//Cloud notes from my desk -Maheshk

"Fortunate are those who take the first steps.” ― Paulo Coelho

[#ImagineCup] 2017 World Finalists Project tech visit

Today I had some little time in middle of vacation to check all 54 #ImagineCup finalist projects ideas and their technology stack to see a trend. It took me 3-4 hours to go through all of them but at the end I felt like someone valued 50+ startup ideas to present score for each of them. I personally evaluated each with some score to compare tomorrows decision to validate my score. As expected, glad to see majority of them are using ML, AI, Cognitive Services and Deep Learning for recognizing or predicting the outcome based on some real time data or past data. Very inspiring and interesting to see current generation students idea of using AI for predicting diseases to live stock pregnancy identification,  and also hoax news finder tool. Glad to see variety of use cases were attempted with AI and ML tech things to solve.

I have added “Technology stack” & “Domain” column on top of the final list for easy reference. Hope it will give an idea for some one who is planning for next similar event Smile.


S.No Title Purpose Country Technology stack Domain area
1 Nash reduce the response times in natural disasters. Argentina ML, AI, Drones, DL Disaster recovery
2 SourceLink reconnects individuals with the producers of their food Australia augmented reality app, Hololens, Image recognition FMCG
3 Team Parasitica analyzes a patient’s sputum, blood and stool samples for screening of TB and other diseases Bangladesh AI, medical diagnosis app Medical diagnosis
4 Scrawlless Web-portal Scrawlless is a platform, which helps kids with cerebral palsy, problems of fine motor skills to do fully do their school tasks. Belarus Web portal, special keyboard to overcome the challenge Disability
5 Knowlead social network learning platform, p2p learning Bosnia .Net Core 2.0 for backend and Angular 4 for frontend Education
6 UpFish monitors and improvise fish production Brazil IoT Fish farming
7 Bubu Digital microcontroller and sensors in baby pacifier records oral measurement of body temperature, sending this data to mobile devices through a wireless connection Brazil IoT, Mobile app Medical record management
8 NeuroGate analyzes gait patterns and diagnose various neurodegenerative diseases Canada Microsoft’s Kinect, ML and Deep Learning Medical diagnosis
9 Karate Manatees online multiplayer team based sports game Canada portal Gaming
10 Surgical Assistant it provides a medical image processing platform and VR applications to view 3D models China Azure ML, Hololens, Medical diagnosis
11 X.GLU hardware and software instruments to allow diabetic patients to cope with the disease better Czech Republic Azure, credit card size hardware, NFc, Bluetooth Medical diagnosis
12 OverSkill targets seven core abilities and is designed to train the mind and the body simultaneously through the use of mixed reality France Mixed Reality Self improvement
13 SmartCase suitcase tracking, alerting Germany NA Material tracking(logistics)
1 koicode helps people to learn programming in an intuitive wa Germany Web portal Education
2 OsteoMentor holistic solution for people suffering from osteoporosis (also known as silent disease) Greece NA Personal Hygiene
3 Sense+ cognitive application that enables the visually impaired to see, explore, notice and search with their ears Hong Kong Microsoft Cognitive Services APIs and Microsoft Azure Disability
4 GlovEye gloves for smart devices which let blind and partially sighted people perceive printed text as Braille Hungary Microsoft AI Disability
5 3alchemists provide quality health care to Alzheimer’s patients India IOT, DL, Raspberry PI, ML Medical diagnosis
6 PocketConfident AI first virtual coach powered by Artificial Intelligence India Mobile app Self improvement
7 Negative Time “Content Holmes” an AI app that comes complete with a profanity filter, URL blocker, depression detection, productivity sessions and your own personal detective Content Holmes. India AI, app Online safety for kids
8 CIMOL web based app “Hoax Analyzer” aims to combat the proliferation of “fake news” Indonesia ML, Cognitive Services, DL, web based Media
9 NeuroVoice converts an input voice into another person’s voice- voice to voice conversion Japan Deep learning Speech
1 TITAMAS a smart white cane device for visually impaired Japan image recognition disability
2 DocStroke provide the cheap technique to determine the risks of stroke using ocular image processing and machine learning Jordon ocular image processing and machine learning Medical diagnosis
3 En#l-Guard windows application designed to prevent and alleviate Computer Vision Syndrome(CVS Korea ML, Windows app Self improvement
4 Bl!nk Feedback for speech or presentation Lebonon NA Self improvement
5 Eranoi Realtime water quality recording Mexico IOT Water
6 e-park Parking space monitoring Morocco Mobile app and web Transportation
7 Echo Innovators monitors live stock through a neck band Nepal Azure ML, AI, cloud and IOT Live stock
8 GroupCram aims to address these problems by giving students a platform to collaborate exam answers for everyone’s benefit. New Zealand NA Education
9 Beta Team ‘Bee’ is an app that is connected with Beacons technology for retail shops Oman Beacon technology Retail
10 Opticode lets these people with eye disorders ‘see’ their surroundings through the power of words. Philippines Computer Vision API will be used to analyze the information of an object and parse texts from reading materials through OCR technology; Emotion API will be used to detect people’s facial expressions; Face API will be used to recognize human faces and predict their age and gender; Bing Search and Translator will be used to translate text from one language to another and convert it to speech. Disability
11 Idea hunters advanced biomedical textronix suites for infants. Poland • smart clothing – a textile integrated sensors • mobile app – responsible for sensor data acquisition, aggregation and child health state recognition • Cloud-based analytical services and web-portal – delivering advanced disabilities and disease recognition mechanisms and a users’ medical knowledgebase Medical diagnosis
12 TaleShip ability to get together in a room and write a story in realtime, Puerto Rico Azure (hosting and advanced AI APIs), Django, Django Channels for realtime communication, ReactJS for the game client, Redis, PostgreSQL Colloborative content writing
13 WaCoMo nteractive visualisation of the water consumption happening at different outlets in a property Qatar NA Environment – water
1 deTpression detect the depression, but also monitor it. It allows the doctor to monitor how the disease evolves Romania a small box that encompasses raspberry pi, an external battery, camera and microphone, records the data in a database and passed through a neural network to get the results. The results will be displayed in an eye-catching web interface using a lot of visual representations to have a better understanding of the result. The final predictive analysis is implemented using Microsoft Azure Machine Learning service. Technologies used: Cognitive Services API’s are used as follows: Speaker API – to identify if the current speaker is known and proceed accordingly Emotion API – to detect emotion on the recognized face Face API – to identify the faces in the current frame Text Analytics API – to detect the level of sadness in the transcripts of the subject’s voic Medical diagnosis
2 Boremeter determine which parts of the lecture were boring from the video-stream of the audience. It uses it’s own neural network to detect whether a person is listening or not, and can handle videos with quite large number of faces Russia computer vision algorithms and neural networks People
3 UTV beautiful and interactive Google for articles Russia NA Content
4 Evermind system of driving under the influence prevention Russia Microsoft Azure platform virtual machines and Microsoft Face API service
5 Heart Sound data will go through a series of signal processing and machine learning so that it would lessen the workload of the doctors to go through all the data to check for abnormality singapore ML Medical diagnosis
6 TeamTitans aims at the kids around the world, who are Asthma Patients and it gives a perfect motivation for the kids to carry out proper breathing practices and keep on using the inhalers accordingly. Sri Lanka Mobile game Medical, game
7 Med x Up It is a real time kidney monitoring system Taiwan NA Medical diagnosis
8 Welse digital wellness platform with a point-of-care testing device Thailand NA Medical diagnosis
9 Green Jam aims to turn recycling into a habit rather than a mandated task for citizens of the future UAE Machine Learning techniques to identify the item, and then sorts it by the use of basic mechanical motors Environment
10 SEAT aims to improve the learning and teaching experience in programming course UK online dashboard and a Visual Studio Code extension Education
11 Donaco wants to use recommendation systems to bring contextualised donations UK Online recommendation Charity
12 KSF.LLC ROOT users can enjoy virtual and real farming experience, educational simulation and professional assistance to grow their own crops through its gamified interface UK IOT Farming
13 Pocket Sized Hands Virtual Reality multiplayer stealth shooter, currently being developed for the HTC Vive UK Gaming Gaming
1 Farmalytics Farmalytics seeks to enable farmers to make data-driven decisions in their daily farming practices US Mobile and Web Farming
2 PulsePal PulsePal is a SaaS API that makes it really easy for telemedicine companies to incorporate cutting-edge advancements in biotelemetry into their own products. With a 15 second video of a patient’s face we can measure their heart rate and heart rate variability within 3.5 BPM US ml SaaS API Medical diagnosis
3 Brazilian Student Association @ Stanford Whenever a major bill or resolution is voted on in Congress, the users of our mobile application receive a notification which directs them to information about their representative’s specific vote. Users, at the touch of a button, can register their approval or disapproval of that vote US App Politics
4 Orai help you become a better speake US deep-learning technologies Self improvement
5 Fluency peer-to-peer language learning web application that connects students from around the world and matches two users who wish to become more fluent in each other’s native languages US NA People
6 Oculogx vision of transforming the logistics and supply chain industry by applying revolutionary new technology traditional problems. Our first product is PickAR, a mixed reality application that runs on the Microsoft HoloLens which optimizes the process of order picking in warehouses US VR, HoloLens Logistics



You can watch the final result from here a special webcast at 9 a.m. PDT on Thursday, July 27. Ref>> https://blogs.microsoft.com/blog/2017/06/14/tune-imagine-cup-july-27-see-team-wins-200000-prizes/

HTH, drop a line of comment if you find this useful. I will be happy to assist if you have some use cases wanted to run with me or get clarified.

Best wishes all.


Update (7/27):-
Congratulation #ImagineCup Winners in order #X.GLU #Oculogx #Nash #NeuroGate

I. Team “X.GLU” from Czech Republic won the 2017 Imagine Cup.
>>>X.GLU’s project is a combination hardware and Microsoft Azure cloud solution designed to help diabetics better cope with the disease’s symptoms

II. Team Oculogx —-> mixed reality app that uses HoloLens and Microsoft Azure to improve the process and experience for locating items in large warehouses.

III. Team Nash —> RESCUE, a Microsoft Azure-powered platform that uses drones to reduce response times during natural disasters

IV. Team NeuroGate, which created a solution that uses Microsoft Kinect motion data and machine learning to analyze gait patterns and diagnose potential neurodegenerative diseases.

2017-07-26 Posted by | Uncategorized | | Leave a comment

[Azure Service Fabric] Five steps to achieve Event aggregation and collection using EventFlow in Service Fabric

Monitoring and diagnostic are critical part in application development for diagnosing issue at production or development time. It helps one to easily identify any application issue, h/w issue and performance data to guide scope for improvement. It has 3 part workflow starts with 1) Event Generation 2) Event Aggregation 3) Analysis.

1) Event Generation –> creation and generation of events & logs. Logs could be of infra level events(anything from the cluster) or application level events (from the apps and services).

2) Event Aggregation –> generated events needs to be collated and aggregated before they can be displayed

3) Analysis –> visualized in some format

Once we decide the log provider, the next phase is aggregation. In Service Fabric, the event aggregation can be achieved by using (a) Azure Diagnostic logs (agent installed on VM’s) or (b) EventFlow (in process log collection).

Agent based log collection is a good option if our event source and destination does not change and have one to one mapping. Any change would require cluster level update which is sometime tedious and time consuming. In this type, the logs get tanked in storage and then goes to display phase.

But in case of EventFlow, in process logs are directly thrown to a remote service visualizer. Changing the data destination doesn’t require any cluster level changes as like in agent way update. Anytime we can change the data destination path from this file eventFlowConfig.json. Depends on the criticality we can have both if required. However, Azure diagnostics logs are recommended for mostly infra level log collection where as EventFlow suggested for Application level logs. The last step is Event Analysis where we analysis and visualize the incoming data. Azure Service fabric has better integration support for OMS and Application Insights.

In this article, let us see how one can easily use EventFlow in their Service Fabric Stateful application in 5 steps.

Step1:- Let say, create a new Service Fabric Project by selecting “Stateful Service” application. Pls change the .NET version of the project to 4.6 and above.

Step2:- Right click and add the following nuget packages. Search for “Diagnostics.EventFlow” and then add the following packages. 



Step3:- Update the eventflowconfig.json file as below. Event Source class uses the Json file to send the data. This file needs to be modified to capture data or configure to desired destination.


Step4: Update the “ServiceEventSource.cs” class.  We need a name of Service’s ServiceEventSource is the value of the attribute set for this class.  


Step5:- Instantiate the EventFlow pipeline in our service startup code and start writing the service message.



Deploy the application and confirm all green and no issue with deployment or any dependency issue.


To verify the trace logs, you can log into portal.azure.com > your_application insights > search and refresh (allow few mins to see the data flowing here )


Reference article:-



2017-07-11 Posted by | .NET, Azure Dev, C#, LogCollection, ServiceFabric, VS2017 | | Leave a comment


%d bloggers like this: