HUSPI

HUSPI’s role was to create a mobile app from scratch with AR features. The project was under strict deadlines due to the event’s scheduled date. We’ve worked closely with the UN Women and HeForShe team to take pictures of the artwork, integrate video of the speakers, and publish the app on the Apple app store just in time (which also was perfect just before the COVID-19 quarantine measures came into force.)

We have used Unity 3D for the development of the app.

Download the app from the app store: https://apps.apple.com/ua/app/heforshe-arts-week/id1498232245

Contact us if you want a similar app: https://huspi.com/contacts/

Execution

For this project, considering the potential high-load and machine learning features, we decided to use Google Cloud Platform, Docker, Python, Flask, Tensorflow, Keras, Jupyter, React.js and Polyglot NLP pipeline.

Analysis: 

We have analyzed the dataset with the publications from the website for the following criteria: View analysis correlation on two criteria: 2 hours after posting the piece and 24 hours after posting the piece, TF-IDF analysis to determine the importance of the specific words to a document in a corpus, LDA topic modeling to round up the relevant tag keywords.

As a result, we have constructed a correlation matrix that illustrates the dependence of these factors on the success rate of the headline. The graph includes the correlations between the publication time (2 and 24 hours after posting), entity count (including person, organization, and location count), title length, polarity, digits, and sentiment score.

Outcome

The solution we got in the result became a foundation for the prototype of Headline Success Prediction Interface: the prototype works on a predictive model based on the AutoML predictions model and custom ML model.

Our client was happy with the way the product turned out and for us, it was a great opportunity to show our experience in the AI/ML technology. Win-win!

Execution: In this project, HUSPI needed to create a cross-platform mobile app with a secure database connection. For these tasks, we have used Xamarin (Android, iOS, and UWP) for mobile development and MySQL and C# for database integration.

Outcome: The project is currently under development, but it is promised to be quite helpful in terms of MedTech. Stay in touch to see the updates.

Need a data analytics & visualization tool similar to this one? Send us a message to [email protected]

TECHNOLOGY:

• Angular 4, Java Spring, REST API, HTML5, MySQL, Oracle;
• Docker, Apache Tomcat, TeamCity, CI, Windows Server 2016.

RESULT:

On production at a large steel factory.

• Created and integrated several databases (including a database of homeopathic medications as well as various diseases and treatment results studies)
• Implemented data mining capabilities based on the patients' input
• Added the fuzzy logic algorithm and machine learning technologies to the system
• Developed the backend and frontend of the project

Due to the self-educating feature, the system, once launched, would continuously update its records with newer findings, making the future patients' treatments more precise.

Execution

From the technical point, we have opted to use Python as our main machine learning language. The additional technologies included HTML, CSS, and Bootstrap.

Outcome

The project is still under development and currently is being tested by the medical staff.

Need a project with AI/ML features integration as well? Contact us at [email protected]

Execution: We used MySQL, Doctrine, Symfony, jQuery, RabbitMQ, NodeJS, Gearman, Ember.js.

Outcome: The project is currently undergoing development. The website and the mobile app will be available in three languages (Ukrainian, English, and Russian). Both the web and mobile apps will offer tools for communication, online payments, and route building.

Want a crowdshipping / logistics service platform like this? Contact us at [email protected].

Execution:

We created several interconnected databases that collect information about the client’s behavior and use it to make his or her Internet experience more effective.

We integrated this platform with a video portal project in order to stimulate user activities and use the collected data to make the video portal digital experience more straightforward (for example, by offering the customer only the movies s/he would like to watch based on the previous movies.)

In terms of technologies used, we relied on Cassandra, CSS, HTML, Spring, VertX, and Java.

Outcome:

Tailoring digital experiences to each given customer is a sure way for numerous companies to motivate their clients. With ABC Loyalty Program, not only they could get their personalized content, but they also earn digital currency and purchase various items.

Would you like a gamification & customer motivation system like this? Contact us at [email protected]

Execution

HUSPI conducted a complex audit of the IT systems and business processes. One of the major tasks for us was to write down technical and functional requirements for the existing IT system optimization for further implementation.

Outcome

The websites of the corporation were created with the help of PHP / Laravel and integrated with third-party service providers using the REST API. 

For the corporation's ERP system, we decided to use Microsoft Navision since it could seamlessly integrate with Power BI by Microsoft for real-time analytics and streamlined decision-making processes across the companies and departments. 

We have transferred a part of the business to the new IT platform - 1C - to accelerate the business processes and improve data quality. 1C was used both for accounting and financial purposes as well as POS software.

Need an e-commerce and database integration solution like this? Contact us at [email protected]

While we were working on the main part of the mobile app, the requirements expanded to add another feature: the ability to close business deals within the app.

Having analyzed the requirements, HUSPI developers used the following technologies for development and DevOps support:

• Ionic 2, Node.JS, REST Web API, HTML5, MySQL;
• Docker, Apache Tomcat, TeamCity, CI, Linux Debian.

Need a mobile app like this? Contact us at [email protected]

We also needed to create a dashboard for patients and doctors, where they can see recorded videos of themselves for further work. 

The project's sensors are non-invasive, which means that all data is coming from video files and biometric parameters. Specially developed light bulb receives the parameters about emotions in real-time and its color reflects the state of the person's nervous system.

Therefore, there were several tasks before HUSPI: 

• Create the architecture and think through all the data processing, storage, and analysis rules in order to avoid crashes and mislabeling
• Develop the dashboard with the incoming data
• Create separate user permission rights for doctors, administrative personnel, and users
• Create all light bulb settings and integrate it with the dashboard's backend

For these tasks, we have used the following technologies: React, Redux, Core UI, Node.js, Noble, PostgreSQL.

This technology helps to accurately translate physiological information into useful for business metrics: engagement, attention, stress, sentiment, connectedness, etc.

Need a MedTech solution like this? Contact us at [email protected]

Another interesting technical challenge for us in this project was the fact that the games had to be controlled using special Bi-Manu Trainer gloves. Special sensors installed in them can track patient's movements and therapists can understand how to tailor the rehab program to a particular person's needs. Therefore, the project was part-IoT due to the gloves' sensors integration.

Our primary task was to develop a set of eight games according to the technical requirements presented by our client. Since, as we mentioned above, the main users are people with cognitive impairment, we had to pay special attention to the user interface and experience.

It had to be light, not overloaded with information, and it always had to provide ample descriptions as to what to do next. The games are connected to the reporting system and track user actions to see whether the patient's mental health is improving.

Need a MedTech solution like this? Contact us at [email protected]

Having explored the technical requirements and expectations of our client, we have opted to use the following technologies and frameworks:

• Web: Angular 4, ASP.NET Web API, HTML5, Telerik, MSSQL
• Databases: PowerBI, Azure, MSSQL

As a result of our diligent work, the efficiency of the EasyPay resource increased 4 times in terms of high-load management. We also have simplified customer experience processes thanks to the complete redesign of the website.

Need a FinTech solution? Contact us at [email protected]

• Improving the user interface and experience
• Making the visual presentation of the data more digestible for the user
• Optimizing the existing services 

The goal was to create clear navigation to all available resources to the user, display relevant information, and provide requested services. Special attention was also dedicated to search forms and product filters.

Having examined the list of requirements, our developers' team have worked on such features:

• List of goods for a given segment, including novelties and what's expected at the stores
• List of places where you can purchase the official equipment, including links to those sales' sources
• The useful content area with a blog section, company news, and catalogs that directly help raise customers' loyalty as well as user engagement with the website
• Various loyalty programs for the end customers and shares in sales points

We created a completely renovated website and a convenient user interface. As a result of our work, we have helped to represent our customer as a modern innovative company and optimized the sales process.

Need an e-commerce website like this? Contact us at [email protected]

We've brainstormed with our Sales & Business Development departments to understand the needs and expectations of those, who have to deal with a lot of emails daily. As a result, SAM was created with the following features:

1. It learns from your activity in email - SAM’s built on the principles of machine learning and has customizable filters.
2. It helps to stay on top of things - you no longer have to worry about missing an email that would be of great help for your business or company. Smart Assistant for eMail integrates seamlessly with a messenger of your choice (we use Telegram) to manage your incoming emails and notify you about the ones you've deemed important.
3. It streamlines your business processes and teamwork due to additional collaboration opportunities.

Our team of developers can help with customization and integration of SAM to tailor the software to your business needs. 

• Personalized filters and actions, based on the type of your business and your role as a business owner, manager, or salesperson.
• Integration with Gmail and other email providers.
• Custom notifications integrated with Telegram, Slack, and other messengers - whichever you use for your business needs.

Need an AI solution like this? Contact us at [email protected]