Interview with Zahra Ghorrati: creating frameworks for human exercise recognition utilizing wearable sensors

On this interview sequence, we’re assembly a few of the AAAI/SIGAI Doctoral Consortium individuals to seek out out extra about their analysis. Zahra Ghorrati is creating frameworks for human exercise recognition utilizing wearable sensors. We caught up with Zahra to seek out out extra about this analysis, the facets she has discovered most fascinating, and her recommendation for potential PhD college students.

Inform us a bit about your PhD – the place are you finding out, and what’s the subject of your analysis?

I’m pursuing my PhD at Purdue College, the place my dissertation focuses on creating scalable and adaptive deep studying frameworks for human exercise recognition (HAR) utilizing wearable sensors. I used to be drawn to this subject as a result of wearables have the potential to remodel fields like healthcare, aged care, and long-term exercise monitoring. In contrast to video-based recognition, which might elevate privateness considerations and requires mounted digicam setups, wearables are moveable, non-intrusive, and able to steady monitoring, making them ideally suited for capturing exercise knowledge in pure, real-world settings.

The central problem my dissertation addresses is that wearable knowledge is commonly noisy, inconsistent, and unsure, relying on sensor placement, motion artifacts, and system limitations. My objective is to design deep studying fashions that aren’t solely computationally environment friendly and interpretable but additionally strong to the variability of real-world knowledge. In doing so, I purpose to make sure that wearable HAR methods are each sensible and reliable for deployment exterior managed lab environments.

This analysis has been supported by the Polytechnic Summer season Analysis Grant at Purdue. Past my dissertation work, I contribute to the analysis neighborhood as a reviewer for conferences comparable to CoDIT, CTDIAC, and IRC, and I’ve been invited to assessment for AAAI 2026. I used to be additionally concerned in neighborhood constructing, serving as Native Organizer and Security Chair for the twenty fourth Worldwide Convention on Autonomous Brokers and Multiagent Programs (AAMAS 2025), and persevering with as Security Chair for AAMAS 2026.

May you give us an outline of the analysis you’ve carried out to this point throughout your PhD?

To this point, my analysis has centered on creating a hierarchical fuzzy deep neural community that may adapt to numerous human exercise recognition datasets. In my preliminary work, I explored a hierarchical recognition strategy, the place less complicated actions are detected at earlier ranges of the mannequin and extra advanced actions are acknowledged at larger ranges. To reinforce each robustness and interpretability, I built-in fuzzy logic ideas into deep studying, permitting the mannequin to higher deal with uncertainty in real-world sensor knowledge.

A key energy of this mannequin is its simplicity and low computational value, which makes it notably nicely fitted to real-time exercise recognition on wearable units. I’ve rigorously evaluated the framework on a number of benchmark datasets of multivariate time sequence and systematically in contrast its efficiency towards state-of-the-art strategies, the place it has demonstrated each aggressive accuracy and improved interpretability.

Is there a facet of your analysis that has been notably fascinating?

Sure, what excites me most is discovering how completely different approaches could make human exercise recognition each smarter and extra sensible. As an example, integrating fuzzy logic has been fascinating, as a result of it permits the mannequin to seize the pure uncertainty and variability of human motion. As a substitute of forcing inflexible classifications, the system can motive when it comes to levels of confidence, making it extra interpretable and nearer to how people really suppose.

I additionally discover the hierarchical design of my mannequin notably fascinating. Recognizing easy actions first, after which constructing towards extra advanced behaviors, mirrors the best way people typically perceive actions in layers. This construction not solely makes the mannequin environment friendly but additionally supplies insights into how completely different actions relate to at least one one other.

Past methodology, what motivates me is the real-world potential. The truth that these fashions can run effectively on wearables means they may finally assist customized healthcare, aged care, and long run exercise monitoring in folks’s on a regular basis lives. And for the reason that strategies I’m creating apply broadly to time sequence knowledge, their affect might lengthen nicely past HAR, into areas like medical diagnostics, IoT monitoring, and even audio recognition. That sense of each depth and flexibility is what makes the analysis particularly rewarding for me.

What are your plans for constructing in your analysis to this point through the PhD – what facets will you be investigating subsequent?

Transferring ahead, I plan to additional improve the scalability and adaptableness of my framework in order that it might probably successfully deal with massive scale datasets and assist real-time functions. A serious focus will likely be on enhancing each the computational effectivity and interpretability of the mannequin, guaranteeing it isn’t solely highly effective but additionally sensible for deployment in real-world situations.

Whereas my present analysis has centered on human exercise recognition, I’m excited to broaden the scope to the broader area of time sequence classification. I see nice potential in making use of my framework to areas comparable to sound classification, physiological sign evaluation, and different time-dependent domains. This can enable me to display the generalizability and robustness of my strategy throughout numerous functions the place time-based knowledge is vital.

In the long term, my objective is to develop a unified, scalable mannequin for time sequence evaluation that balances adaptability, interpretability, and effectivity. I hope such a framework can function a basis for advancing not solely HAR but additionally a broad vary of healthcare, environmental, and AI-driven functions that require real-time, data-driven decision-making.

What made you need to research AI, and specifically the world of wearables?

My curiosity in wearables started throughout my time in Paris, the place I used to be first launched to the potential of sensor-based monitoring in healthcare. I used to be instantly drawn to how discreet and non-invasive wearables are in comparison with video-based strategies, particularly for functions like aged care and affected person monitoring.

Extra broadly, I’ve at all times been fascinated by AI’s means to interpret advanced knowledge and uncover significant patterns that may improve human well-being. Wearables provided the proper intersection of my pursuits, combining cutting-edge AI strategies with sensible, real-world affect, which naturally led me to focus my analysis on this space.

What recommendation would you give to somebody pondering of doing a PhD within the area?

A PhD in AI calls for each technical experience and resilience. My recommendation can be:

• Keep curious and adaptable, as a result of analysis instructions evolve rapidly, and the flexibility to pivot or discover new concepts is invaluable.
• Examine combining disciplines. AI advantages drastically from insights in fields like psychology, healthcare, and human-computer interplay.
• Most significantly, select an issue you might be really captivated with. That keenness will maintain you thru the inevitable challenges and setbacks of the PhD journey.

Approaching your analysis with curiosity, openness, and real curiosity could make the PhD not only a problem, however a deeply rewarding expertise.

May you inform us an fascinating (non-AI associated) reality about you?

Exterior of analysis, I’m captivated with management and neighborhood constructing. As president of the Purdue Tango Membership, I grew the group from simply 2 college students to over 40 lively members, organized weekly lessons, and hosted massive occasions with internationally acknowledged instructors. Extra importantly, I centered on making a welcoming neighborhood the place college students really feel related and supported. For me, tango is greater than dance, it’s a option to convey folks collectively, bridge cultures, and steadiness the depth of analysis with creativity and pleasure.

I additionally apply these abilities in tutorial management. For instance, I function Native Organizer and Security Chair for the AAMAS 2025 and 2026 conferences, which has given me hands-on expertise managing occasions, coordinating groups, and creating inclusive areas for researchers worldwide.

About Zahra

Zahra Ghorrati is a PhD candidate and instructing assistant at Purdue College, specializing in synthetic intelligence and time sequence classification with functions in human exercise recognition. She earned her undergraduate diploma in Pc Software program Engineering and her grasp’s diploma in Synthetic Intelligence. Her analysis focuses on creating scalable and interpretable fuzzy deep studying fashions for wearable sensor knowledge. She has introduced her work at main worldwide conferences and journals, together with AAMAS, PAAMS, FUZZ-IEEE, IEEE Entry, System and Utilized Comfortable Computing. She has served as a reviewer for CoDIT, CTDIAC, and IRC, and has been invited to assessment for AAAI 2026. Zahra additionally contributes to neighborhood constructing as Native Organizer and Security Chair for AAMAS 2025 and 2026.