Problem/Opportunity

Through legislation and lifestyle changes, consumers on average are becoming more aware of the good and bad of what they’re eating (e.g., calorie counts in states that require listing at chain restaurants), but there’s currently few ways for people to track how their diet and lifestyle truly impacts their health. Fitness monitoring has increased in popularity through the proliferation of smart devices, but there’s no automated equivalent for monitoring your diet, and even if you manually log everything you eat, it’s nearly impossible to know how your body reacts to certain foods, and if your body is getting everything it needs.  

 

This is a problem and opportunity that reaches across age ranges and demographics.   A solution that provides seamless nutritional monitoring and recommendations based on dietary shortfalls and user habits/behaviors that adjusts based on learned preferences could benefit everyone.  For example, even with rigorous food tracking, elite athletes can’t truly tell if they’re getting adequate levels of, say, the eight essential amino acids.  Cancer patients or those in remission don’t truly know if they’re getting enough Vitamin C or D.  Diabetics can currently monitor their glucose levels, but could be at a loss in terms of what else they should be tracking.  Everyday consumers may be falling short on certain vitamins and minerals, but aren’t aware of their impact or how to close those gaps.

 

Solution

To address the opportunity described above, we would like to reintroduce HiPo! and its next line of product, Hi-Per!. Hi-Per! is designed to continually monitor key nutrient levels in the human body and provide feedback in the form of food consumption recommendations and alerts that ensure individuals maintain optimal levels of health.

 

Recent developments in technology have expanded the possibilities of how sensors are used to evaluate health and wellness attributes. While existing sensor technology focuses on measuring nutrient levels of food items, we believe that the application of this technology to nutrient levels and other health metrics of an actual individual is a viable next step. Hi-Per!  is housed in wearable (and fashionable) wristband sensor that uses infrared spectrometer technology to make periodic measurements of the user’s vitals and nutrient levels. This information is sent to the Hi-Per! application which is accessible on the user’s mobile device.

 

The application itself leverages a machine learning recommendation algorithm to evaluate the user’s vitals and nutrient levels, alert the user of any deficiencies, and suggest preferred foods to remediate those deficiencies. The algorithm is built upon a database of inputs, including: (a) benchmark vital and nutrient level data for different user profiles based on sex, age, and weight; (b) nutritional data on food and drinks; (c) research data on the metabolic profiles of both individuals and foods. Using these inputs, the algorithm will be designed to optimize a user’s food and drink consumption based on their nutrient needs, taste preferences, and individualized food digestion traits (i.e., metabolic behavior). The user will be able to log what food and drink has been consumed in the application, providing a feedback loop that will further optimize the user’s health and wellness profile.

Pilot
We conducted a pilot study on 10,000 pregnant women. A recent study showed that prenatal vitamins do not have benefits for women and their unborn children as advertised and, instead, pregnant women should focus on improving the overall quality of their diet to reduce complications related to birth and pregnancy from vitamin deficiencies. Yet there are many dietary restrictions placed on what women can consume during pregnancy. Given the heightened health awareness, benefits of optimal vitamin levels, and dietary restrictions, pregnant women represent an ideal customer base to test our technology. We focused on optimizing the top 8 nutrients pregnant women need: iron, calcium, vitamin D, folate, protein, zinc, iodine, and omega 3-fatty acids. The results drastically showed how Hi-Per! was able to improve vitamin levels in pregnant women to minimize birth defects and pregnancy complications. For example, abnormal bone growth, fractures, and rickets in newborns decreased in prevalence by 65% against control groups (attributed to vitamin D levels).

 

Sources:

https://www.fastcompany.com/3030342/this-tiny-device-fits-on-your-keychain-and-measures-the-calories-in-your-dinner

http://www.livescience.com/55363-prenatal-multivitamins-dont-help-much.html

Problem

Recent events in the U.S have highlighted the need for an effective system that is able to identify police officers who are at risk of serious misconduct in order to provide them with the proper training to mitigate potential misconduct. According to the Chicago Reporter, the officer in Chicago who shot and killed 17-year-old Laquan McDonald in October 2014 had 19 citizen complaints and two misconduct lawsuits against him, yet the system in place had not flagged him as at risk of misconduct. Many current systems do not use computer programming to identify potentially problematic officers, and instead rely on a threshold system that uses only a limited number of metrics. This threshold system often places an unnecessarily high number of officers in an at-risk category, failing to identify officers that are truly most at-risk of committing adverse actions.

 

According to FiveThirtyEight, the number of prior complaints against police officers is strongly correlated with future misconduct. Police departments can combine this data with other police officer attributes to build a predictive model which identifies officers with a high-risk of misconduct prior to that misconduct actually taking place.

 

Solution

A team of researchers with the University of Chicago’s Center for Data Science and Public Policy developed an early intervention system (EIS) predictive model that can foresee adverse interactions between officers and civilians. In addition to flagging risk, the model also provides suggestions for preventative measures based on the individual’s risk profile.

In order to develop the predictive model, the researchers analyzed a comprehensive data set of interactions between cops and the public gathered by Charlotte police officials for more than ten years. The data included information on officer attributes, officer activities, and internal affairs investigations provided by the police department, as well as publically-available data such as weather and quality-of-life survey information. They tested the data using historical information to see which pieces of data would have predicted officers committing misconduct.

 

They found that cops with many instances of adverse interactions in one year were the most likely to have them in the next year, so they use this, combined with other indicators, to predict potential issues in the police force. Some of the identified additional indicators include excessive tardiness, misuse of medical leave, or a low grade on an annual performance review.

 

Results and Potential Improvements

Since police departments are not yet actively using this EIS, the researchers do not know if the predictions will successfully enable interventions that will reduce the likelihood of adverse interactions. However, three studies of police agencies that have implemented similar early warning systems have shown that targeted interventions can reduce citizen complaints against officers as much as 66 percent over two to three years. For example, if EIS identifies officers that are at high risk of committing misconduct, the police department can implement interventions that address the causes of the risk, such as training for working with youth.

 

The model developed by University of Chicago researchers correctly flagged 15 – 20 percent more officers who were involved later in adverse incidents than the current system in Charlotte, while also reducing the number officers incorrectly flagged by 50 percent or more. By improving the ability to correctly identify at-risk officers and the causes behind adverse incidents, this model will enable police departments to save time and resources while also improving their effectiveness in keeping their jurisdictions safe.

 

While other early intervention systems exist, the strength of this model is that it uses multiple indicators, rather than a single indicator threshold. By using multiple indicators, police departments will better be able to identify the root causes of police officer misconduct, which will allow them to implement more effective interventions to prevent this misconduct.

 

The success of the EIS algorithm is dependent on the quality and relevance of the inputted data. The Center for Data Science and Public Policy can improve the EIS by finding new sources of data that come from outside a police department. An organization called OpenOversight in Chicago has attempted to democratize police accountability by providing a digital gallery that allows the public to identify the name and badge number of a police officer they would like to file a complaint about. From March 2011 – March 2015, 28 percent of police complaints in Chicago were immediately dropped due to no officer identification. These are complaints that likely would not show up in the EIS so crowdsourced data from an organization like OpenOversight could help to fill this gap. Additionally, data crowdsourced from the public could serve as a way to check potential biases currently impacting a police department’s data.

By: Ex Machina Learners

Sources:

“About OpenOversight.” OpenOversight – a Lucy Parsons Labs Project. N.p., n.d. Web. 21 Apr. 2017.

 

Arthur, Rob. “We Now Have Algorithms To Predict Police Misconduct.” FiveThirtyEight. FiveThirtyEight, 10 Mar. 2016. Web. 21 Apr. 2017.

 

Gregory, Ted. “U. of C. Researchers Use Data to Predict Police Misconduct.”Chicagotribune.com. N.p., 18 Aug. 2016. Web. 21 Apr. 2017.

 

Joseph, George. “Crowdsourcing Police Accountability.” CityLab. N.p., 25 Oct. 2016. Web. 21 Apr. 2017.

 

Mitchum, Rob, Jacqueline Genova, and Lin Taylor. “Police Project Update: Expanding and Implementing the Early Intervention System.” Data Science for Social Good. N.p., 12 Jan. 2017. Web. 21 Apr. 2017

 

Newman, Jonah. “Program That Flags Chicago Cops at Risk of Misconduct Misses Most Officers.” Chicago Reporter. N.p., 04 Mar. 2016. Web. 21 Apr. 2017.

 

Smith, Megan. “Launching the Police Data Initiative.” National Archives and Records Administration. National Archives and Records Administration, 18 May 2015. Web. 21 Apr. 2017.

Opportunity & Solution Summary

Beyond the enormous societal benefit of reducing traffic collisions, a connected fleet of autonomous vehicles allows for more predictable, efficient traffic flow; improved mobility and productivity among travelers; and–eventually–a business model shift from outright vehicle ownership to ‘transportation-as-a-service’.

Looking ahead, the National Highway Traffic Safety Administration (NHTSA) created a five-level classification system of autonomous capabilities to measure progress and innovation:

In October 2015, Tesla Motors pushed software version 7.0 to its Model S customers, which included Tesla Autopilot, the most advanced publicly-available autonomous driving software.

While many companies have developed autonomous capabilities (particularly Google, who, as the first-mover, logged 1 million fully-autonomous miles before Tesla launched Autopilot), Tesla’s software has uniquely iterated and addressed the changing needs of the user to become the superior solution.  Interestingly, 20+ automakers have more autonomous driving patents than Tesla (mostly surrounding anti-collision and braking control mechanisms), but Tesla has been the first automaker to provide substantial Level 3 features in the marketplace.

This has enabled Tesla to leverage its thousands of drivers to quickly improve its algorithms via ensemble training.  By pushing these solutions to the market, Tesla has logged 50-fold more autonomous miles (supplemented by user feedback) than Google to boost algorithm performance.  In the short run, this means improving vehicle efficiency and customers safety.  In the longer run, this means reaching full self-driving automation (“Level 4”).  The software’s continuous learning technology enables the autonomous cars to update as new processes are observed from the user.

NVIDIA and Tesla together have fed millions of miles worth of driving data and videos to train the computer about driving.  Tesla leverages NVIDIA’s DRIVE PX 2 platform to run an internally-developed neural net for vision, sonar, and radar processing.  DRIVE PX 2 works in combination with version 6.0 of its deep-learning CUDA® Deep Neural Network library (cuDNN) and Tesla’s P100 GPU to detect and classify objects 10x faster than its previous processor, dramatically increasing the accuracy of its decision-making.

Effectiveness, Commercial Promise, and Competition

While Google’s technology is more precise–it’s LIDAR system builds a 360-degree model that tracks obstacles better than Tesla, and can localize itself within 10 centimeters–Tesla’s is publicly available at a reasonable price.  Tesla’s most recent hardware set includes forward-facing radar, as well as eight cameras and twelve sensors around the vehicle.  The company continues to roll out new features in regular over-the-air updates.

To date, Tesla’s continuous push of new/updated Autopilot features has been (largely) successful in improving consumer safety.  Following a 2016 investigation into a deadly crash involving a Tesla Model S (which was closed without issue), the U.S. Department of Transportation found Tesla’s Autosteer feature had already improved Tesla’s exemplary safety record, reducing accidents by 40%, from 1.3 to 0.8 crashes per million miles.

 

Tesla’s software algorithms are a short-run competitive advantage over other automakers; its technology is in the hands of more users, quickly improving its solution.  However, as full-autonomous driving becomes commoditized over 10-30 years, the automotive business model will shift from vehicle ownership to transportation-as-a-service and the competitive advantage will shift towards mass-market fleet vehicle manufacturers (e.g., Toyota, Ford, GM).  If vehicles aren’t owned by the end-user, and, instead, summoned or rented, the need for a superior driving experience drastically decreases in favor of the cheapest fare. Accordingly, GM invested $500M in Lyft last year to begin building an integrated on-demand network of autonomous vehicles.

Improvement and Alterations

Tesla has made progress since its first software push, but according to Elon Musk–the company is multiple years away from pushing out Level 4 capabilities.  Moving forward, Tesla’s biggest obstacles (beyond regulation) are better local road mapping; removing the need for user input; and stronger recognition of stop signs, traffic lights, and road updates.  In most geographies, many Autopilot features are geoblocked, restricting use primarily to highways and other major roads.  By training its software to better recognize stop sign images, as well as traffic light locations and color changes, Autopilot can be utilized in more local situations.  In addition, Tesla’s publicly-available vehicles are not yet truly autonomous, even on highways.  Vehicles have hands-on warnings that require the driver to be engaged throughout the ride, as well as a feature that shuts off Autopilot for the remainder of the drive cycle if the driver fails to respond to alerts (“Autopilot strikeout”).

 

Tesla’s Autopilot In Action

Blog post by Ex Machina Learners

Sources

Ackerman Evan. “GM Starts Catching Up in Self-Driving Car Tech with $1 Billion Acquisition of Cruise Automation.” IEEE Spectrum: Technology, Engineering, and Science News. N.p., 14 Mar. 2016. Web. 07 Apr. 2017.

“Autopilot.” Tesla, Inc. Apr. 2017.

Fehrenbacher, Katie. “How Tesla’s Autopilot Learns.” How Tesla’s Autopilot Learns. Fortune, 19 Oct. 2015. Web. 07 Apr. 2017.

Habib, Kareem. “Automatic Vehicle Control Systems.” U.S. Department of Transportation NHTSA Announcement. Jan. 2017.

“NVIDIA CuDNN.” NVIDIA Developer. N.p., 30 Mar. 2017. Web. 07 Apr. 2017.

Pressman, Matt. “Inside NVIDIA’s New Self-Driving Supercomputer Powering Tesla’s Autopilot.” CleanTechnica. N.p., 25 Oct. 2016. Web. 07 Apr. 2017.

Randall, Tom. “Tesla’s Autopilot Vindicated With 40% Drop in Crashes.” Bloomberg.com. Bloomberg, 19 Jan. 2017. Web. 04 Apr. 2017.

Vijh, Rahul. “Autonomous Cars – Patents and Perspectives.” IPWatchdog.com | Patents & Patent Law. N.p., 06 Apr. 2016. Web. 07 Apr. 2017.