Circular Image

M.A. Zuñiga Zamalloa

info

Please Note

79 records found

Towards Device-Free Gaming with mmWave Radar

Journal article (2026) - Yukuan Ding, Harvy Martinez, Girish Vaidya, Koen Langendoen, Marco Zuniga Zamalloa
Developing millimeter-wave (mmWave) radar applications, particularly for human pose estimation (HPE), often requires substantial manual effort to build custom code for data access, visualization, and model training. In addition, the lack of shared dataset formats and module interfaces makes it difficult to reproduce results and to compare different systems under consistent preprocessing and evaluation settings. To address these challenges, we provide two toolkits, mwCore and mwPose3d, released alongside our paper [1] : mwCore [2] and mwPose3d [3]. Together, these artifacts provide a unified pipeline for processing radar point clouds, evaluating state-of-the-art tracking and HPE models, and deploying online applications via inference from streaming radar data, e.g., device-free gaming. ...

Exploiting mmWave Sensors to Provide Privacy for Areas With Glass Walls

Journal article (2026) - Asterios Parlitsis, Girish Vaidya, Marco Zuniga
Glass walls reduce illumination costs, enhance thermal comfort and improve social safety. However, they raise privacy concerns. People do not like passersby looking into personal areas, such as computer monitors. Our solution combines two upcoming technologies, mmWave sensors and transparent screens. The mmWave sensors detect passersby, and the transparent screen allows us to turn opaque only a small area instead of the entire wall. We build upon studies performing human pose estimation (HPE) from radar point clouds while addressing their two important shortcomings. They (i) focus on single static users, and (ii) estimate only the right pose, not the exact body location. We provide a solution that works for multiple mobile people, while simultaneously providing accurate location and pose estimation, enabling a robust identification of head coordinates. Our live evaluation shows that, for three passersby, dynamic opaque areas of 30 cm × 30 cm block the line of sight over 95% of the time. Furthermore, our method outperforms a competitive SoA alternative for HPE, reducing the RMSE error (worst-case error) for the head by a factor of 17. Our code and dataset will be publicly available to study human pose estimation in challenging mobile scenarios with multiple people. ...
Journal article (2026) - Yukuan Ding, Harvy Martinez, Girish Vaidya, Koen Langendoen, Marco Zúñiga Zamalloa
Given the significant amount of time that people spend indoors, public spaces are reinventing themselves to deliver immersive experiences. One approach is to provide interactive gaming, such as the spaces created in big international airports like Singapore. The problem is that these gaming areas rely on either (i) wearable devices, which can easily spread germs, particularly in highly transited areas, such as those in airports, or (ii) cameras, which are increasingly raising privacy concerns and are being forbidden in some public areas. To provide an immersive gaming experience that is device-free and privacy-aware, we propose a system based on mmWave radar. In particular, our work provides three contributions. (1) For the first time, we compare various tracking and human pose estimation (HPE) models in the SoA under a unified framework. This approach allows us to identify the best methods in terms of position accuracy, latency, and smoothness-which are critical gaming metrics. (2) We build an integrated system with tracking and HPE capabilities. Our system includes the design of four games with different levels of complexity and a dataset collected specifically to train models for gaming applications. (3) Our evaluation, which includes a subjective users' survey and an objective comparison with a Kinect console, shows that today's mmWave is suitable for games where only the user's location is required or when coarse-grained gestures are needed. There are two key areas where mmWave research needs to improve to match camera-based consoles: sensors need a higher sampling rate, since a high frame rate is critical for seamless gaming, and HPE models need to master fine-grained gestures, in particular when arms end up in front of the body. All the code and datasets will be made available as a stepping stone for future work. ...

EODL: Energy-Aware On-Device Training on Microcontrollers

Conference paper (2026) - Hao Liu, Shashwath Suresh, Marco Zuniga
Deep learning models can be trained on microcontrollers (MCUs) for privacy-sensitive applications, but such training is severely constrained by tiny SRAM capacity and limited battery energy. Existing on-device learning methods optimise memory usage by selectively freezing layers so that training fits within SRAM budgets, yet none explicitly account for training energy. A strategy that is feasible in memory may therefore still consume significantly more energy than necessary, shortening battery life on energyconstrained devices. We present eODL, an energy-aware on-device learning framework. eODL exploits two observations: (1) counts of multiplyaccumulate operations (MACs) predict training energy with high fidelity (R2 = 0.993), so energy can be estimated; and (2) energyaware layer-update selection can be solved efficiently with tabular dynamic programming. Using these, eODL selects which layers to update under a hard SRAM budget while balancing energy against accuracy. We implement eODL end to end on STM32 MCUs and evaluate it on MCUNetV2 fine-tuned on the Flowers-102 dataset. Under a 50 kB training-memory budget, eODL matches state-of-the-art accuracy while reducing measured on-device energy by 22.6% per epoch. ...
Conference paper (2026) - Jeremy Gummeson, Pei Zhang, Marco Zúñiga

Optimizing Sensing and Inference for Solar-Powered TinyML Platforms

Conference paper (2025) - Hao Liu, Qing Wang, Marco Zuniga
Machine learning models can now run on microcontrollers. Thanks to the advances in neural architectural search, we can automatically identify tiny machine learning (tinyML) models that satisfy stringent memory and energy requirements. However, existing methods often overlook the energy used during event detection and data gathering. This is critical for devices powered by renewable energy sources like solar power, where energy efficiency is paramount. To address it, we introduce SolarML, a solution designed specifically for solar-powered tinyML platforms, which optimizes the end-to-end system's inference accuracy and energy consumption, from data gathering and processing to model inference. Considering two applications of gesture recognition and keywords spotting, SolarML has the following contributions: 1) a hardware platform with an optimal event detection mechanism that reduces event detection costs by up to 10 x compared to state-of-the-art alternatives; 2) a joint optimization framework eNAS that reduces the energy consumption of the sensor and inference model by up to 2 x, compared to methods that only optimize the inference model. Jointly, they enable SolarML to run end-to-end gesture and audio inference on a battery-free tinyML platform by only harvesting solar energy for 30 and 57 seconds, respectively, in an office environment (500 lux). Source code is available at [1]. ...
A recent technology known as transparent screens is transforming windows into displays. These smart windows are present in buses, airports and offices. They can remain transparent, as a normal window, or display relevant information that overlays their panoramic views. In this paper, we propose transforming these windows not only into screens but also into wireless transmitters. To achieve this goal, we build upon the research area of screen-to-camera communication. In this area, videos are modified in a way that smartphone cameras can decode data out of them, while this data remains invisible to the viewers. A person sees a normal video, but the camera sees the video plus additional information. In this communication method, one of the biggest disadvantages is the traditional screens’ power consumption, more than 80% of which is used to generate light. To solve this, we employ novel transparent screens relying on ambient light to display pictures, hence eliminating the power source. However, this comes at the cost of a lower image quality, since they use variable and out-of-control environment light, instead of generating a constant and strong light by LED panels. Our work–dubbed PassiveCam – overcomes the challenge of creating the first screen-to-camera communication link using passive displays. This paper presents two main contributions. First, we analyze and modify existing screens and encoding methods to embed information reliably in ambient light. Second, we develop an Android App that optimizes the decoding process obtaining a real-time performance. Our evaluation, which considers a musical application, shows a Packet Success Rate (PSR) of close to 90%. In addition, our real-time application achieves response times of 530 ms and 1071 ms when the camera is static and when it is hand-held, respectively. ...

Localization Through LEDs’ Hue Spectrum

Journal article (2024) - Jagdeep Singh, Marco Zuniga, Tim Farnham, Qing Wang
Over the past decade, visible light positioning has become increasingly important for precise localization systems, yet its widespread adoption is limited due to the necessity of modifying existing lighting systems. This paper presents HueLoc, a novel method that bypasses this issue by using inherent features of light, such as the dominant colours in white LED lights, and employs affordable, energy-efficient hue sensors for location services. We propose that by extracting the power at dominant wavelengths of LEDs, these can be uniquely identified using a specifically designed signature. The unique signatures can be used by mobile objects for spatial awareness and further localization using the proposed regression-based learning approach. Our experiments demonstrate that HueLoc attains a location-mapping accuracy of 100% and achieves decimeter-level localization precision with a moving object in uncontrolled lighting conditions. Moreover, these unique signatures can be combined with other RF-based technologies to enhance their localization accuracy. As an example, this paper details the integration of Bluetooth features with light signatures using a three-stage incremental learning approach. ...
Conference paper (2024) - Suchdeep Singh Juneja, Girish Vaidya, Marco Zuniga
In the field of music technology, the ability to connect body movements with music generation has led to highly engaging applications. Many existing solutions use cameras or wearable devices to capture physical movements and translate them into commands for a music generation tool. While the camera-based systems are privacy-invasive and demand good lighting conditions, the wearable devices adversely impact the fluidity of movements. We propose WaveTune, a privacy-friendly and device-free interface for creating music beats through body gestures. Wavetune has the following components: (i) a millimeter-wave radar as the frontend sensor that captures body movements, (ii) a gesture recognition algorithm that performs gesture delimitation and identification in real-time, and (iii) a music generation component that maintains a seamless and pleasant experience. WaveTune also provides an option to continuously map random dynamic movements into musical parameters to encourage further interaction. We recruited 24 users to train and test WaveTune’s ability to map body gestures to musical commands. To the best of our knowledge, WaveTune is the first mmWave system that allows a layered composition of music beats. ...
Conference paper (2024) - Seyed Keyarash Ghiasi, Marco Zuniga
Multiple-input multiple-output (MIMO) methods play a pivotal role in increasing the capacity of wireless communication systems, but they have not been analyzed systematically in the nascent area of passive communication with visible light (passive-VLC). The main challenge in passive-VLC is its low data rate. This limitation is caused by the slow switching speed of the most popular modulator used in the state-of-the-art: liquid crystal cells (LCs). Several studies use sophisticated modulation schemes with multiple LCs to increase the data rate. However, these efforts have only led to logarithmic improvements. A transmitter with a single LC can provide 1 kbps, and a transmitter with 64 LCs delivers 8 kbps: resulting in an efficiency of 125 bps per LC cell. Ideally, the capacity should increase linearly with the number of LCs.

We propose a general framework to achieve reliable MIMO communications with passive-VLC. Our approach, which has a theoretical and empirical foundation, has three desirable properties: (i) does not assume orthogonality of the individual channels (overcomes co-channel interference), (ii) can exploit multiple properties of light (polarization and color); and (iii) is agnostic to LC parameters (which some studies rely on). Our results show that a transmitter with 9 LCs increases its capacity almost linearly up to 9 channels, attaining 6.8 kbps (750 bps per LC) using the simplest modulation method in the SoA. ...
Conference paper (2024) - M.A. Chavez Tapia, M. Xu, Marco Zuniga
Consider an enclosed area, such as a room without windows. During the day, artificial light can provide illumination and communication thanks to advances in Visible Light Communication (VLC). Artificial lighting, however, has some drawbacks compared to using daylight in enclosed spaces. First, using sunlight consumes less power. Second, the use of natural light improves the health and comfort of the occupants. We propose a system, dubbed Sol-Fi, to provide joint illumination and communication in enclosed spaces using sunlight. Sol-Fi relies on two main components: commercial sunlight collectors and a novel transmitter to modulate ambient light. The sunlight collectors utilize optical fibers to guide natural light from open to enclosed spaces, and our transmitter modulates the incoming light providing two novel features. First, to analyze the pros and cons of the optical devices used in the literature for ambient light communication, Sol-Fi examines the properties of Liquid Crystals (LCs) and Digital Micro Mirror Devices (DMDs). Second, to investigate the trade-off between single- and multi-band communication, Sol-Fi proposes an optical design that can modulate the entire spectrum or divide it into different (individually modulated) bands. Our evaluation shows that, depending on the number of bands (single or dual) and the type of modulator (LC or DMD), Sol-Fi provides a data rate between 0.8 to 80 kbps, a range between 0.5 to 5 m, and a field-of-view between 30° to 60°. ...
Conference paper (2024) - M.A. Chavez Tapia, Daniel Tomás Menacho Ordoñez, Kiara Micaela Rodriguez Bautista, M. Xu, Davorka Medvedović, Marco Zuniga
Every day, we are surrounded by billions of invisible bits transmitted by our phones, tablets, and laptops. Wireless communication is pervasive but hard to teach because radio waves (5G, WiFi, BLE) cannot be seen, and a sensory experience is key to learning. From a physics perspective, radio and light waves are similar, but our eyes only see light. Thus, we design a platform to teach the complex concept of wireless communication using light. With our platform, children can "see" how a device transmits information using a normal flashlight. Our design includes connections with robots, superheroes, and games to make a joyful learning experience. The platform was used by hundreds of school students at an international science fair. After a guided activity, 80% of the students reported understanding the basic idea of wireless communication and some students even identified advanced concepts, such as interference, playing on their own. ...

Exploiting Luminescent Solar Concentrators for Ambient Light Communication

Journal article (2024) - Miguel A. Chávez Tapia, Diego Palma Rodríguez, Marco Zúñiga Zamalloa
A recent advance in embedded Internet of Things (IoT) exploits ambient light for wireless communication. This new paradigm enables highly efficient links via simple light modulation, but the design space has a fundamental constraint: in most State of the Art (SoA) studies, the link can only follow the propagation direction of ambient light. Consider, for example, a swarm of drones and ground robots that want to communicate with sunlight. Drone-to-robot communication could be possible because sunlight travels downwards from the air (drone) to the ground (robot), allowing drones to modulate light to send information to robots beneath them. Robot-to-robot communication, however, is not possible because sunlight does not travel sideways (parallel to the ground). To allow ‘lateral communication’ with ambient light, we propose using Luminescent Solar Concentrators (LSC). These optical components receive ambient light on their surface and re-direct part of the spectra towards their edges. Considering this optical property of LSC, our work has three main contributions. First, we benchmark various optical properties of LSC to assess their performance for ambient light communication. Second, we combine LSC with liquid crystal (LC) shutters to form lateral links with ambient light. Third, we test our links indoors and outdoors with artificial and natural ambient light, by enhancing two robots with our LSC transceivers and showing that they can exchange basic commands and coordinate tasks by communicating only with sunlight. ...

Towards Exploiting the Full Spectrum with Passive VLC

In recent years, the number of wireless applications has increased significantly, resulting in the radio bands becoming expensive and prone to interference. There is a new research area aiming at mitigating these issues by creating communication links using ambient light. This area, called passive-VLC, not only exploits the visible light frequencies, but does so with low-power transmitters. All the previous work in passive-VLC, however, forget about individual wavelength bands of light, and do not exploit its wide spectrum, reducing the potential channel capacity. In this paper, we propose a novel method to transmit and decode data, using liquid crystal cells that modulate and consider the full spectrum, and put it to the test by prototyping a multi-symbol communication link. The main contribution of our work is to show that passive-VLC can move from spectrum-agnostic to spectrum-aware modulation. We explore this new domain by making use of a novel type of receiver (i.e., a spectrometer) and uncovering the advantages and caveats of this spectrum-aware approach. ...
Conference paper (2023) - Ricardo Ampudia Hernandez, Talia Xu, Yanqiu Huang, Marco Zuniga Zamalloa
In this paper, we propose a new approach where drones attain accurate localization by fusing information from artificial lighting and their embedded inertial and barometer sensors. Our system is able to provide accurate drone localization without the use of radios, GPS or cameras. We evaluate our framework, dubbed Firefly, with a testbed consisting of four light beacons and a mini-drone. Our results show that Firefly allows locating the drone within a few decimeters of the actual position; and compared to two state-of-the-art positioning methods that rely solely on lighting information, Firefly can reduce the localization error by 50 % and 80%.. respectively. ...

Featuring LED Lights Through Hue Sensing

Conference paper (2023) - Jagdeep Singh, Qing Wang, Marco Zuniga, Tim Farnham
Visible Light Positioning (VLP) has been prevalent in providing high-precision localization systems in the past decade. However, the commercial availability or usage is still limited primarily due to the requirement of changing the existing lighting infrastructure. In this paper, we propose HueSense, an alternative technique to develop a passive VLP system by extracting light-emission intrinsic features, such as dominant colours present in the white LED light. The method can eliminate the need to change lighting-infrastructure, and only uses cheaper and power-efficient off-the-shelf hue sensors. Our experiments demonstrate that HueSense can achieve a location-mapping accuracy of 80.14% with a moving robot in uncontrolled lighting environments. ...
Conference paper (2023) - Weizheng Wang, Girish Vaidya, Anup Bhattacharjee, Francesco Fioranelli, Marco Zuniga
Sensing people with mmWave radars is gaining significant attention. This growing interest is due to two factors: radar monitoring provides more privacy than camera-based alternatives, and radio waves are not as easily blocked as light waves. Most mmWave studies, however, have three common characteristics. They are done indoors, without protecting the sensor (no casing), and the evaluation is performed for short periods of time. To assess the suitability of mmWave sensing in realistic outdoor scenarios, we deploy two nodes to track the flow of pedestrians over a period of three months. This longterm deployment provides three main contributions. First, we follow a detailed process to design a casing that can protect the sensors from harsh environmental conditions. Second, we install our nodes close to a set of cameras that were already deployed in the area. To compare the performance of both types of sensors, we propose a framework that considers the different coverage patterns of cameras and radars. Third, the time frame of our evaluation considers various types of weather, from sunny days to rainy and windy. Our results indicate that mmWave sensors need to be explored further outside the comfort zone of indoor spaces. To the best of our knowledge, this is the first long-term study assessing the reliability of radar sensors in the 60 GHz ISM band. ...

Exploiting Drones and VLC to Gather Data from Batteryless Sensors

Conference paper (2023) - Lucan de Groot, Talia Xu, Marco Zuniga Zamalloa
We explore a new alternative for drones to gather information from sensors. Instead of using the traditional radio-frequency spectrum, whose broadcast nature makes it more difficult to poll specific objects, we utilize the light spectrum. In our system, the drone carries a light, and flies to an area that it is interested in polling. Only the sensor (tag) under the coverage of the light sends data back by backscattering the impinging light waves. Enabling this system poses two challenges. First, a reliable modulation method with light is required. The method must overcome noise dynamics introduced by the drone (mechanical oscillations), the object (backscattering effects) and the environment (interference from ambient light). Second, to facilitate the deployment of tags in pervasive applications, the design of the tag should be battery-less and have a small surface area. These requirements limit the amount of power available for reception, transmission and sensing, since the energy harvested by solar cells is proportional to their surface area. Regarding the first challenge, we show that the amplitude-based modulation methods used in state-of-the-art studies do not work in our scenario, and investigate instead a frequency-based approach. For the second challenge, we optimize the computation, reception and transmission of the tag to create a battery-less design that operates with frequency-modulated signals generated from light. We build a prototype for the drone and the tag, and test them under different lighting scenarios: dark, indoors, and outdoors with sunlight. The results show that, under standard indoor lighting, our system can attain a polling range of 1.1 m with a data rate of 120 bps, while the tag operates with small solar cells and consumes less than 1 mW. ...
Journal article (2023) - Weizheng Wang, Qing Wang, Marco Zuniga
Cardiac patterns are being used to provide hard-to-forge biometric signatures in identification applications. However, this performance is obtained under controlled scenarios where cardiac signals maintain a relatively uniform pattern, facilitating the identification process. In this work, we analyze cardiac signals collected in more realistic (uncontrolled) scenarios and show that their high signal variability makes them harder to obtain stable and distinct features. When faced with these irregular signals, the state-of-the-art (SOTA) reduces its performance significantly. To solve these problems, we propose the CardioID framework1 with two novel properties. First, we design an adaptive method that achieves stable and distinct features by tailoring the filtering process according to each user’s heart rate. Second, we show that users can have multiple cardiac morphologies, offering us a bigger pool of cardiac signals compared to the SOTA. Considering three uncontrolled datasets, our evaluation shows two main insights. First, while using a PPG sensor with healthy individuals, the SOTA’s balanced accuracy (BAC) reduces from 90–95% to 75–80%, while our method maintains a BAC above 90%. Second, under more challenging conditions (using smartphone cameras or monitoring unhealthy individuals), the SOTA’s BAC reduces to values between 65–75%, and our method increases the BAC to values between 75–85%. ...

Mitigating the Effects of Irregular Cardiac Signals for Biometric Identification

Journal article (2022) - Weizheng Wang, Qing Wang, Marco Zuniga
Cardiac patterns are being used to obtain hard-to-forge biometric signatures and have led to high accuracy in state-of-the-art (SoA) identification applications. However, this performance is obtained under controlled scenarios where cardiac signals maintain a relatively uniform pattern, facilitating the identification process. In this work, we analyze cardiac signals collected in more realistic (uncontrolled) scenarios and show that their high signal variability (i.e., ir-regularity) makes it harder to obtain stable and distinct user features. Furthermore, SoA usually fails to identify specific groups of users, rendering existing identification methods futile in uncontrolled scenarios. To solve these problems, we propose a framework with three novel properties. First, we design an adaptive method that achieves stable and distinct features by tailoring the filtering spectrum to each user. Second, we show that users can have multiple cardiac morpholo-gies, offering us a much bigger pool of cardiac signals and users compared to SoA. Third, we overcome other distortion effects present in authentication applications with a multi-cluster approach and the Mahalanobis distance. Our evaluation shows that the average balanced accuracy (BAC) of SoA drops from above 90% in controlled scenarios to 75% in uncontrolled ones, while our method maintains an average BAC above 90% in uncontrolled scenarios. ...