Research Facilities
There are a number of research facilities designed, developed and managed by Cardiff IOT Group. They are funded and maintained through various funding courses
There are a number of research facilities designed, developed and managed by Cardiff IOT Group. They are funded and maintained through various funding courses
The Smart Home Lab (SHL) is a key research facility designed, developed and managed by the IoT group. It is a physical space comprised of over 170 networked smart home devices. It has six hotdesk working areas where researchers (staff and students) can conduct various types of research with smart home devices. It comprises a wide range of devices such as smart TV, environmental monitoring kettles, various smart speakers, robotic vacuum cleaners, smart metre bells, door locks and many more. We use OpenHab and Home Assistant to capture semantic data and Wireshark to capture network traffic and related network communications and behaviours. The smart home lab also comprises a video network connected to six different types of smart home and consumer CCTV cameras to a network video recorder that allows connecting video analysis research in relation to the smart home domain. We also have a dedicated data science workstation to support extensive machine learning and deep learning research using smart home data.
Edge Lab is a key research facility supporting Edge Computing and Edge-AI research, enabling the exploration of a new class of latency-sensitive applications and the computational analysis techniques that underpin them. The lab consists of 100 experimental nodes, each built around a Raspberry Pi 4 (4GB RAM) with a 32GB SD card, Grove Pi, Arduino Shield for Raspberry Pi, Arduino Base Shield, and a range of sensing capabilities including temperature and humidity, light, motion, loudness, air quality, dust, and camera sensing. Each node is equipped with interchangeable communication technologies, including Wi-Fi, Bluetooth, XBee socket, XBee-PRO® ZigBee, and LoRa, and is housed in a case to support practical deployment. The lab is further enhanced by advanced computing platforms for AI and large model research, including the HOLMES (High perfOrmance for Large Machine modElS) workstation, featuring an Intel Core Ultra 7 processor, 128GB DDR5 RAM, NVIDIA RTX A6000 PRO 96GB GPU, and 4TB NVMe storage, as well as NVIDIA Jetson AGX Orin 64GB development kits for state-of-the-art Edge-AI experimentation. Additional resources include NVIDIA Jetson Nano devices, Neural sticks, and over 200 different types of Grove sensors (with multiple units of each type) that can be connected to any node. Supported by the EPSRC Early Career Equipment Fund, the Edge Lab provides a versatile platform for designing, deploying and evaluating intelligent, distributed and real-time edge systems.
The Abacws Living Lab is a high-density sensor network across the 5th floor of the Abacws building ceiling that captures a wide range of sensor data and enables researchers to conduct various research. We collect over 16 sensor parameters at high frequency, enabling us to monitor the building at high resolution using 34 sensor nodes.
Physical Sensing Lab is a key research facility supporting experimental work in physical sensing, embedded systems, Edge-AI and large foundation models. The lab brings together high-performance computing infrastructure, including the HOLMES workstation for large model research and NVIDIA Jetson AGX Orin development kits for edge intelligence, alongside a comprehensive electronic testing station equipped with a PicoScope 5000 oscilloscope and function generator, Saleae Logic Pro 16 analyser, Otii Arc Pro power analyser, JLink debuggers, bench power supplies and multimeters. It also houses a wide range of electronic and mobile development platforms, including Android and iOS devices, Arduino boards, Raspberry Pis, USRP B200 software-defined radios, physiological sensing devices such as blood pressure, EKG, biopotential and bioimpedance sensing platforms, as well as robotic development kits. In addition, the lab includes a dedicated rapid prototyping station with soldering and rework equipment, fume extraction, a hot plate, and a broad range of tools and materials for fast hardware development and iteration. Together, these capabilities make the Physical Sensing Lab an important environment for designing, building, testing and evaluating next-generation sensing and intelligent cyber-physical systems.
The Lego Lab is a key research and public engagement facility designed, developed and managed by the group members. It is a Lego-based smart city demonstrator enhanced with , allowing researchers and visitors to explore urban infrastructure, sensor networks, data pathways and cyber-physical risks through interactive digital overlays. The lab supports research, education and outreach in Internet of Things and smart city technologies by making complex technical ideas more accessible to non-specialist audiences. It also provides a controlled and engaging platform for demonstrating how connected urban systems operate in practice and for exploring potential cyber-physical security scenarios