Utku Günay Acer
Research Subjects
Research Interests
Utku Günay Acer has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
Fahim Kawsar
TU Delft
14 shared publicationsClaudio Forlivesi
Nokia Bell Labs
8 shared publicationsAfra Mashhadi
Nokia Bell Labs
4 shared publicationsAlhussein A. Abouzeid
Electrical, Computer & Systems Engineering Department, Rensselaer Polytechnic Institute, 110 8th Street, Troy, NY, 1280, USA
4 shared publications- Chulhong Min
Nokia Bell Labs, Cambridge, U.K.
4 shared publications - Fahim Kawsar
University of Glasgow
4 shared publications
Latest Publications
- 29 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (10) , 9319-9333
Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables
The advent of tiny artificial intelligence (AI) accelerators enables AI to run at the extreme edge, offering reduced latency, lower power cost, and improved privacy. When integrated into wearable devices, these accelerators open exciting opportunities, allowing various AI apps to run directly on the body. We present Synergy that provides AI apps with best-effort performance via system-driven holistic collaboration over AI accelerator-equipped wearables. To achieve this, Synergy provides device-agnostic programming interfaces to AI apps, giving the system visibility and controllability over the app's resource use. Then, Synergy maximizes the inference throughput of concurrent AI models by creating various execution plans for each app considering AI accelerator availability and intelligently selecting the best set of execution plans. Synergy further improves throughput by leveraging parallelization opportunities over multiple computation units. Our evaluations with 7 baselines and 8 models demonstrate that, on average, Synergy achieves a 23.0× improvement in throughput, while reducing latency by 73.9% and power consumption by 15.8%, compared to the baselines.
- 29 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (10) , 9319-9333
Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables
The advent of tiny artificial intelligence (AI) accelerators enables AI to run at the extreme edge, offering reduced latency, lower power cost, and improved privacy. When integrated into wearable devices, these accelerators open exciting opportunities, allowing various AI apps to run directly on the body. We present Synergy that provides AI apps with best-effort performance via system-driven holistic collaboration over AI accelerator-equipped wearables. To achieve this, Synergy provides device-agnostic programming interfaces to AI apps, giving the system visibility and controllability over the app's resource use. Then, Synergy maximizes the inference throughput of concurrent AI models by creating various execution plans for each app considering AI accelerator availability and intelligently selecting the best set of execution plans. Synergy further improves throughput by leveraging parallelization opportunities over multiple computation units. Our evaluations with 7 baselines and 8 models demonstrate that, on average, Synergy achieves a 23.0× improvement in throughput, while reducing latency by 73.9% and power consumption by 15.8%, compared to the baselines.
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (1) , 117-134
Argus: Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart Cameras
Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis. However, existing video analytics systems for multi-camera streams are mostly limited to (i) per-camera processing and aggregation and (ii) workload-agnostic centralized processing architectures. In this paper, we present Argus, a distributed video analytics system with cross-camera collaboration on smart cameras. We identify multi-camera, multi-target tracking as the primary task of multi-camera video analytics and develop a novel technique that avoids redundant, processing-heavy identification tasks by leveraging object-wise spatio-temporal association in the overlapping fields of view across multiple cameras. We further develop a set of techniques to perform these operations across distributed cameras without cloud support at low latency by (i) dynamically ordering the camera and object inspection sequence and (ii) flexibly distributing the workload across smart cameras, taking into account network transmission and heterogeneous computational capacities. Evaluation of three real-world overlapping camera datasets with two Nvidia Jetson devices shows that Argus reduces the number of object identifications and end-to-end latency by up to 7.13× and 2.19× (4.86× and 1.60× compared to the state-of-the-art), while achieving comparable tracking quality.
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (1) , 117-134
Argus: Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart Cameras
Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis. However, existing video analytics systems for multi-camera streams are mostly limited to (i) per-camera processing and aggregation and (ii) workload-agnostic centralized processing architectures. In this paper, we present Argus, a distributed video analytics system with cross-camera collaboration on smart cameras. We identify multi-camera, multi-target tracking as the primary task of multi-camera video analytics and develop a novel technique that avoids redundant, processing-heavy identification tasks by leveraging object-wise spatio-temporal association in the overlapping fields of view across multiple cameras. We further develop a set of techniques to perform these operations across distributed cameras without cloud support at low latency by (i) dynamically ordering the camera and object inspection sequence and (ii) flexibly distributing the workload across smart cameras, taking into account network transmission and heterogeneous computational capacities. Evaluation of three real-world overlapping camera datasets with two Nvidia Jetson devices shows that Argus reduces the number of object identifications and end-to-end latency by up to 7.13× and 2.19× (4.86× and 1.60× compared to the state-of-the-art), while achieving comparable tracking quality.
- Open Access
- 9 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 22 (6) , 1-27
SensiX++: Bringing MLOps and Multi-tenant Model Serving to Sensory Edge Devices
We present SensiX++, a multi-tenant runtime for adaptive model execution with integrated MLOps on edge devices, e.g., a camera, a microphone, or IoT sensors. SensiX++ operates on two fundamental principles: highly modular componentisation to externalise data operations with clear abstractions and document-centric manifestation for system-wide orchestration. First, a data coordinator manages the lifecycle of sensors and serves models with correct data through automated transformations. Next, a resource-aware model server executes multiple models in isolation through model abstraction, pipeline automation, and feature sharing. An adaptive scheduler then orchestrates the best-effort executions of multiple models across heterogeneous accelerators, balancing latency and throughput. Finally, microservices with REST APIs serve synthesised model predictions, system statistics, and continuous deployment. Collectively, these components enable SensiX++ to serve multiple models efficiently with fine-grained control on edge devices while minimising data operation redundancy, managing data and device heterogeneity, and reducing resource contention. We benchmark SensiX++ with 10 different vision and acoustics models across various multi-tenant configurations on different edge accelerators (Jetson AGX and Coral TPU) designed for sensory devices. We report on the overall throughput and quantified benefits of various automation components of SensiX++ and demonstrate its efficacy in significantly reducing operational complexity and lowering the effort to deploy, upgrade, reconfigure, and serve embedded models on edge devices.
- 9 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 22 (6) , 1-27
Open AccessSensiX++: Bringing MLOps and Multi-tenant Model Serving to Sensory Edge Devices
We present SensiX++, a multi-tenant runtime for adaptive model execution with integrated MLOps on edge devices, e.g., a camera, a microphone, or IoT sensors. SensiX++ operates on two fundamental principles: highly modular componentisation to externalise data operations with clear abstractions and document-centric manifestation for system-wide orchestration. First, a data coordinator manages the lifecycle of sensors and serves models with correct data through automated transformations. Next, a resource-aware model server executes multiple models in isolation through model abstraction, pipeline automation, and feature sharing. An adaptive scheduler then orchestrates the best-effort executions of multiple models across heterogeneous accelerators, balancing latency and throughput. Finally, microservices with REST APIs serve synthesised model predictions, system statistics, and continuous deployment. Collectively, these components enable SensiX++ to serve multiple models efficiently with fine-grained control on edge devices while minimising data operation redundancy, managing data and device heterogeneity, and reducing resource contention. We benchmark SensiX++ with 10 different vision and acoustics models across various multi-tenant configurations on different edge accelerators (Jetson AGX and Coral TPU) designed for sensory devices. We report on the overall throughput and quantified benefits of various automation components of SensiX++ and demonstrate its efficacy in significantly reducing operational complexity and lowering the effort to deploy, upgrade, reconfigure, and serve embedded models on edge devices.
- Open Access
- 9 September 2019
- Published by Association for Computing Machinery (ACM)
- p. 1102-1106
The city as a personal assistant
- 9 September 2019
- Published by Association for Computing Machinery (ACM)
- p. 1102-1106
Open AccessThe city as a personal assistant
- Open Access
- 12 June 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-4
On Hyper-local Conversational Agents in Urban Settings
Conversational agents are increasingly becoming digital partners in our everyday computational experiences. Although rich, and fresh in content, these agents are completely oblivious to users' locality beyond geospatial weather and traffic conditions. In this position statement, we envisage a brand-new class of conversational agents that are hyper-local, embedded deeply in a local neighbourhood, e.g., at urban landmarks - providing rich, purposeful, detail, and in some cases playful information relevant to a neighbourhood. By design, these agents are spatially constrained, and one can only interact with them once she is in close vicinity at street-level granularity. Learning from quantitative (n=1992) and qualitative (n=21) studies, we identify a set of information that these agents must accommodate. Finally, we discuss the technical architecture of this class of conversational agents that leverages covert communication channel, edge AI and on-body devices for offering such hyper-local information access.
- 12 June 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessOn Hyper-local Conversational Agents in Urban Settings
Conversational agents are increasingly becoming digital partners in our everyday computational experiences. Although rich, and fresh in content, these agents are completely oblivious to users' locality beyond geospatial weather and traffic conditions. In this position statement, we envisage a brand-new class of conversational agents that are hyper-local, embedded deeply in a local neighbourhood, e.g., at urban landmarks - providing rich, purposeful, detail, and in some cases playful information relevant to a neighbourhood. By design, these agents are spatially constrained, and one can only interact with them once she is in close vicinity at street-level granularity. Learning from quantitative (n=1992) and qualitative (n=21) studies, we identify a set of information that these agents must accommodate. Finally, we discuss the technical architecture of this class of conversational agents that leverages covert communication channel, edge AI and on-body devices for offering such hyper-local information access.
- Open Access
- 10 June 2018
- Published by Association for Computing Machinery (ACM)
- p. 27-32
Mindful interruptions
- 10 June 2018
- Published by Association for Computing Machinery (ACM)
- p. 27-32
Open AccessMindful interruptions
- Open Access
- 10 June 2018
- Published by Association for Computing Machinery (ACM)
- p. 520
On-Wearable AI to Model Human Interruptibility
- 10 June 2018
- Published by Association for Computing Machinery (ACM)
- p. 520
Open AccessOn-Wearable AI to Model Human Interruptibility