<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Daniel Kremerov on Medium]]></title>
        <description><![CDATA[Stories by Daniel Kremerov on Medium]]></description>
        <link>https://medium.com/@danielkremerov?source=rss-398a815cb5a6------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*AG_VEyaU2vgBYAwf.</url>
            <title>Stories by Daniel Kremerov on Medium</title>
            <link>https://medium.com/@danielkremerov?source=rss-398a815cb5a6------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Tue, 17 Nov 2026 21:47:34 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@danielkremerov/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Limitations of Alexa for Telehealth]]></title>
            <link>https://medium.com/@danielkremerov/limitations-of-alexa-for-telehealth-a6f054961705?source=rss-398a815cb5a6------2</link>
            <guid isPermaLink="false">https://medium.com/p/a6f054961705</guid>
            <category><![CDATA[alexa]]></category>
            <dc:creator><![CDATA[Daniel Kremerov]]></dc:creator>
            <pubDate>Fri, 08 Sep 2017 09:55:18 GMT</pubDate>
            <atom:updated>2017-09-10T08:28:45.469Z</atom:updated>
            <content:encoded><![CDATA[<p>This is the last post of the series on Alexa. After discussing development-related topics in the past two posts, this post goes back to the path of the first one. I will look again at the user perspective and share some of the opportunity’s and problems when using Alexa for Telehealth.</p><p>Recall that in the first post I mentioned that Voice Interfaces are a good fit as interaction via Voice is easier for tech-averse seniors with physical limitations. However, not everything is bright about this. There are two limitations that I want to introduce.</p><p>Firstly, from a use case perspective, seniors certainly need extensive reminder functionalities. A logic use case, which I also explored during my project, is to have a web interface for caretakers where they can set custom reminders for medication intake and other activities for the seniors (e.g. their parents). The seniors then get reminded via the Alexa skill. However, this is currently not feasible, as reminders are supported in an insufficient spectrum. The spectrum is only for native Alexa functions. This implies that the senior has to set her reminders via voice, without any possible support through 3rd party applications as the one discussed here. However, improvements are likely for the future.</p><p>Secondly, from a voice recognition perspective, there are still some limitations. Although, Alexa’s Natural language processing is already quite sophisticated while testing my project I realised that is having problems with reacting to different wording. Also, it seems that seniors use less typical wordings and pronunciations. Together with the mentioned technology-averseness, this can easily create frustration. However, also this limitation is likely to improve in the future. Nevertheless, despite some limitations, I believe that Alexa is a good solution for Telehealth.</p><p>I hope you enjoyed reading my blog series!</p><p><strong>About the author:</strong></p><p>I am an entrepreneurially-minded MSc. Computer Science student at University College London. Priorly I studied Business and worked in the consulting and StartUp-sphere. This summer, I have the unique opportunity to dive very deep into the topic of Personal Assistants in Telehealth, fully supported by UCL and NHS Digital UK. I want to give back, so I strive to provide unique insights to my readers, from a technical and non-technical perspective.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=a6f054961705" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Alexa Development — Some Backend bottlenecks]]></title>
            <link>https://medium.com/@danielkremerov/alexa-development-some-backend-bottlenecks-c3f5bdb78e16?source=rss-398a815cb5a6------2</link>
            <guid isPermaLink="false">https://medium.com/p/c3f5bdb78e16</guid>
            <category><![CDATA[aws]]></category>
            <dc:creator><![CDATA[Daniel Kremerov]]></dc:creator>
            <pubDate>Fri, 01 Sep 2017 13:07:27 GMT</pubDate>
            <atom:updated>2017-09-10T08:27:56.180Z</atom:updated>
            <content:encoded><![CDATA[<p>The backend is hosted in Amazon’s Serverless infrastructure using AWS Lambda. This post has some NodeJS specifics, but generally, should apply to other languages such as Java or Python. One can use one of the templates for Alexa skills which support development in the browser. However, more sophisticated skills require additional packages, and that requires the upload of a complete zip file to Lambda. This implies that one needs to set up a good development environment that supports quick iterations. As described in the previous blog post, it is crucial to be able to deploy the application quickly, as currently, the dialogue model requires device testing. Therefore, I recommend using Apex, which deploys your changes to Lambda with one terminal command. Note that when using Apex, to use “exports.handle” for expecution, whereas the standard case is “exports.handler” Make sure to have all your packages installed with npm before deploying. Below some standard code to get going.</p><pre><strong>var </strong>Alexa = require(<strong>&#39;alexa-sdk&#39;</strong>);<br><strong>var </strong>APP_ID = <strong>undefined</strong>;  <em>// </em><strong><em>TODO replace with your app ID </em></strong></pre><pre>exports.<strong>handle </strong>= (<strong>event</strong>, context) =&gt; {<br>    <strong>var </strong>alexa = Alexa.<strong>handler</strong>(<strong>event</strong>, context);<br>    alexa.<strong>APP_ID </strong>= APP_ID;<br>    alexa.<strong>registerHandlers</strong>(handlers);<br>    alexa.<strong>execute</strong>();<br>};<br><br><strong>var </strong>handlers = {<br>    <strong>&#39;LaunchRequest&#39;</strong>: <strong>function </strong>() {<br>            <strong>this</strong>.<strong>emit</strong>(<strong>&#39;:askWithCard&#39;</strong>, welcomeOutput, welcomeReprompt,welcomeUsercardTitle,welcomeUsercardContent);},<br>    <strong>&#39;Unhandled&#39;</strong>: <strong>function</strong>() {<br>        <strong>this</strong>.<strong>emit</strong>(<strong>&#39;:ask&#39;</strong>, <strong>&#39;There was an error, please repeat what you want to do.&#39;</strong>);<br>    }<br>}</pre><p>Another interesting aspect of development is related to the separation of concerns. On the one hand, most of the Alexa prompts are handled in the dialogue model. On the other hand, so far it is still required to handle prompts at the end of intents in the backend, which by definition is not a clean operation of concerns. The reason is that Alexa expects from the developer to define whether the session continues or closes after the intent. This is done using the <a href="https://github.com/alexa/alexa-skills-kit-sdk-for-nodejs">ask, and tell word</a>s, where the names are a bit misleading as ask is not necessarily a question but every prompt that keeps the skill running. Also, another UI element is handled in the backend, namely skill cards. These are visual prompts that the user can see as support through the Alexa mobile app. In my opinion, it would make more sense to handle this in the skill builder interface for a better separation of concerns. Nevertheless, skill cards are a good mechanism to display the user possible next actions. Besides specific account linking skill cards are used for user authentication, which I introduce in the next post.</p><p>Further, an important topic for more sophisticated skills is data persistence. Without a database connection, Alexa can only store data in session variables throughout one session. Given that Alexa is currently a reactive system (e.g. it only replies after the user asks it), many use cases centre around inputting information that is stored and displayed somewhere, which requires a database. A natural choice is to use Amazons DynamoDB as schema-less NoSQL database offers flexibility and one can assume that it works well. From my experience, however, even the Amazon services do not always work as well together as one might expect. Nevertheless, connecting it is quite easy, and a natural identity key is the unique device id of the echo. I recommend setting up a local database copy using Docker and the respective DynamoDB package, as after testing several options, this worked one certainly works best for me. The<a href="https://medium.com/@danielkremerov/limitations-of-alexa-for-telehealth-a6f054961705"> last posts</a> will describe some limitations</p><p><strong>About the author:</strong></p><p>I am an entrepreneurially-minded MSc. Computer Science student at University College London. Priorly I studied Business and worked in the consulting and StartUp-sphere. This summer, I have the unique opportunity to dive very deep into the topic of Personal Assistants in Telehealth, fully supported by UCL and NHS Digital UK. I want to give back, so I strive to provide unique insights to my readers, from a technical and non-technical perspective.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c3f5bdb78e16" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Some tipps on building the core of your Alexa skill — the Interaction Model]]></title>
            <link>https://medium.com/@danielkremerov/some-tipps-on-building-the-core-of-your-alexa-skill-the-interaction-model-631d299c65ab?source=rss-398a815cb5a6------2</link>
            <guid isPermaLink="false">https://medium.com/p/631d299c65ab</guid>
            <category><![CDATA[amazon-echo]]></category>
            <dc:creator><![CDATA[Daniel Kremerov]]></dc:creator>
            <pubDate>Fri, 25 Aug 2017 09:05:49 GMT</pubDate>
            <atom:updated>2017-09-10T08:27:01.237Z</atom:updated>
            <content:encoded><![CDATA[<p>This blog post describes how to set up the interaction mode for a skill with a clear focus on potential problems that I encountered along the way. The next two posts will help you with setting up the backend, consisting of business logic hosted on AWS Lambda and a persistence layer and configuring them with the created Interaction Model.</p><p>During my project, I developed a total of three fully working Alexa skills (and many test-skills along the way). As there is already a lot of advice out there, I want to focus on describing aspects that were problematic for me. Most of the things are not overall complex as Amazon does a good job to simplify developed. However, a big challenge is that the environment grows and evolves at a fast pace. Therefore many recommendations and third party frameworks get outdated quickly, which for me resulted in a lot of trial and error and even some periods of frustration.</p><p>Setting up a basic skill is relatively straight forward and is well documented. After selecting a skill name, it is important to choose an invocation name that is easy to pronounce as a complicated name can be a bottleneck when testing, as Alexa often has trouble to recognise it (although it gets better over time, thanks to “AI inside”). Another thing to watch out for is to select exactly the language that you want to use, so even differentiate between American and British English. Latest at the point when the skill is linked to a Lambda backend, selecting the wrong language will break the whole skill. Once I developed a whole Skill, connected it to the backend, deployed to my Echo Dot, and all Alexa was just saying “Sorry, I don’t know that skill” and the only reason was that my interaction model was build in American instead of British English.</p><p>Next, you are building the core of the skill — the interaction model. Terms like intents, utterances and slots are defined all over the internet, so we skip this part here. Rather it is important to emphasise that currently there are two ways to create an interaction model, either using a basic JSON file or using the new Skill Builder, which is a fancy UI that simplifies the process. I strongly recommend to use the Builder, but keep in mind that most of the documentation online is made for the basic JSON version. This is certainly a tradeoff. Next, to the supportive UI, the big advantage of the Builder is the Dialog model. It allows to handle different dialogue flows inside the Interaction model, whereas with the old version it was necessary to address these in the backend code.</p><p>For instance, if you have an intent that takes in a vital reading (body weight, blood glucose etc.) and the value of this reading, Alexa eventually needs to retrieve two slots, namely type and value. To give the maximum user flexbility, it is important that he can invoke this intent either by saying something like “Take my vitals” or “Take my body weight” or “My body weight is 90kg”. The last prompt, contains all slot values, whereas for the other two in needs to get more information by asking the user something like “Which vital do you want to take?” or “How much is your body weight today?”. Also, Alexa can ask for confirmation either for each slot value or for the total outcome like “So your body weight today is 170kg?”. So to sum up, dynamically asking for slot values and prompting for confirmation can both be handled inside the interaction model when using the new Skillbuilder.</p><p>Also, it is worth mentioning that it is important to provide as many sample utterances as possible for each intent, as when testing it becomes clear that this trains the Alexa AI and makes it comprehend the users of your skill much better. Rather than typing in all utterances by hand, I recommend to create them using Regular Expressions in combination with a third party script such as this <a href="http://alexa-utter-gen.paperplane.io/">one</a>, as this will save you a lot of time when creating a sophisticated interaction model.</p><p>In the <a href="https://medium.com/@danielkremerov/alexa-development-some-backend-bottlenecks-c3f5bdb78e16">next post</a>, I will describe some of the configuration options and explain things to watch out for when creating your backend function and linking it to your skill.</p><p><strong>About the author:</strong><br>I am an entrepreneurially-minded MSc. Computer Science student at University College London. Priorly I studied Business and worked in the consulting and StartUp-sphere. This summer, I have the unique opportunity to dive very deep into the topic of Personal Assistants in Telehealth, fully supported by UCL and NHS Digital UK. I want to give back, so I strive to provide unique insights to my readers, from a technical and non-technical perspective.</p><p>Also, check out my StartUp <a href="http://www.permitly.io/">Permitly</a>. ;)</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=631d299c65ab" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[“Alexa, my heart rate is 200 bpm” — Are you excited?]]></title>
            <link>https://medium.com/@danielkremerov/alexa-my-heart-rate-is-200-bpm-are-you-exited-87b14d0e1100?source=rss-398a815cb5a6------2</link>
            <guid isPermaLink="false">https://medium.com/p/87b14d0e1100</guid>
            <category><![CDATA[alexa]]></category>
            <category><![CDATA[amazon-echo]]></category>
            <category><![CDATA[personal-assistant]]></category>
            <category><![CDATA[telehealth]]></category>
            <category><![CDATA[nhs]]></category>
            <dc:creator><![CDATA[Daniel Kremerov]]></dc:creator>
            <pubDate>Tue, 15 Aug 2017 10:56:14 GMT</pubDate>
            <atom:updated>2017-09-10T08:27:05.659Z</atom:updated>
            <content:encoded><![CDATA[<h3>“Alexa, my heart rate is 200 bpm” — Are you excited? Kickoff blog series on Personal Assistants in Telehealth</h3><p>Over the past two months, I investigated how Personal Assistants (PAs) such as Amazon Alexa and Google Home can provide benefits to Telehealth. A typical use case in distant health is a patient measuring vitals such as body weight or heart rate at home and sending them over to a caretaker or doctor for monitoring. So far, existing solutions mostly rely on visual input from classic notepads and SMS or apps on the patient’s smartphone. Considering that many Telehealth patients are seniors who are technology averse and physically restricted, existing User Interfaces seem neither a natural nor a viable solution.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/561/1*K8pIgKh4o3wuJAjOPKh0aw.png" /></figure><p>Obviously, a voice input is more natural. However, only recent progression in Artificial Intelligence (AI) and Natural Language Processing make it possible to have fluent conversations with the PA, as variations in utterances of the user are recognized and handled.</p><p>Although the project is about a general software architecture that utilizes PAs for Telehealth, the proof of concept centers around one particular PA, namely Amazon Alexa. The three dominant selection factors were the effectiveness of the AI engine, developer-friendliness and installation costs. Whereas Alexa and Google Home score very high on the first two, the competitive advantage of Amazon Alexa is its low setup costs. An Amazon Echo Dot costs only £50, whereas the cheapest Google Alternative is about three times as expensive. Particularly, for distant health, the low hardware costs are crucial, as patients and healthcare providers can be reluctant to high spendings on technology.</p><p>In the next blog posts, I will walk you through different steps of the development process, how I developed and linked an Alexa Skill to existing solutions but also how to develop a standalone product. I also strive to provide non-technical posts that advise on implementing PAs, backed by technical arguments.</p><p>While waiting for my <a href="https://medium.com/@danielkremerov/some-tipps-on-building-the-core-of-your-alexa-skill-the-interaction-model-631d299c65ab">next posts,</a> let me know whether you would set up Alexa for your grandmother!</p><p><strong>About the author:</strong><br>I am an entrepreneurially-minded MSc. Computer Science student at University College London. Priorly I studied Business and worked in the consulting and StartUp-sphere. This summer, I have the unique opportunity to dive very deep into the topic of Personal Assistants in Telehealth, fully supported by UCL and NHS Digital UK. I want to give back, so I strive to provide unique insights to my readers, from a technical and non-technical perspective.</p><p>Also, check out my StartUp <a href="http://www.permitly.io/">Permitly</a>. ;)</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=87b14d0e1100" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>