Shahriar Nirjon
YOU?
Author Swipe
View article: mmCounter: Static People Counting in Dense Indoor Scenarios Using mmWave Radar
mmCounter: Static People Counting in Dense Indoor Scenarios Using mmWave Radar Open
mmWave radars struggle to detect or count individuals in dense, static (non-moving) groups due to limitations in spatial resolution and reliance on movement for detection. We present mmCounter, which accurately counts static people in dens…
View article: mmJoints: Expanding Joint Representations Beyond (x,y,z) in mmWave-Based 3D Pose Estimation
mmJoints: Expanding Joint Representations Beyond (x,y,z) in mmWave-Based 3D Pose Estimation Open
In mmWave-based pose estimation, sparse signals and weak reflections often cause models to infer body joints from statistical priors rather than sensor data. While prior knowledge helps in learning meaningful representations, over-reliance…
View article: Integrating Stakeholder Insights to Inform the Design of AURA – An IoT-Based System Supporting Older Adults with Physical and Cognitive Health Challenges (Preprint)
Integrating Stakeholder Insights to Inform the Design of AURA – An IoT-Based System Supporting Older Adults with Physical and Cognitive Health Challenges (Preprint) Open
View article: Designing AURA: Integrating Stakeholder Insights into an IoT-Based System for Chronic Illness Management (Preprint)
Designing AURA: Integrating Stakeholder Insights into an IoT-Based System for Chronic Illness Management (Preprint) Open
BACKGROUND Chronic illnesses often impair mobility, memory, and daily functioning, creating challenges for both patients and caregivers. Smart Internet of Things (IoT) technologies offer promising solutions by enabling real-time monitorin…
View article: PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches
PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches Open
As large language models (LLMs) increasingly shape the AI landscape, fine-tuning pretrained models has become more popular than in the pre-LLM era for achieving optimal performance in domain-specific tasks. However, pretrained LLMs such as…
View article: Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Tasks
Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Tasks Open
Edge devices, with their widely varying capabilities, support a diverse range of edge AI models. This raises the question: how does an edge model differ from a high-accuracy (base) model for the same task? We introduce XDELTA, a novel expl…
View article: SensEmo: Enabling Affective Learning through Real-time Emotion Recognition with Smartwatches
SensEmo: Enabling Affective Learning through Real-time Emotion Recognition with Smartwatches Open
Recent research has demonstrated the capability of physiological signals to infer both user emotional and attention responses. This presents an opportunity for leveraging widely available physiological sensors in smartwatches, to detect re…
View article: Data Distribution Dynamics in Real-World WiFi-Based Patient Activity Monitoring for Home Healthcare
Data Distribution Dynamics in Real-World WiFi-Based Patient Activity Monitoring for Home Healthcare Open
This paper examines the application of WiFi signals for real-world monitoring of daily activities in home healthcare scenarios. While the state-of-the-art of WiFi-based activity recognition is promising in lab environments, challenges aris…
View article: SoundSieve: Seconds-Long Audio Event Recognition on Intermittently-Powered Systems
SoundSieve: Seconds-Long Audio Event Recognition on Intermittently-Powered Systems Open
A fundamental problem of every intermittently-powered sensing system is that signals acquired by these systems over a longer period in time are also intermittent. As a consequence, these systems fail to capture parts of a longer-duration e…
View article: Amalgamated Intermittent Computing Systems
Amalgamated Intermittent Computing Systems Open
Intermittent computing systems undergo frequent power failure, hindering\nnecessary data sample capture or timely on-device computation. These missing\nsamples and deadlines limit the potential usage of intermittent computing\nsystems in m…
View article: Efficient Multitask Learning on Resource-Constrained Systems
Efficient Multitask Learning on Resource-Constrained Systems Open
We present Antler, which exploits the affinity between all pairs of tasks in a multitask inference system to construct a compact graph representation of the task set and finds an optimal order of execution of the tasks such that the end-to…
View article: CarFi: Rider Localization Using Wi-Fi CSI
CarFi: Rider Localization Using Wi-Fi CSI Open
With the rise of hailing services, people are increasingly relying on shared mobility (e.g., Uber, Lyft) drivers to pick up for transportation. However, such drivers and riders have difficulties finding each other in urban areas as GPS sig…
View article: Sound-Adapter
Sound-Adapter Open
The accuracy of an audio classifier drops when it is trained and tested in different conditions aka domains, e.g., different devices, different environments, or their combinations. Previous works have proposed audio domain adaptation techn…
View article: SmartON: Just-in-Time Active Event Detection on Energy Harvesting Systems
SmartON: Just-in-Time Active Event Detection on Energy Harvesting Systems Open
We propose SmartON, a batteryless system that learns to wake up proactively at the right moment in order to detect events of interest. It does so by adapting the duty cycle to match the distribution of event arrival times under the constra…
View article: Intelligent Chargers Will Make Mobile Devices Live Longer
Intelligent Chargers Will Make Mobile Devices Live Longer Open
Editor's notes: Editor's note: Battery aging is becoming a major concern in mobile devices such as laptops or smartphones and often results in premature device replacement. This perspective article gives an overview of recent advances made…
View article: Fast and scalable in-memory deep multitask learning via neural weight virtualization
Fast and scalable in-memory deep multitask learning via neural weight virtualization Open
This paper introduces the concept of Neural Weight Virtualization - which enables fast and scalable in-memory multitask deep learning on memory-constrained embedded systems. The goal of neural weight virtualization is two-fold: (1) packing…
View article: EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching
EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching Open
EyeFi Dataset This dataset is collected as a part of the EyeFi project at Bosch Research and Technology Center, Pittsburgh, PA, USA. The dataset contains WiFi CSI values of human motion trajectories along with ground truth…
View article: EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching
EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching Open
EyeFi Dataset This dataset is collected as a part of the EyeFi project at Bosch Research and Technology Center, Pittsburgh, PA, USA. The dataset contains WiFi CSI values of human motion trajectories along with ground truth…
View article: EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching
EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching Open
EyeFi Dataset This dataset is collected as a part of the EyeFi project at Bosch Research and Technology Center, Pittsburgh, PA, USA. The dataset contains WiFi CSI values of human motion trajectories along with ground truth…
View article: EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching
EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching Open
Human sensing, motion trajectory estimation, and identification are central to a wide range of applications in many domains such as retail stores, surveillance, public safety, public address, smart homes and cities, and access control. Exi…
View article: Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named Gesture Recognition
Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named Gesture Recognition Open
The lack of adequate training data is one of the major hurdles in WiFi-based activity recognition systems. In this paper, we propose Wi-Fringe, which is a WiFi CSI-based device-free human gesture recognition system that recognizes named ge…
View article: SuperRF: Enhanced 3D RF Representation Using Stationary Low-Cost mmWave Radar.
SuperRF: Enhanced 3D RF Representation Using Stationary Low-Cost mmWave Radar. Open
This paper introduces SuperRF- which takes radio frequency (RF) signals from an off-the-shelf, low-cost, 77GHz mmWave radar and produces an enhanced 3D RF representation of a scene. SuperRF is useful in scenarios where camera and other typ…
View article: Differences in Reliability and Predictability of Harvested Energy from Battery-less Intermittently Powered Systems
Differences in Reliability and Predictability of Harvested Energy from Battery-less Intermittently Powered Systems Open
Solar and radio frequency harvesters serve as a viable alternative energy source to batteries in many cases where the battery cannot be easily replaced. However, energy harvesters do not consistently produce enough energy to sustain an ene…
View article: Non-Line-of-Sight Around the Corner Human Presence Detection Using Commodity WiFi Devices
Non-Line-of-Sight Around the Corner Human Presence Detection Using Commodity WiFi Devices Open
As robots penetrate into real-world environments, practical human-robot co-existence issues such as the requirement for safe human-robot interaction are becoming increasingly important. In almost every vision-capable mobile robot, the fiel…
View article: Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named\n Gesture Recognition
Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named\n Gesture Recognition Open
The lack of adequate training data is one of the major hurdles in WiFi-based\nactivity recognition systems. In this paper, we propose Wi-Fringe, which is a\nWiFi CSI-based device-free human gesture recognition system that recognizes\nnamed…
View article: Zygarde: Time-Sensitive On-Device Deep Intelligence on Intermittently-Powered Systems.
Zygarde: Time-Sensitive On-Device Deep Intelligence on Intermittently-Powered Systems. Open
In this paper, we propose a time-, energy-, and accuracy-aware scheduling algorithm for intermittently powered systems that execute compressed deep learning tasks that are suitable for MCUs and are powered solely by harvested energy. The s…
View article: Intermittent Learning: On-Device Machine Learning on Intermittently Powered System
Intermittent Learning: On-Device Machine Learning on Intermittently Powered System Open
This paper introduces intermittent learning - the goal of which is to enable energy harvested computing platforms capable of executing certain classes of machine learning tasks effectively and efficiently. We identify unique challenges to …
View article: SoundSemantics
SoundSemantics Open
In this paper, we propose a fundamentally different approach to acoustic event classification that exploits knowledge from the textual domain to deal with a well-known pain point in audio event classification---i.e., the lack of adequate t…
View article: Smart Audio Sensing‐Based<scp>HVAC</scp>Monitoring
Smart Audio Sensing‐Based<span>HVAC</span>Monitoring Open
This chapter proposes a Smart Audio SEnsing-based Maintenance (SASEM) system that has a single unifying intellectual focus, that is, enabling predictive maintenance of building equipment by autonomously monitoring and analyzing their acous…