Non-invasive glucose monitor EasyGlucose takes home Microsoft’s Imagine Cup and $100K

Non-invasive glucose monitor EasyGlucose takes home Microsoft’s Imagine Cup and $100K

12:36pm, 8th May, 2019
yearly Imagine Cup student startup competition crowned its latest winner today: , a non-invasive, smartphone-based method for diabetics to test their blood glucose. It and the two other similarly beneficial finalists presented today at Microsoft’s Build developers conference. The Imagine Cup brings together winners of many local student competitions around the world with a focus on social good and, of course, Microsoft services like Azure. Last year’s winner was a smart prosthetic forearm that uses a camera in the palm to identify the object it is meant to grasp. (They were on hand today as well, with an improved prototype.) The three finalists hailed from the U.K., India, and the U.S.; EasyGlucose was a one-person team from my alma mater UCLA. EasyGlucose takes advantage of machine learning’s knack for spotting the signal in noisy data, in this case the tiny details of the eye’s iris. It turns out, as creator Brian Chiang explained in his presentation, that the iris’s “ridges, crypts, and furrows” hide tiny hints as to their owner’s blood glucose levels. EasyGlucose presents at the Imagine Cup finals. These features aren’t the kind of thing you can see with the naked eye (or rather, on the naked eye), but by clipping a macro lens onto a smartphone camera Chiang was able to get a clear enough image that his computer vision algorithms were able to analyze them. The resulting blood glucose measurement is significantly better than any non-invasive measure and more than good enough to serve in place of the most common method used by diabetics: stabbing themselves with a needle every couple hours. Currently EasyGlucose gets within 7 percent of the pinprick method, well above what’s needed for “clinical accuracy,” and Chiang is working on closing that gap. No doubt this innovation will be welcomed warmly by the community, as well as the low cost: $10 for the lens adapter, and $20 per month for continued support via the app. It’s not a home run, or not just yet: Naturally, a technology like this can’t go straight from the lab (or in this case the dorm) to global deployment. It needs FDA approval first, though it likely won’t have as protracted a review period as, say, a new cancer treatment or surgical device. In the meantime, EasyGlucose has a patent pending, so no one can eat its lunch while it navigates the red tape. As the winner, Chiang gets $100,000, plus $50,000 in Azure credit, plus the coveted one-on-one mentoring session with Microsoft CEO Satya Nadella. The other two Imagine Cup finalists also used computer vision (among other things) in service of social good. Caeli is taking on the issue of air pollution by producing custom high-performance air filter masks intended for people with chronic respiratory conditions who have to live in polluted areas. This is a serious problem in many places that cheap or off-the-shelf filters can’t really solve. It uses your phone’s front-facing camera to scan your face and pick the mask shape that makes the best seal against your face. What’s the point of a high-tech filter if the unwanted particles just creep in the sides? Part of the mask is a custom-designed compact nebulizer for anyone who needs medication delivered in mist form, for example someone with asthma. The medicine is delivered automatically according to the dosage and schedule set in the app — which also tracks pollution levels in the area so the user can avoid hot zones. Finderr is an interesting solution to the problem of visually impaired people being unable to find items they’ve left around their home. By using a custom camera and computer vision algorithm, the service watches the home and tracks the placement of everyday items: keys, bags, groceries, and so on. Just don’t lose your phone, since you’ll need that to find the other stuff. You call up the app and tell it (by speaking) what you’re looking for, then the phone’s camera it determines your location relative to the item you’re looking for, giving you audio feedback that guides you to it in a sort of “getting warmer” style, and a big visual indicator for those who can see it. After their presentations, I asked the creators a few questions about upcoming challenges, since as is usual in the Imagine Cup, these companies are extremely early stage. Right now EasyGlucose is working well but Chiang emphasized that the model still needs lots more data and testing across multiple demographics. It’s trained on 15,000 eye images but many more will be necessary to get the kind of data they’ll need to present to the FDA. Finderrr recognizes all the images in the widely used ImageNet database, but the team’s Ferdinand Loesch pointed out that others can be added very easily with 100 images to train with. As for the upfront cost, the U.K. offers a 500-pound grant to visually-impaired people for this sort of thing, and they engineered the 360-degree ceiling-mounted camera to minimize the number needed to cover the home. Caeli noted that the nebulizer, which really is a medical device in its own right, is capable of being sold and promoted on its own, perhaps licensed to medical device manufacturers. There are other smart masks coming out, but he had a pretty low opinion of them (not strange in a competitor but there isn’t some big market leader they need to dethrone). He also pointed out that in the target market of India (from which they plan to expand later) isn’t as difficult to get insurance to cover this kind of thing. While these are early-stage companies, they aren’t hobbies — though admittedly many of their founders are working on them between classes. I wouldn’t be surprised to hear more about them and others from Imagine Cup pulling in funding and hiring in the next year.
At home on the road: Stay Alfred loaded a party bus to bring its Spokane startup energy to Seattle

At home on the road: Stay Alfred loaded a party bus to bring its Spokane startup energy to Seattle

1:57pm, 3rd May, 2019
The Stay Alfred team didn’t win in the Next Tech Titan category at the GeekWire Awards, but they were happy to take the stage afterward at Seattle’s Museum of Pop Culture. (GeekWire Photo / Kevin Lisota) Twenty-six people loaded onto a party bus that left Spokane, Wash., at 10 a.m. on Wednesday with three cases of beer and a professional driver. The destination? Seattle, and the . The team from , a Spokane-based startup transforming the hospitality business, wasn’t just hard to miss Thursday night because they were all wearing matching and quintessentially Northwest flannel shirts. They were also wearing ear-to-ear grins as if they were crashing a big-city party. “This is a big deal for us,” said Jordan Allen, founder and CEO of the 8-year-old company. “For some of the other folks here, maybe they’ve done this before, but for a Spokane company to be invited to this, this is a once-in-a-lifetime opportunity for us to join the likes of some of the companies that are here. So we are thrilled.” Stay Alfred, No. 48 on the index of Pacific Northwest startups, certainly earned its place at the event and as a nominee in the Next Tech Titan category, which was ultimately won by pet-sitting juggernaut Rover. The company, which operates upscale apartments for travelers in prime downtown locations, has been “growing like wildfire,” according to Allen, raising $62 million to date and expanding to 32 cities across the U.S. They have their sights set on Europe, next. On the bus ride over to Seattle, the day before the Awards, Allen shared a selfie of his team, beers in hand, as they made the 5-hour trek west across Washington. Stay Alfred CEO Jordan Allen and his team on a bus traveling from Spokane, Wash., to Seattle this week for the GeekWire Awards. (Photo courtesy of Jordan Allen) The bus journey fell on Steve Helmbrecht’s first day on the job, as Stay Alfred’s new president. After joining from a private investment company, he knew the trip would be part of his initial experience with the startup, and he was looking forward to it. “During [the drive] Jordan and I made two investment banking calls and then I had a couple of beers before noon with the crew,” Helmbrecht told GeekWire at the Museum of Pop Culture, site of Thursday’s Awards. “It was great. I already love it.” Helmbrecht said that Stay Alfred had a board meeting in Seattle during the day and then geared up for the big event later on. “What I really like about it is not only did Jordan bring over the executive team, he brought the five longest serving members of the company to come over, including employee No. 1,” Helmbrecht said. “They get to share this tonight. We’re honored to just be even nominated. We feel really good about it.” Stay Alfred employees arrive at MoPOP and walk the pink carpet. (GeekWire Photo / Kevin Lisota) Stay Alfred leases hundreds of apartments and condos to short-term travelers in its bid to get ahead of the likes of Airbnb. Allen believes tourists and business travelers have outgrown that 10-year-old company and now, with families in tow, are looking for a consistent guest experience that still comes with a unique, boutique-hotel-style setting. Part of its plan is to take over entire floors or buildings so as to control guest amenities. “We’re really forming an army of people that are excited about changing what the future of hospitality looks like and multifamily real estate,” Allen said. In Seattle, Stay Alfred and the team took advantage of that this week, which Allen said illustrates just what their mission is. “We had a pre-funk in one of the buildings,” he said. “That’s why our model exists — 10 people in the living room having a great time, we’re able to hang out versus being scattered across 10 hotel rooms. And it was just super cool, to have beer in the fridge and have appetizers out for all the employees and stuff. It was awesome.” A Stay Alfred property on First Avenue in downtown Seattle offers guests access to this swimming pool. (Stay Alfred Photo) With 1,000 people in attendance at the Awards, from some of the most successful, innovative and fastest growing companies in the Seattle area, the flannel-clad Stay Alfred team mixed and mingled and perhaps tried to do a little recruiting for anyone who might want to jump ship and head to the other side of the state. Allen’s pitch was pretty impressive. “We’re a big deal in Spokane, we’re a big fish in a small pond,” he said. “If we were in Seattle maybe we’d be the 20th coolest company. But it has a lot of advantages because we can get to recruit the best of the best in Spokane. There’s close to a million people in the overall metropolitan area, so there’s a lot of really talented people there. “Spokane is the greatest place to live, especially once you have a family and kids,” Allen added. “You can buy a really, really nice house for what you can buy a parking space in Seattle for. It’s a 37-minute flight back and forth, and it’s really cheap to do. If you’re into the outdoors, there’s 10 ski mountains and 75 lakes within an hour, so it’s a pretty attractive place to live.” As good as he made Spokane sound for the business he has been building, and for the team he bused over with, Allen was clearly feeding off the Seattle energy Thursday night as he made his way around MoPOP. “I really can’t say enough, for our team to be able to come over here … we don’t have events like this in Spokane for the startup community,” he said. “Everybody’s so damn excited they can’t even see straight.”
Seattle startup Spruce Up raises $3M for AI-powered home shopping platform

Seattle startup Spruce Up raises $3M for AI-powered home shopping platform

7:24pm, 2nd May, 2019
Spruce Up CEO Mia Lewin. (Spruce Up Photo) has some new spending money. The high-tech home shopping startup just closed a $3 million seed round, bringing its total funding to $4.5 million. New York investment firm Two Sigma Ventures led the round. Other investors include Madrona Venture Group, Female Founders Fund, Alumni Ventures Group, and Peterson Ventures. Spruce Up uses artificial intelligence to recommend home products from a catalog of more than 25,000 items curated by home stylists. Shoppers fill out an interactive quiz to gauge their taste and then receive curated suggestions from designers. “With this seed round, we are doubling down on AI powering every aspect of our product and operations,” Spruce Up CEO Mia Lewin said in a statement. The new funding will also help Spruce Up grow its engineering and data science teams. The startup currently has eight full-time employees and nine part-time stylists. Two Sigma Ventures’ Dan Abelon will join Spruce Up’s board of directors as part of the deal. “We believe AI-powered personalization is the future of e-commerce, and Spruce Up is addressing a multi-billion dollar market and significant pain point for consumers today stuck in eternal scroll,” Abelon said in a statement. Spruce Up is a spin out of Madrona Venture Labs, the venture capital firm’s in-house startup studio. The startup’s co-founders are technology and interior design veterans. Lewin is a former eBay executive who founded several design studios before joining Madrona Venture Labs as CEO-in-residence. Her co-founder Mike Dierken previously held leadership roles at Amazon and McKinsey & Co.
Spy on your smart home with this open source research tool

Spy on your smart home with this open source research tool

6:41am, 13th April, 2019
Researchers at have built a web app that lets you (and them) spy on your smart home devices to see what they’re up to. The open source tool, called IoT Inspector, is available for download . (Currently it’s Mac OS only, with a wait list for Windows or Linux.) In a about the effort the researchers write that their aim is to offer a simple tool for consumers to analyze the network traffic of their Internet connected gizmos. The basic idea is to help people see whether devices such as smart speakers or wi-fi enabled robot vacuum cleaners are sharing their data with third parties. (Or indeed how much snitching their gadgets are doing.) Testing the IoT Inspector tool in their lab the researchers say they found a Chromecast device constantly contacting Google’s servers even when not in active use. A Geeni smart bulb was also found to be constantly communicating with the cloud — sending/receiving traffic via a URL (tuyaus.com) that’s operated by a China-based company with a platform which controls IoT devices. There are other ways to track devices like this — such as setting up a wireless hotspot to sniff IoT traffic using a packet analyzer like WireShark. But the level of technical expertise required makes them difficult for plenty of consumers. Whereas the researchers say their web app doesn’t require any special hardware or complicated set-up so it sounds easier than trying to go packet sniffing your devices yourself. (, which got an early look at the tool, describes it as “incredibly easy to install and use”.) One wrinkle: The web app doesn’t work with Safari; requiring either Firefox or Google Chrome (or a Chromium-based browser) to work. The main caveat is that the team at Princeton do want to use the gathered data to feed IoT research — so users of the tool will be contributing to efforts to study smart home devices. The title of their research project is Identifying Privacy, Security, and Performance Risks of Consumer IoT Devices. The listed principle investigators are professor Nick Feamster and PhD student Danny Yuxing Huang at the university’s Computer Science department. The Princeton team says it intends to study privacy and security risks and network performance risks of IoT devices. But they also note they may share the full dataset with other non-Princeton researchers after a standard research ethics approval process. So users of IoT Inspector will be participating in at least one research project. (Though the tool also lets you delete any collected data — per device or per account.) “With IoT Inspector, we are the first in the research community to produce an open-source, anonymized dataset of actual IoT network traffic, where the identity of each device is labelled,” the researchers write. “We hope to invite any academic researchers to collaborate with us — e.g., to analyze the data or to improve the data collection — and advance our knowledge on IoT security, privacy, and other related fields (e.g., network performance).” They have produced an extensive which anyone thinking about running the tool should definitely read before getting involved with a piece of software that’s explicitly designed to spy on your network traffic. (tl;dr, they’re using ARP-spoofing to intercept traffic data — a technique they warn may slow your network, in addition to the risk of their software being buggy.) The dataset that’s being harvesting by the traffic analyzer tool is anonymized and the researchers specify they’re not gathering any public-facing IP addresses or locations. But there are still some privacy risks — such as if you have smart home devices you’ve named using your real name. So, again, do read the FAQ carefully if you want to participate. For each IoT device on a network the tool collects multiple data-points and sends them back to servers at Princeton University — including DNS requests and responses; destination IP addresses and ports; hashed MAC addresses; aggregated traffic statistics; TLS client handshakes; and device manufacturers. The tool has been designed not to track computers, tablets and smartphones by default, given the study focus on smart home gizmos. Users can also manually exclude individual smart devices from being tracked if they’re able to power them down during set up or by specifying their MAC address. Up to 50 smart devices can be tracked on the network where IoT Inspector is running. Anyone with more than 50 devices is asked to contact the researchers to ask for an increase to that limit. The project team has produced a video showing how to install the app on Mac: