1. Spy Camera Detector
Haru
Collaborators: Inha University and KAIST
Research funded by: National Research Foundation of Korea

This is an innovative solution for detecting spy cameras in indoor environments. Our approach utilizes cutting-edge technology to provide a discreet and effective means of protecting personal privacy. The increasing prevalence of spy cameras in private rental spaces has raised serious privacy concerns. Existing detection methods often require users to carry additional hardware or perform cumbersome actions, making them impractical and uncomfortable. Our solution offers an efficient and unobtrusive spy camera detection system. By leveraging Channel States Information (CSI) and monitoring WiFi camera video bitrate fluctuations, our solution eliminates the need for physical hardware or user-intensive actions. Our system is designed to operate seamlessly in multipath-rich environments, ensuring reliable detection without user discomfort. Our system represents a significant advancement in spy camera detection, providing a practical and user-friendly solution to safeguard personal privacy in various indoor environments.

Publications:

IMWUT - Toptier (~20% Acceptance rate)
CSI: DeSpy: Enabling Effortless Spy Camera Detection via Passive Sensing of User Activities and Bitrate Variations
Muhammad Salman, Nguyen Dao, Uichin Lee, Youngtae Noh
IEEE Access - SCI(E)
DeepDeSpy: A Deep Learning-Based Wireless Spy Camera Detection System
Dinhnguyen Dao, Muhammad Salman, Youngtae Noh
2. Contactless Stress/Fatigue Detection
Haru
Collaborators: KENTECH, Hanyang, and Hyundai Motors
Research funded by: Hyundai-NGV

This project was aimed at enhancing road safety. We successfully integrated diverse sensors, including mmWave Radar and wearables like the Polar H10 and E4 wrist device, to comprehensively monitor a driver's physiological indicators. In this project, we unified data from various sources, overcoming morphological differences to consistently extract fatigue information. We unified these features into and trained a deep-learning model to anticipate driver fatigue.

Publications:

UbiComp - Toptier (~20% Acceptance rate)
A Contactless and Non-Intrusive System for Driver’s Stress Detection
Muhammad Salman, Hyunkyu Jang, Youngtae Noh, Seungwan Jin, Dayoung Jeong, Hoyoung Choi, Kyungsik Han, Hyangmi Kim
BigComp
Contactless Vital Signs Tracking with mmWave RADAR in Realtime
Muhammad Salman and Youngtae Noh
3. Wireless Occupancy Monitoring
Haru
Collaborators: KENTECH and Inha University.
Research funded by: National Research Foundation of Korea (NRF); and Ministry of Trade, Industry, and Energy (MOTIE).

In addressing the limitations of traditional, costly methods such as PIR sensors and cameras in complex indoor environments, this project focuses on energy-efficient solutions within buildings. Introducing WiSOM, a system harnessing WiFi signals, we developed a self-adaptive occupancy detection system resilient to wireless impairments. Comprehensive evaluations under various indoor conditions, including multipath effects, activity intensities, and wall absorption, demonstrate WiSOM's high detection rate and resilience to multipath variations. The results also showcase significant improvements over recent baselines in real-house scenarios, positioning WiSOM as a promising solution for effective energy management in buildings.

Publications:

ACM SAC
WiFi-enabled Occupancy Monitoring in Smart Buildings with a Self-Adaptive Mechanism
Muhammad Salman, Young-Duk Seo, Youngtae Noh
Elsevier Energy (SCI-E: Q1 - top 5 %)
WiSOM: WiFi-enabled self-adaptive system for monitoring the occupancy in smart buildings
Muhammad Salman, Lismer Andres Caceres-Najarro, Young-Duk Seo, Youngtae Noh
4. Enhancing WiFi UX (SDN-controlled)
Haru
Collaborators: Inha University, TmaxSoft, KENTECH, and KAIST
Research funded by: National Research Foundation of Korea

This research project addressed the sticky user problem in WiFi networks by implementing an innovative framework to load balancing through association redistribution. For this, we utilized Software-Defined Networking (SDN) to enable swift and seamless transitions for WiFi users. The methodology has been rigorously tested in both real-world scenarios and simulations, resulting in an impressive 80% improvement compared to existing solutions.

Publications:

IEEE Internet of Things (SCI-E: Q1 - Top 10 %)
DARCAS: Dynamic Association Regulator Considering Airtime Over SDN-Enabled Framework
Muhammad Salman, Jin-Ho Son, Dong-Wan Choi, Uichin Lee and Youngtae Noh
5. WSN Localization
Haru
Collaborators: Inha University, KIET, Lusófona de Humanidades e Tecnologias, KENTECH, and GIST
Research funded by: National Research Foundation of Korea

Unlock precise target tracking in wireless sensor networks (WSNs) with our cutting-edge solution! Our this project introduces a revolutionary approach to the target tracking problem, leveraging received signal strength (RSS) and angle of arrival (AOA) within the maximum a posteriori (MAP) framework. Unlike conventional algorithms that compromise tracking accuracy by approximating and relaxing the highly nonlinear and nonconvex cost function, our proposed tracking algorithm utilizes evolutionary techniques for unparalleled precision.

Publications:

IEEE Sensors Journal (SCI-E: Q1)
Evolutionary Tracking Algorithm Based on Combined Received Signal Strength and Angle of Arrival Measurements in Wireless Sensor Networks
LA. Caceres Najarro, Iickho Song, Slavisa Tomic, Muhammad Salman, Youngtae Noh and Kiseon Kim
Experience