By using deep learning and predictive analytics, researchers have determined who could develop age-related chronic disease based on immune system health.

Researchers from the Buck Institute and Stanford University have created an inflammatory clock for aging (iAge) that uses deep learning and predictive analytics to determine immunological health and chronic diseases associated with aging. By utilizing artificial intelligence technology, researchers studied the blood immunome of 1001 people.

The team of researchers also discovered a modifiable chemokine associated with cardiac aging. This chemokine can be used for early detection of age-related pathology and can help provide targets for interventions.

“Standard immune metrics which can be used to identify individuals most at risk for developing single or even multiple chronic diseases of aging have been sorely lacking,” David Furman, PhD, Buck Institute Associate Professor, Director of the 1001 Immunomes Project at Stanford University School of Medicine and senior author of the study said in a press release.

Dig Deeper

• Deep Learning Aids Prediction of Lung Cancer Immunotherapy Response
• Deep Learning, Genomic Data May Help Predict Alzheimer’s Disease
• Deep Learning Approach May Reduce Knee Pain Disparities

“Bringing biology to our completely unbiased approach allowed us to identify a number of metrics, including a small immune protein which is involved in age-related systemic chronic inflammation and cardiac aging. We now have means of detecting dysfunction and a pathway to intervention before full-blown pathology occurs,” Furman continued.

According to first author Nazish Sayed, MD, PhD, Assistant Professor of Vascular Surgery at Stanford Medicine, the study highlights the soluble chemokine CXCL9 as the major contributor to iAge. Furman describes CXCL0 as a small immune protein typically called to action to attract lymphocytes to infection sites.

“But in this case we showed that CXCL9 upregulates multiple genes implicated in inflammation and is involved in cellular senescence, vascular aging and adverse cardiac remodeling,” Furman stated then added that silencing CXCL9 reversed the loss of function in aging endothelial cells in humans and mice.

According to Furman, the age of one’s immune system provides important information regarding health and longevity.

“On average, centenarians have an immune age that is 40 years younger than what is considered ‘normal’ and we have one outlier, a super-healthy 105 year-old man (who lives in Italy) who has the immune system of a 25 year old,” he said.

 Results for the initial analysis and the cardiac health study were able to be validated. Additionally, Furman said that the researchers found a correlation between CXCL9 and the results from the pulse wave velocity testing.

“These people are all healthy according to all available lab tests and clinical assessments, but by using iAge we were able to predict who is likely to suffer from left ventricular hypertrophy (an enlargement and thickening of the walls of the heart’s main pumping chamber) and vascular dysfunction,” Furman said.

These artificial intelligence tools can be used to track a patient’s risk of developing multiple chronic diseases by assessing the total physiological damage done to their immune system.

Predictive analytics of age-related frailty can be determined by comparing biological immune metrics to information about how long it takes an individual to perform a task, such as standing up from a chair or walking a certain distance.

“Using iAge it’s possible to predict seven years in advance who is going to become frail,” Furman said. “That leaves us lots of room for interventions.”

In 2013, a group of researchers conducted a study on aging and identified nine “hallmarks” in the process. Age-related immune system dysfunction was not one of them.

“It’s becoming clear that we have to pay more attention to the immune system with age, given that almost every age-related malady has inflammation as part of its etiology,” said Furman.

“If you’re chronically inflamed, you will have genomic instability as well as mitochondrial dysfunction and issues with protein stability. Systemic chronic inflammation triggers telomere attrition, as well as epigenetic alterations. It’s clear that all of these nine hallmarks are, by and large, triggered by having systemic chronic inflammation in your body. I think of inflammation as the 10th hallmark,” Furman concluded.

The post Deep Learning, Predictive Analytics Helps Identify Chronic Diseases appeared first on Artificial Intelligence.

Researchers from the Queensland University of Technology (QUT) in Australia have developed an algorithm that detects misogynistic content on Twitter.

The team developed the system by first mining 1 million tweets. They then refined the dataset by searching the posts for three abusive keywords: whore, slut, and rape.

Next, they categorized the remaining 5,000 tweets as either misogynistic or not, based on their context and intent. These labeled tweets were then fed to a machine learning classifier, which used the samples to create its own classification model.

The system uses a deep learning algorithm to adjust its knowledge of terminology as language evolves. While the AI built up its vocabulary, the researchers monitored the context and intent of the language, to help the algorithm differentiate between abuse, sarcasm, and “friendly use of aggressive terminology.”

“Take the phrase ‘get back to the kitchen’ as an example — devoid of context of structural inequality, a machine’s literal interpretation could miss the misogynistic meaning,” said Professor Richi Naya, a co-author of the study.

“But seen with the understanding of what constitutes abusive or misogynistic language, it can be identified as a misogynistic tweet.”

Nayak said this enabled the system to understand different contexts just by analyzing text, and without the help of tone.

We were very happy when our algorithm identified ‘go back to the kitchen’ as misogynistic — it demonstrated that the context learning works.

The researchers say the model identifies misogynistic tweets with 75% accuracy. It could also be adjusted to spot racism, homophobia, or abuse of disabled people.

The team now wants social media platforms to develop their research into an abuse detection tool.

“At the moment, the onus is on the user to report abuse they receive,” said Naya. “We hope our machine-learning solution can be adopted by social media platforms to automatically identify and report this content to protect women and other user groups online.”

You can read the research paper on the Springer database of academic journals.

The post New algorithm can identify misogyny on Twitter appeared first on Artificial Intelligence.

As companies step up the use of machine learning-enabled systems in their day-to-day operations, they become increasingly reliant on those systems to help them make critical business decisions. In some cases, the machine learning systems operate autonomously, making it especially important that the automated decision-making works as intended.

However, machine learning-based systems are only as good as the data that’s used to train them. If there are inherent biases in the data used to feed a machine learning algorithm, the result could be systems that are untrustworthy and potentially harmful.

In this article, you’ll learn why bias in AI systems is a cause for concern, how to identify different types of biases and six effective methods for reducing bias in machine learning.

Why is eliminating bias important?

The power of machine learning comes from its ability to learn from data and apply that learning experience to new data the systems have never seen before. However, one of the challenges data scientists have is ensuring that the data that’s fed into machine learning algorithms is not only clean, accurate and — in the case of supervised learning, well-labeled — but also free of any inherently biased data that can skew machine learning results.

The power of supervised learning, one of the core approaches to machine learning, in particular depends heavily on the quality of the training data. So it should be no surprise that when biased training data is used to teach these systems, the results are biased AI systems. Biased AI systems that are put into implementation can cause problems, especially when used in automated decision-making systems, autonomous operation, or facial recognition software that makes predictions or renders judgment on individuals.

Some notable examples of the bad outcomes caused by algorithmic bias include: a Google image recognition system that misidentified images of minorities in an offensive way; automated credit applications from Goldman Sachs that have sparked an investigation into gender bias; and a racially biased AI program used to sentence criminals. Enterprises must be hyper-vigilant about machine learning bias: Any value delivered by AI and machine learning systems in terms of efficiency or productivity will be wiped out if the algorithms discriminate against individuals and subsets of the population.

However, AI bias is not only limited to discrimination against individuals. Biased data sets can jeopardize business processes when applied to objects and data of all types. For example, take a machine learning model that was trained to recognize wedding dresses. If the model was trained using Western data, then wedding dresses would be categorized primarily by identifying shades of white. This model would fail in non-Western countries where colorful wedding dresses are more commonly accepted. Errors also abound where data sets have bias in terms of the time of day when data was collected, the condition of the data and other factors.

All of the examples described above represent some sort of bias that was introduced by humans as part of their data selection and identification methods for training the machine learning model. Because the systems technologists build are necessarily colored by their own experiences, they must be very aware that their individual biases can jeopardize the quality of the training data. Individual bias, in turn, can easily become a systemic bias as bad predictions and unfair outcomes are automated.

How to identify and measure AI bias

Part of the challenge of identifying bias is due to the difficulty of seeing how some machine learning algorithms generalize their learning from the training data. In particular, deep learning algorithms have proven to be remarkably powerful in their capabilities. This approach to neural networks leverages large quantities of data, high performance compute power and a sophisticated approach to efficiency, resulting in machine learning models with profound abilities.

Deep learning, however, is a “black box.” It’s not clear how an individual decision was arrived at by the neural network predictive model. You can’t simply query the system and determine with precision which inputs resulted in which outputs. This makes it hard to spot and eliminate potential biases when they arise in the results. Researchers are increasingly turning their focus on adding explainability to neural networks. Verification is the process of proving the properties of neural networks. However, because of the size of neural networks, it can be hard to check them for bias.

Until we have truly explainable systems, we must understand how to recognize and measure AI bias in machine learning models. Some of the biases in the data sets arise from the selection of training data sets. The model needs to represent the data as it exists in the real world. If your data set is artificially constrained to a subset of the population, you will get skewed results in the real world, even if it performs very well against training data. Likewise, data scientists must take care in how they select which data to include in a training data set and which features or dimensions are included in the data for machine learning training.

Companies are combating inherent data bias by implementing programs to not only broaden the diversity of their data sets, but also the diversity of their teams. More diversity on teams means that people of many perspectives and varied experiences are feeding systems the data points to learn from. Unfortunately, the tech industry today is very homogeneous; there are not many women or people of color in the field. Efforts to diversify teams should also have a positive impact on the machine learning models produced, since data science teams will be better able to understand the requirements for more representative data sets.

Different types of machine learning bias

There are a few sources for the bias that can have an adverse impact on machine learning models. Some of these are represented in the data that is collected and others in the methods used to sample, aggregate, filter and enhance that data.

• Sampling bias. One common form of bias results from mistakes made when collecting data. A sampling bias happens when data is collected in a manner that oversamples from one community and under samples from another. This might be intentional or unintentional. The result is a model that is overrepresented by a particular characteristic, and as a result is weighted or biased in that way. The ideal sampling should either be completely random or match the characteristics of the population to be modeled.
• Measurement bias. Measurement bias is the result of not accurately measuring or recording the data that has been selected. For example, if you are using salary as a measurement, there might be differences in salary including bonus or other incentives, or regional differences in the data. Other measurement bias can result from using incorrect units, normalizing data in incorrect ways or miscalculations.
• Exclusion bias. Similar to sampling bias, exclusion bias arises from data that is inappropriately removed from the data source. When you have petabytes or more of data, it’s tempting to select a small sample to use for training, but when doing so you might be inadvertently excluding certain data, resulting in a biased data set. Exclusion bias can also occur due to removing duplicates from data when the data elements are actually distinct.
• Experimenter or observer bias. Sometimes, the act of recording data itself can be biased. When recording data, the experimenter or observer might only record certain instances of data, skipping others. Perhaps you’re creating a machine learning model based on sensor data but only sampling every few seconds, missing key data elements. Or there is some other systemic issue in the way that the data has been observed or recorded. In some instances, the data itself might even become biased by the act of observing or recording that data, which could trigger behavioral changes.
• Prejudicial bias. One insidious form of bias has to do with human prejudices. In some cases, data might become tainted by bias based on human activities that under-selected certain communities and over-selected others. When using historical data to train models, especially in areas that have previously been rife with prejudicial bias, care should be taken to make sure new models don’t incorporate that bias.
• Confirmation bias. Confirmation bias is the desire to select only the information that supports or confirms something you already know, rather than data that might suggest something that runs counter to preconceived notions. The result is data that is tainted because it was selected in a biased manner or because information that doesn’t confirm the preconceived notion is thrown out.
• Bandwagoning or bandwagon effect. The bandwagon effect is a form of bias that happens when there is a trend occurring in the data or in some community. As the trend grows, the data supporting that trend increases and data scientists run the risk of overrepresenting the idea in the data they collect. Moreover, any significance in the data may be short-lived: The bandwagon effect could disappear as quickly as it appeared.

There are no doubt other types of bias that might be represented in the data set than just the ones listed above, and all those forms should be identified early in the machine learning project.

Six ways to reduce bias in machine learning

1. Identify potential sources of bias. Using the above sources of bias as a guide, one way to address and mitigate bias is to examine the data and see how the different forms of bias could impact the data being used to train the machine learning model. Have you selected the data without bias? Have you made sure there isn’t any bias arising from errors in data capture or observation? Are you making sure not to use an historic data set tainted with prejudice or confirmation bias? By asking these questions you can help to identify and potentially eliminate that bias.

2. Set guidelines and rules for eliminating bias and procedures. To keep bias in check, organizations should set guidelines, rules and procedures for identifying, communicating and mitigating potential data set bias. Forward-thinking organizations are documenting cases of bias as they occur, outlining the steps taken to identify bias, and explaining the efforts taken to mitigate bias. By establishing these rules and communicating them in an open, transparent manner, organizations can put the right foot forward to address issues of machine learning model bias.

3. Identify accurate representative data. Prior to collecting and aggregating data for machine learning model training, organizations should first try to understand what a representative data set should look like. Data scientists should use their data analysis skills to understand the nature of the population that is to be modeled along with the characteristics of the data used to create the machine learning model. These two things should match in order to build a data set with as little bias as possible.

4. Document and share how data is selected and cleansed. Many forms of bias occur when selecting data from among large data sets and during data cleansing operations. In order to make sure few bias-inducing mistakes are made, organizations should document their methods of data selection and cleansing and allow others to examine when and if the models exhibit any form of bias. Transparency allows for root-cause analysis of sources of bias to be eliminated in future model iterations.

5. Evaluate model for performance and select least-biased, in addition to performance. Machine learning models are often evaluated prior to being placed into operation. Most of the time these evaluation steps focus on aspects of model accuracy and precision. Organizations should also add measures of bias detection in their model evaluation steps. Even if the model performs with certain levels of accuracy and precision for particular tasks, it could fail on measures of bias, which might point to issues with the training data.

6. Monitor and review models in operation. Finally, there is a difference between how the machine learning model performs in training and how it performs in the real world. Organizations should provide methods to monitor and continuously review the models as they perform in operation. If there are signs that certain forms of bias are showing up in the results, then the organization can take action before the bias causes irreparable harm.

Combating machine learning bias makes for more robust systems

When bias becomes embedded in machine learning models, it can have an adverse impact on our daily lives. The bias is exhibited in the form of exclusion, such as certain groups being denied loans or not being able to use the technology, or in the technology not working the same for everyone. As AI continues to become more a part of our lives, the risks from bias only grow larger. Companies, researchers and developers have a responsibility to minimize bias in AI systems. A lot of it comes down to ensuring that the data sets are representative and that the interpretation of data sets is correctly understood. However, just making sure that the data sets aren’t biased won’t actually remove bias, so having diverse teams of people working toward the development of AI remains an important goal for enterprises.

The post 6 ways to reduce different types of bias in machine learning appeared first on Artificial Intelligence.

The supply chain industry is facing data flooding at an accelerated rate. And this is hampering the organization’s ability to keep up with the upcoming insights and the inflows. 

The bottlenecks are becoming too prominent in the network.

While, decision-makers are trying to seek out effective ways to manage humongous amounts of data. In the end, they want the power of their data should benefit the company in a significant way.

The leaders want their supply chain to leverage the capabilities of advanced analytics that can streamline the process, make it more responsive, customer centric, and demand driven.

Why Risk Management has become a key factor in Supply Chain?

According to KPMG.US: 

1. 61 percent of leaders (compared with 37 percent of others) consider supply chain risk management very important. As they recognize the importance of capabilities that can enable them to gain greater visibility and predictability across their network. 
2. Secondly, supply chain leaders are nearly three times as likely as other companies to boost their investments in risk management by 20 percent or more in the next two years.

So, how is machine learning (ML) helping the industry in breaking through the bottlenecks? 

One of the major issues that the process is facing is its over-the-top reactive approach to the risks, which most of the time disrupts the overall operations of the network.

For it a more proactive and predictive approach is required to identifying and mitigating risk before it affects operations. And also has the power to eliminate many unnecessary financial and operational losses.

Some more problems that the industry is facing

According to KPMG.US:

• No real-time reporting – 56% of supply chain executives do not have access to real-time reporting. 
• Risk and compliance issues – 50% have limited knowledge of risk and compliance issues.
• End-to-end visibility – 13% do not have complete end-to-end visibility of supply chains.
• Cyber breaches – 80% of all cyber breaches occur in the supply chain.  

1) Machine Learning helps gain visibility into the supply chain to determine where forthcoming bottlenecks can occur.

This implies the workforce getting visibility into the process, equipment, and inventory that comprises of an operations phase.

A lot of information can be driven to improve productivity out of supply chain, inventory management, manufacturing process, distribution, and fulfillment. 

Machine learning has the capability to take into account various factors that the traditional forecasting model cannot predict.

It not only looks for patterns, but mines deeper into extremely complex data and identify the potential issues that can be the holdup on the process. ML provides better simulation models of future environments by analyzing complex data sets.

2) Another way ML is helping supply chain is by reducing costs and improving response time.

With accurate forecasting capabilities, organizations can easily optimize their processes. They can also pinpoint the challenging areas that display inefficiencies, while also projecting the roadblocks or bottlenecks in the future.

Supply chain companies with emerging technologies, such as artificial intelligence and machine learning, have inculcated the capability to respond quickly to the upcoming threats by detecting them quickly. The faster an organization has the option to respond; the more cost-effective is the solution.

3) Machine learning also has the power to better manage and maintain the assets. 

When ML is integrated into asset management, it can predict the need for repairs with the help of Internet of Things (IoT) sensors. When an equipment breakdown, the IoT sensors sends an immediate notification so that the supply chain process faces very little or no downtime.

Additionally, when these sensors are paired with ML, they can predict when failure is about to occur. These forecasting can lead to prior servicing of the equipment before any issue arises, therefore reducing the cost of damages.

It has been noted that maintained equipment lasts longer with no downtime. 

IoT gives an opportunity that is cost-effective in managing and maintaining the equipment that cannot be achieved with the human inspection. Also, IoT analysis can be done more frequently than human inspections.

4) Real-time monitoring with transparency.

Machine Learning provides real-time monitoring throughout the supply chain process. With the right reporting and tracking, we can monitor each and every aspect in the supply chain with ease.

This helps in identifying core inefficiencies that need to be resolved, as well as the requirement to optimize and streamline the supply chain processes.

ML also promotes transparency that provides a 360 clear view of the process. Making it easier to report any loss in the inventory within the supply chain and also reducing the chances of lost or damaged inventories.

To Conclude

By integrating machine learning along with the emerging technologies in supply chain management, companies can achieve a better understanding of the logistics and operations.

With IoT devices, organizations have collected huge volumes of data that can streamline and optimize the supply chain. Resulting in better maintenance and superior overall outcomes.

Amit Dua is the Founder of Signity Solutions. A tech-evangelist, he has an uncanny ability to synergize and build associations, thriving teams, and reputable clients. His vision is to grow his decade-old company as per global standards, and his deep analytical skills to foresee market trends, as well as global challenges.

The post Identify bottlenecks in your supply chain with machine learning appeared first on Artificial Intelligence.