

The findings revealed:

Dr Jonathan Kennedy, Data Lab Manager at NCPHWR and study lead:"Our study indicates the enormous potential machine learning has to help identify people with AS and better understand their diagnostic journeys through the health system.

"Early detection and diagnosis are crucial to secure the best outcomes for patients. Machine learning can help with this. In addition, it can empower GPs helping them detect and refer patients more effectively and efficiently.

"However, machine learning is in the early stages of implementation. To develop this, we need more detailed data to improve prediction and clinical utility."

Professor Ernest Choy, Researcher at NCPHWR and Head of Rheumatology and Translational Research at Cardiff University, added:"On average, it takes eight years for patients with AS from having symptoms to receiving a diagnosis and getting treatment. Machine learning may provide a useful tool to reduce this delay."

Professor Kieran Walshe, Director of Health and Care Research Wales, added: Its fantastic to see the cutting-edge role that machine learning can play in the early identification of patients with health conditions such as AS and the work being undertaken at the National Centre for Population Health and Wellbeing Research.

Though it is in its early stages, machine learning clearly has the potential to transform the way that researchers and clinicians approach the diagnostic journey, bringing about benefits to patients and their future health outcomes.

Read the full publication in the PLOS ONE journal.

View original post here:
New study shows the potential of machine learning in the early ... - Swansea University

*The datasets used and/or analyzed during the current study are available from the corresponding author.

We used a casecontrol study for our research. All patients were recruited from Rabats Cheikh Zaid University Center Hospital. COVID-19 hospitalizations occurred between March 6, 2020, and May 20, 2020, and were screened using clinical features (fever, cough, dyspnea, fatigue, headache, chest pain, and pharyngeal discomfort) and epidemiological histology. Any patient admitted to Cheikh Zaid Hospital with a positive PCR-RT for SARS-CoV-2 was considered a COVID-19 case. According to the severity, the cases were divided into two categories: Cases with COVID symptoms and a positive RT-PCR test requiring oxygen therapy are considered severe. Case not requiring oxygen therapy: any case with or without COVID symptoms, normal lung CT with positive RT-PCR. The Controls were selected from Cheikh Zaid Hospital employees (two to three per week) who exhibited no clinical signs of COVID-19 and whose PCR-RT test was negative for the virus. People with chronic illnesses (high blood pressure, diabetes, cancer, and cardiovascular disease) and those who had used platelet-disrupting medications within the previous two weeks (Aspirin, Prasugrel, Clopidogrel, Ticagrelor, Cangrelor, Cilostazol, Dipyridamole, Abciximab, Eptifibatide, Tirofiban, Non-steroidal anti-inflammatory drugs) are excluded from our study (Fig.2).

Consequently, a total of 87 participants were selected for this study and divided as follows: 57 Patients infected with SARS-CoV-2: Thirty without severe COVID-19 symptoms, twenty-seven with severe symptoms requiring hospitalization, and thirty healthy controls. Table1 displays patients basic demographic and clinical information.

The cytokines investigated in our study are displayed in Table2, it consists of two panels, the first one contains 48 cytokines, while the second panel contains only 21 cytokines.

A data imputation procedure was considered for filling in missing values in entries. In fact, 29 individuals in our dataset had a missingness rate of more than 50 percent for their characteristics (cytokines), therefore our analysis will be significantly impacted by missing values. The most prevalent method for dealing with incomplete information is data imputation prior to classification, which entails estimating and filling in the missing values using known data.

There are a variety of imputation approaches, such as mean, k-nearest neighbors, regression, Bayesian estimation, etc. In this article, we apply the iterative imputation strategy Multiple imputation using chained equations Forest (Mice-Forest) to handle the issue of missing data. The reason for this decision is to employ an imputation approach that can handle any sort of input data and makes as few assumptions as possible about the datas structure55.the chained equation process is broken down into four core steps which are repeated until optimal results are achieved56. The first step involves replacing every missing data with the mean of the observed values for the variable. In the second phase, mean imputations are reset to missing. In the third step, the observed values of a variable (such as x) are regressed on the other variables, with x functioning as the dependent variable and the others as the independent variables. As the variables in this investigation are continuous, predictive mean matching (PPM) was applied.

The fourth stage involves replacing the missing data with the regression models predictions. This imputed value would subsequently be included alongside observed values for other variables in the independent variables. An Iteration is the recurrence of steps 2 through 4 for each variable with missing values. After one iteration, all missing values are replaced by regression predictions based on observed data. In the present study, we examined the results of 10 iterations.

The convergence of the regression coefficients is ideally the product of numerous iterations. After each iteration, the imputed values are replaced, and the number of iterations may vary. In the present study, we investigated the outcomes of 10 iterations. This is a single "imputation." Multiple imputations are performed by holding the observed values of all variables constant and just modifying the missing values to their appropriate imputation predictions. Depending on the number of imputations, this leads to the development of multiply imputed datasets (30, in this study). The number of imputations depends on the values that are missing. The selection of 30 imputations was based on the White et al.57 publication. The fraction of missing data was around 30%. We utilized the version 5.4.0 of the miceforest Python library to impute missing data. The values of the experiments hyper-parameters for the Mice-Forest technique are listed in Table3, and Fig.4 illustrates the distribution of each imputation comparing to original data (in red).

The distribution of each imputation compared to the original data (in red).

Machine learning frameworks have demonstrated their ability to deal with complex data structures, producing impressive results in a variety of fields, including health care. However, a large amount of data is required to train these models58. This is particularly challenging in this study because available datasets are limited (87 records and 48 attributes) due to acquisition accessibility and costs, such limited data cannot be used to analyze and develop models.

To solve this problem, Synthetic Data Generation (SDG) is one of the most promising approaches (SDG) and it opens up many opportunities for collaborative research, such as building prediction models and identifying patterns.

Synthetic Data is artificial data generated by a model trained or built to imitate the distributions (i.e., shape and variance) and structure (i.e., correlations among the variables) of actual data59,60. It has been studied for several modalities within healthcare, including biological signals61, medical pictures62, and electronic health records (EHR)63.

In this paper, a VAE network-based approach is suggested to generate 500 samples of synthetic cytokine data from real data. VAEs process consists of providing labeled sample data (X) to the Encoder, which captures the distribution of the deep feature (z), and the Decoder, which generates data from the deep feature (z) (Fig.1).

The VAE architecture preserved each samples probability and matched the column means to the actual data. Figure5 depicts this by plotting the mean of the real data column on the X-axis and the mean of the synthetic data column on the Y-axis.

Each point represents a column mean in the real and synthetic data. A perfect match would be indicated by all the points lying on the line y=x.

The cumulative feature sum is an extra technique for comparing synthetic and real data. The feature sum can be considered as the sum of patient diagnosis values. As shown in Fig.6, a comparison of the global distribution of feature sums reveals a significant similarity between the data distributions of synthetic and real data.

Plots of each feature in our actual dataset demonstrate the similarity between the synthesized and actual datasets.

Five distinct models are trained on synthetic data (Random Forest, XGBoost, Bagging Classifier, Decision Tree, and Gradient boosting Classifier). Real data is used for testing, and three metrics were applied to quantify the performance of fitting: precision, recall, F1 score, and confusion matrix.

As shown in Figs.7, 8, 9, 10 and 11 the performance of the Gradient Boosting Classifier proved to be superior to that of other models, with higher Precision, Recall, and F1 score for each class, and a single misclassification. Consequently, we expect that SHAP and LIMEs interpretation of the Gradient Boosting model for the testing set will reflect accurate and exhaustive information for the cytokines data set.

Matrix confusion and Report Classification of Random Forest.

Matrix confusion and Report Classification of Gradient Boosting.

Matrix confusion and Report Classification of XGB Classifier.

Matrix confusion and Report Classification of Bagging Classifier.

Matrix confusion and Report Classification of Decision Tree.

Explaining a prediction refers to the presentation of written or visual artifacts that enable qualitative knowledge of the relationship between the instances components and the models prediction. We suggest that if the explanations are accurate and understandable, explaining predictions is an essential component of convincing humans to trust and use machine learning effectively43. Figure12 depicts the process of explaining individual predictions using LIME and SHAP as approaches that resemble the classifiers black box to explain individual predictions. When explanations are provided, a doctor is clearly in a much better position to decide using a model. Gradient Boosting predicts whether a patient has an acute case of COVID-19 in our study, whereas LIME and SHAP highlight the cytokines that contributed to this prediction.

The Flow chart demonstrates how Machine learning can be used to make medical decisions. We entered cytokine data from severe, non-severe, and healthy patients, trained predictive models on cytokine data, and then used LIME and SHAP to explain the most important cytokine for each class of patients (Fig.12).

The SHAP explanation utilized in this study is the Kernel Explainer, a model-agnostic approach that produces a weighted linear regression depending on the data, predictions, and model64. It examines the contribution of a feature by evaluating the model output if the feature is removed from the input for various (theoretically all) combinations of features. The Kernel Explainer makes use of a backdrop dataset to demonstrate how missing inputs are defined, i.e., how a missing feature is approximated during the toggling process.

SHAP computes the impact of each characteristic on the learned systems predictions. Using gradient descent, SHAP values are created for a single prediction (local explanations) and multiple samples (resulting in global explanations).

Figure13 illustrates the top 20 SHAP value features for each class in the cytokine data prediction model (Healthy, Severe, and Non-Severe classes). The distribution of SHAP values for each feature is illustrated using a violin diagram. Here, the displayed characteristics are ordered by their highest SHAP value. The horizontal axis represents the SHAP value. The bigger the positive SHAP value, the greater the positive effect of the feature, and vice versa. The color represents the magnitude of a characteristic value. The color shifts from red to blue as the features value increases and decreases. For example, Mip-1b in Figure8, the positive SHAP value increases as the value of the feature increases. This may be interpreted as the probability of a patient developing COVID-19, severity increasing as MIP-1b levels rise.

Examples of SHAP values computed for individuals predictions (local explanations) for Healthy, Non-Sever, and Sever patients.

In the situation of a healthy patient, TNF, IL-22, and IL-27 are the most influential cytokines, as shown in Fig.14s first SHAP diagram (from left). The second diagram is for a patient with severity, and we can observe that the VEGF-A cytokines value is given greater weight. This can be viewed as an indication that the patient got a serious COVID-19 infection due to the increase in this cytokine.

SHAP diagrams of characteristics with varying conditions: Healthy, Severe, and Non-Severe, respectively.

The last SHAP diagram depicts an instance of a non-Severe patient, and we can see that the higher the feature value, the more positive the direction of IL-27. On the other hand, MDC, PDGF-AB/BB, and VEGF-A cytokines have a deleterious effect. The levels of MDC and PDGF-AB/BB cytokines suggest that the patient may be recovering, however, the presence of VEGF-A suggests that the patient may develop a severe case of COVID-19, despite being underweight.

LIME is a graphical approach that helps explain specific predictions. It can be applied to any supervised regression or classification model, as its name suggests. Behind the operation of LIME is the premise that every complex model is linear on a local scale and that it is possible to fit a simple model to a single observation that mimics the behavior of the global model at that locality. LIME operates in our context by sampling the data surrounding a prediction and training a simple interpretable model to approximate the black box of the Gradient Boosting model. The interpretable model is used to explain the predictions of the black-box model in a local region surrounding the prediction by generating explanations regarding the contributions of the features to these predictions. As shown in Fig.15, a bar chart depicts the distribution of LIME values for each feature, indicating the relative importance of each cytokine for predicting Severity in each instance. The order of shown features corresponds to their LIME value.

In the illustrations explaining various LIME predictions presented in Fig.16. We note that the model has a high degree of confidence that the condition of these patients is Severe, Non-Severe, or Healthy. In the graph where the predicted value is 2, indicating that the expected scenario for this patient is Severe (which is right), we can see for this patient that Mip-1b level greater than 41 and VEGF-A level greater than 62 have the greatest influence on severity, increasing it. However, MCP-3 and IL-15 cytokines have a negligible effect in the other direction.

Explaining individual predictions of Gradient descent classifier by LIME.

Alternatively, there are numerous cytokines with significant levels that influence non-Severity. For example, IL-27 and IL-9, as shown in the middle graph in Fig.14. and that IL-12p40 below a certain value may have the opposite effect on model decision-making. RANTES levels less than 519, on the other hand, indicate that the patient is healthy, as shown in Fig.16.

By comparing the individuals explanation of SHAP values to the individuals explanation of LIME values for the same patients, we may be able to determine how these two models differ in explaining the Severity results of the Gradient descent model. As a result, we can validate and gain insight into the impact of the most significant factors. To do so, we begin by calculating the frequency of the top ten features among all patients for each Explainer. We only consider features that appear in the top three positions, as we believe this signifies the features high value, and we only consider the highest-scoring features that appear at least ten times across all SHAP or LIME explanations (Tables 4, 5, and 6).

Table4 demonstrates that MIP-1b, VEGF-A, and IL-17A have Unanimous Importance according to the SHAP Value and LIME. In addition, we can remark that M-CSF is necessary for LIME but is ranks poor.

In the instance of non-Severity, Table5 reveals that IL-27 and IL-9 are essential in both explanatory models for understanding non-Severity in patients. We can see that IL-12p40 and MCP-3 are also essential for LIME and are highly ranked; hence, we add these two characteristics to the list of vital features for the non-Severity instance. RANTES, TNF, IL-9, IL-27, and MIP-1b are the most significant elements in the Healthy scenario, according to Table6.

The elements that explain the severity of the COVID-19 sickness are summarized in Table7.

See the rest here:
Explanatory predictive model for COVID-19 severity risk employing ... - Nature.com

Few-shot learning is a subfield of machine learning and deep learning that aims to teach AI models how to learn from only a small number of labeled training data. The goal of few-shot learning is to enable models to generalize new, unseen data samples based on a small number of samples we give them during the training process.

In general, few-shot learning involves training a model on a set of tasks, each of which consists of a small number of labeled samples. We train the model to learn how to recognize patterns in the data and use this knowledge.

One challenge of traditional machine learning is the fact that training models require large amounts of training data with labeled training samples. Training on a large data set allows machine learning models to generalize new, unseen data samples. However, in many real-world scenarios, obtaining a large amount of labeled data can be very difficult, expensive, time consuming or all of the above. This is where few-shot learning comes into play. Few-shot learning enables machine learning models to learn from only a few labeled data samples.

More From This Expert5 Deep Learning and Neural Network Activation Functions to Know

One reason few-shot learning is important is because it makes developing machine learning models in real-world settings feasible. In many real-world scenarios, it can be challenging to obtain a large data set we can use to train a machine learning model. Learning on a smaller training data set can significantly reduce the cost and effort required to train machine learning models. Few-shot learning makes this possible because the technique enables models to learn from only a small amount of data.

Few-shot learning can also enable the development of more flexible and adaptive machine learning systems. Traditional machine learning algorithms are typically designed to perform well on specific tasks and are trained on huge data sets with a large number of labeled examples. This means that algorithms may not generalize well to new, unseen data or perform well on tasks that are significantly different from the ones on which they were trained.

Few-shot learning solves this challenge by enabling machine learning models to learn how to learn and adapt quickly to new tasks based on a small number of labeled examples. As a result, the models become more flexible and adaptable.

Few-shot learning has many potential applications in areas such as computer vision, natural language processing (NLP) and robotics. For example, when we use few-shot learning in robotics, robots can quickly learn new tasks based on just a few examples. In natural language processing, language models can better learn new languages or dialects with minimal training data.

An error occurred.

Few-shot learning has become a promising approach for solving problems where data is limited. Here are three of the most promising approaches for few-shot learning.

Meta-learning, also known as learning to learn, involves training a model to learn the underlying structure (or meta-knowledge) of a task. Meta-learning has shown promising results for few-shot learning tasks where the model is trained on a set of tasks and learns to generalize to new tasks by learning just a few data samples. During the meta-learning process, we can train the model using meta-learning algorithms such as model-agnostic meta-learning (MALM) or by using prototypical networks.

Data augmentation refers to a technique wherein new training data samples are created by applying various transformations to the existing training data set. One major advantage of this approach is that it can improve the generalization of machine learning models in many computer vision tasks, including few-shot learning.

For computer vision tasks, data augmentation involves techniques like rotation, flipping, scaling and color jittering existing images to generate additional image samples for each class. We then add these additional images to the existing data set, which we can then use to train a few-shot learning model.

Generative models, such as variational autoencoders (VAEs) and generative adversarial networks (GANs) have shown promising results for few-shot learning. These models are able to generate new data points that are similar to the training data.

In the context of few-shot learning, we can use generative models to augment the existing data with additional examples. The model does this by generating new examples that are similar to the few labeled examples available. We can also use generative models to generate examples for new classes that are not present in the training data. By doing so, generative models can help expand the data set for training and improve the performance of the few-shot learning algorithm.

In computer vision, we can apply few-shot learning to image classification tasks wherein our goal is to classify images into different categories. In this example, we can use few-shot learning to train a machine learning model to classify images with a limited amount of labeled data. Labeled data refers to a set of images with corresponding labels, which indicate the category or class to which each image belongs. In computer vision, obtaining a large number of labeled data is often difficult. For this reason, few-shot learning might be helpful since it allows machine learning models to learn on fewer labeled data.

Few-shot learning can be applied to various NLP tasks like text classification, sentiment analysis and language translation. For instance, in text classification, few-shot learning algorithms could learn to classify text into different categories with only a small number of labeled text examples. This approach can be particularly useful for tasks in the area of spam detection, topic classification and sentiment analysis.

Related Reading From Built In ExpertsWhat Are Self-Driving Cars?

In robotics, we can apply few-shot learning to tasks like object manipulation and motion planning. Few-shot learning can enable robots to learn to manipulate objects or plan their movement trajectories by using small amounts of training data. For robotics, the training data typically consists of demonstrations or sensor data.

In medical imaging, learning from only a few exposures can help us train machine learning models for medical imaging tasks such as tumor segmentation and disease classification. In medicine, the number of available images is usually limited due to strict legal regulations and data protection laws around medical information. As a result, there is less data available on which to train machine learning models. Few-shot learning solves this problem because it enables machine learning models to successfully learn to perform the mentioned tasks on a limited data set.

See original here:
What Is Few Shot Learning? (Definition, Applications) - Built In

New telescopes with unprecedented sensitivity and resolution are being unveiled around the world and beyond. Among them are theGiant Magellan Telescopeunder construction in Chile, and theJames Webb Space Telescope, which is parked a million and a half kilometres out in space.

This means there is a wealth of data available to scientists that simply wasnt there before. The raw data from just a single observation of the MeerKAT radio telescopein South Africas Northern Cape province can measure a terabyte. Thats enough to fill a laptop computers hard drive.

MeerKATis an array of 64 large antenna dishes. It uses radio signals from space to study the evolution of the universe and everything it contains galaxies, for example. Each dish is said to generate as muchdata in one secondas youd find on a DVD.

Machine learningis helping astronomers to work through this data quickly and more accurately than poring over it manually.

Perhaps surprisingly, despite increasing reliance on computers, up until recently the discovery of rare or new astrophysical phenomena has completely relied on human inspection of the data.

Machine learning is essentially a set of algorithms designed to automatically learn patterns and models from data. Because we astronomers arent sure what were going to find we dont know what we dont know we also design algorithms to look out for anomalies that dont fit known parameters or labels.

This approach allowed my colleagues and Ito spot a previously overlooked object in data from MeerKAT. It sits some seven billion light years from Earth a light year is a measure of how far light would travel in a year. From what we know of the object so far, it has many of the makings of whats known as an Odd Radio Circle (ORC).

Odd Radio Circles are identifiable by theirstrange, ring like structure. Only a handful of these circles have been detected since the first discovery in 2019, so not much is known about them yet.

In a newpaper we outline the features of our potential ORC, which weve named Sauron (a Steep and Uneven Ring Of Non-thermal Radiation). Sauron is, to our knowledge, the first scientific discovery made in MeerKAT data with machine learning. There have been a handful of other discoveries assisted by machine learning in astronomy.

Not only is discovering something new incredibly exciting, new discoveries are critical for challenging our understanding of thecosmos. These new objects may match our theories of how galaxies form and evolve, or we may need to change how we see the universe. New discoveries of anomalous astrophysical objects help science to make progress.

Identifying anomalies

We spotted Sauron in data from theMeerKAT Galaxy Cluster Legacy Survey.

The survey is a programme of observations conducted with South Africas MeerKAT telescope, a precursor to theSquare Kilometre Array. The array is a global project to build the worlds largest and most sensitive radio telescope within the coming decade, co-located in South Africa and Australia.

The survey was conducted between June 2018 and June 2019. It zeroed in on some 115 galaxy clusters, each made up of hundreds or even thousands of galaxies.

Thats a lot of data to sift through, which is where machine learning comes in.

We developed and used a coding framework which we calledAstronomalyto sort through the data. Astronomaly ranked unknown objects according to an anomaly scoring system. The human team then manually evaluated the 200 anomalies that interested us most. Here, we drew on vast collective expertise to make sense of the data.

It was during this part of the process that we identified Sauron. Instead of having to look at 6 000 individual images, we only had to look through the first 60 that Astronomaly flagged as anomalous to pick up Sauron.

But the question remains: what, exactly, have we found?

Is Sauron an ORC?

We know very little about ORCs. It is currently thought that their bright, blast-like emission is the wreckage of a huge explosionin their host galaxies.

The name Sauron captures the fundamentals of the objects make-up. Steep refers to its spectral slope, indicating that at higher radio frequencies the source (or object) very quickly grows fainter. Ring refers to the shape. And the Non-Thermal Radiation refers to the type of radiation, suggesting that there must be particles accelerating in powerful magnetic fields. Sauron is at least 1.2 million light years across, about 20 times the size of the Milky Way.

But Sauron doesnt tick all the right boxes for us to say its definitely an ORC. We detected a host galaxy but can find no evidence of radio emissions with the wavelengths and frequency that match those of host galaxies of the other known ORCs.

And even thoughSauron has a number of features in common with Odd Radio Circle1 the first ORC spotted it differs in others. Its strange shape and oddly behaving magnetic fields dont align well with the main structure.

One of the most exciting possibilities is that Sauron is a remnant of the explosive merger of two supermassive black holes. These are incredibly dense objects at the centre of galaxies such as our Milky Way that could cause a massive explosion when galaxies collide.

More to come

More investigation is required to unravel the mystery.

Meanwhile, machine learning is quickly becoming an indispensable tool to find more strange objects by sorting through enormous datasets from telescopes. With this tool, we can expect to unveil more of what the universe is hiding.

Michelle Lochner is Senior Lecturer in Astronomy, University of the Western Cape

This article is republished fromThe Conversationunder a Creative Commons licence. Read theoriginal articlehere.

AI Masterclass:Moneyweb has partnered with the Institute for Technology Strategy andInnovation and North-West University Business School to offer aground-breaking new artificial intelligence course.AllInsider Gold subscribersreceivereceive a 10% discount for the four-day virtual course. For more information clickhere.

The rest is here:
Astronomers used machine learning to mine SA's MeerKAT ... - Moneyweb