Department Publications

Neurotransmitters, such as dopamine and serotonin, are endogenous chemicals that enable neurons to communicate with one another throughout the body. Alterations in the levels of specific neurotransmitters are associated with various neuropsychiatric disorders. Dopamine (DA) - often known as the feel-good hormone – is primarily responsible for reward and motivation and is a key biomarker of Parkinson’s disease. Medications such as Levodopa alter its level in biological fluids, monitoring of which is important to ensure the proper therapeutic range for sufficient medication to cross the blood-brain barrier. Serotonin (5-HT) regulates mood, stress response, sleep, and autonomic function, and its dysregulation is implicated in depression, anxiety, and other neuropsychiatric disorders. Continuous or longitudinal monitoring of serotonin—especially in accessible biological matrices—can provide critical insights into …

Semi-grant-free non-orthogonal multiple access (SGF-NOMA) schemes group one grant-based (GB) user with multiple grant-free (GF) users into one time/frequency resource block (RB) to enhance spectral efficiency. Due to the sporadic traffic of GF users and the stringent quality of service (QoS) requirement of the GB user, the access collision problem becomes severe in SGF-NOMA. To solve this problem, this paper firstly designs an RB-based power pool (PP), which directs GF users to adjust their transmit power without disrupting the ongoing transmission of the internal GB user. After that, this work proposes an efficient multi-agent deep reinforcement learning (MA-DRL) framework to jointly optimize the PP and access strategy for maximizing the network throughput. In particular, this work exploits the fast-response feature of the traditional competitive MA-DRL and the increased-performance feature of the …

Fire is a serious threat to both human life and property, and fire safety is crucial. Many traditional methods have been developed to detect fires. However, inspired by past research that used Wi-Fi signals for monitoring environments and recognizing activities, this approach aims to use Wi-Fi signals to detect fire that utilize existing wireless communication systems for non-intrusive sensing. The idea is that fire and smoke can interfere with Wi-Fi signals passing through an environment, then Wi-Fi CSI could provide detailed information about the wireless channel between a Wi-Fi transmitter and a receiver. This research demonstrates the effectiveness of using Wi-Fi for fire detection, utilizing Raspberry Pi and ESP32 devices with ESP32 CSI tool. It analyses the temporal shift in Wi-Fi CSI Amplitude before, during, and after the ignition of a flame. The results showed that fire causes a noticeable variation in the CSI …

The Relative Transfer Matrix (ReTM), recently introduced as a generalization of the relative transfer function for multiple receivers and sources, shows promising performance when applied to speech enhancement in noisy environments. Estimating the ReTM of sound sources by exploiting the covariance matrices of multichannel recordings is highly beneficial for practical applications and, to date, remains the only proposed approach. This paper investigates deep learning-based ReTM estimation. We propose three novel supervised learning frameworks using time and short-time frequency transform domain convolutional networks, and a Long Short-Term Memory-based recurrent neural network. Experimental results demonstrate that the proposed models achieve more accurate estimation of the ReTM using five objective metrics compared to the covariance-based method. We also show the effectiveness of the proposed frameworks for speech enhancement, achieving performance on par with the baseline method.

Meditation has been associated with a range of cognitive and physiological benefits. However, the underlying neural mechanisms of different meditation practices are not yet fully understood. This study investigates whether electroencephalogram (EEG) signals can be used to characterize and distinguish two commonly practiced meditation techniques, namely Samatha and Vipassana, which involve distinct cognitive processes, with Samatha emphasizing sustained concentration and Vipassana emphasizing mindful observation and insight. By extracting features such as band power, coherence and wavelet entropy from EEG signals recorded during pre-meditation resting, Samatha, and Vipassana states, we provide an assessment of how spectral power, signal complexity, and functional connectivity differentiate these practices. Preliminary results from experienced meditators indicate condition-dependent EEG differences, with the most pronounced effects observed in the delta frequency band. These results demonstrate the utility of EEG-based metrics for the objective characterization of meditation and advance our comprehension of the neural processes underlying different contemplative practices.

Isolating a desired speech signal in noisy multi-talker conversational scenarios is a key requirement for augmented reality (AR) wearable microphone array systems. In this work, a binaural target speaker extraction (TSE) framework, termed BiTSE, is proposed. It leverages both spatial and temporal cues, specifically the direction-of-arrival (DoA) of the target speaker and corresponding voice activity information, to guide the extraction process. Built upon a binaural signal denoising architecture, our model integrates three key enhancements: (i) a DoA-aware attention mechanism using cyclic positional embeddings, (ii) a timestamp-based masking strategy that utilizes speaker activity to suppress non-target segments, and (iii) a novel two-stage loss optimization strategy that first trains the model for robust denoising and then fine-tunes it to improve perceptual quality. Evaluations on the SPeech Enhancement for Augmented Reality (SPEAR) challenge dataset demonstrate that the proposed BiTSE consistently improves upon conventional approaches, leading to enhanced signal fidelity and perceptual quality.

Drone audio broadcasting enables rapid, flexible speech communication in scenarios such as search and rescue, disaster response, and public safety by projecting speech from onboard loudspeakers. However, speech played from drones is contaminated by its own intense, time-varying rotor noise, while increasing playback level is often undesirable as it raises concerns about privacy and noise pollution. Speech intelligibility improvement methods could be used to improve the intelligibility of speech under noise without increasing its sound level. To date, most methods have been evaluated using conventional maskers such as speech shaped noise or babble noise, rather than fluctuating drone noise. This study presents a subjective listening test with native New Zealand English listeners, that investigates the performance of four modern speech intelligibility improvement methods under varying input signal-to-noise ratio (SNRs) with two recorded drone noise conditions. The results show that the spectral shaping and dynamic range compression (SSDRC) and its variant consistently achieved better performance yielding up to a 72% intelligibility score improvement over unmodified speech at an input SNR of-16 dB, with diminishing gain at higher input SNR levels. Performance difference between drone types was are while the ranking of the evaluated methods was consistent across both conditions.

The Gaussian Mixture Model (GMM) based multi-stage Wiener filter (WF), recently introduced as a single-channel noise suppression method, demonstrates promising performance when applied to low signal-to-noise ratio (SNR) speech enhancement. This paper introduces a method for phonocardiogram (PCG) signal denoising using a two-stage subspace adaptive filtering method, with the aim of improving the noise suppression performance using GMM WF. Specifically, we utilize the normalized least mean squares (NLMS) and GMM WF to propose a hybrid adaptive filter with multi-channel spectral principal components analysis (PCA), which suppresses residual noise. We perform experimental evaluations on two heart sound datasets and show that the proposed denoising method exhibits increased performance over baseline approaches under various real-world noise conditions.

Neonatal jaundice, caused by elevated bilirubin levels, requires timely diagnosis to prevent severe complications. Existing deep learning approaches primarily focus on binary classification of jaundice from visual data, but do not provide quantitative bilirubin estimation. A binary decision alone is insufficient for clinical management, where treatment thresholds depend on precise bilirubin levels. This paper presents a deep-learning-based contactless framework for neonatal jaundice assessment using image-based analysis. The proposed lightweight multi-stage pipeline integrates eye-region obfuscation, skin segmentation, and deep-learning-based image classification and bilirubin estimation. The system first performs jaundice classification; upon positive detection, a regression model is invoked to estimate bilirubin. Furthermore, image-based neonatal screening raises privacy concerns, as facial images of …

In coastal environments, detecting and classifying low radar cross-section (RCS) moving targets such as dinghies and trawlers using pulse radar system is challenging due to strong sea and land clutter. The clutter reduces detection accuracy. Further, the detection and classification heavily depend on radar operator expertise. To overcome these limitations, we propose an operator-independent framework for detection and classification. This paper presents a hybrid approach that combines Robust Principal Component Analysis (RPCA) with deep learning-based object detection models to improve target detection using radar Plan Position Indicator (PPI) images. RPCA is first applied as a low rank nature clutter separation from sparse moving targets. Detection is then performed using You Only Look Once (YOLO) and Detection Transformer (DETR) models on these clutter-suppressed representations. Experimental …

Humanoid robots have become increasingly popular in applications such as social interaction, education, and service roles, which drives the need for more natural and efficient human-robot interactions. However, currently available humanoid heads often face limitations, including high costs, mechanical complexity, and limited adaptability across diverse environments. To address these challenges, we present an articulated humanoid robot head designed for a receptionist role, integrating a mechanical structure with 21 degrees of freedom (DoF), including mechanisms for the mouth, eyes, eyebrows, and neck, and covered with realistic silicone skin to achieve a human-like appearance and expression. The system integrates a model-based architecture that combines SCRFD, ArcFace, and ByTetrack for face recognition and Llama and Whisper for natural language processing, with hardware support enabling real …

Vehicle license plate recognition is an integral component of intelligent transportation systems. In this work, we present an embedded real-time license plate recognition system customized for developing countries. We address the challenge of handling complex, unstructured traffic scenes with diverse vehicle types while implementing the system on an embedded platform for low-cost deployment. Our method consists of license plate detection on a multi-vehicle image, followed by character recognition on the detected license plates. Both steps use lightweight convolutional neural networks to balance accuracy and efficiency. We also introduce the SL-LPR dataset of Sri Lankan road images, which contains a variety of vehicle types and traffic conditions typically seen in developing countries. On this dataset, the license plate detection and character recognition models achieved 93.6% mAP and 87.88% accuracy, respectively, and were competitive against larger models on several public datasets. To achieve real-time performance in a resource-constrained embedded environment, we applied low-bitwidth quantization using the Brevitas library and implemented FPGA acceleration for the models using the FINN framework. The end-to-end system can operate at 11.5~FPS when implemented on the Xilinx Kria KV260 platform. These results demonstrate that our system is effective for real-time license plate recognition on an embedded device, even in complex traffic scenarios. The SL-LPR dataset is available for research use at: https://github.com/sl-lpr-uom/SL-LPR.git.

Civilian GNSS receivers are vulnerable to spoofing due to open signal structures, while adaptive electronic-warfare platforms increasingly synthesize high-fidelity counterfeit signals. Existing detection methods depend on handcrafted features or supervised learning, limiting robustness under distribution shifts and novel attacks. This paper introduces NEMESIS, a self-supervised framework based on joint embedding predictive architectures (JEPA) in the wavelet time-frequency domain, which leverages unlabeled RF corpora via masked time-frequency prediction to learn spoofing-relevant embeddings directly from raw RF signals without labels or contrastive augmentation. Experiments demonstrate that wavelet-domain JEPA substantially outperforms time- and frequency-domain variants and achieves competitive accuracy relative to contrastive learning while significantly reducing labeling requirements.

Remote photoplethysmography (rPPG) enables contact free monitoring of vital signs and is especially valuable for neonates, since conventional methods often require sustained skin contact with adhesive probes that can irritate fragile skin and increase infection control burden. We present VideoPulse, a neonatal dataset and an end to end pipeline that estimates neonatal heart rate and peripheral capillary oxygen saturation (SpO2) from facial video. VideoPulse contains 157 recordings totaling 2.6 hours from 52 neonates with diverse face orientations. Our pipeline performs face alignment and artifact aware supervision using denoised pulse oximeter signals, then applies 3D CNN backbones for heart rate and SpO2 regression with label distribution smoothing and weighted regression for SpO2. Predictions are produced in 2 second windows. On the NBHR neonatal dataset, we obtain heart rate MAE 2.97 bpm using 2 second windows (2.80 bpm at 6 second windows) and SpO2 MAE 1.69 percent. Under cross dataset evaluation, the NBHR trained heart rate model attains 5.34 bpm MAE on VideoPulse, and fine tuning an NBHR pretrained SpO2 model on VideoPulse yields MAE 1.68 percent. These results indicate that short unaligned neonatal video segments can support accurate heart rate and SpO2 estimation, enabling low cost non invasive monitoring in neonatal intensive care.

Label noise is prevalent in medical image datasets, arising from observer disagreement and ambiguous cases and deep networks memorize the mislabeled examples at the cost of generalization. Current solutions such as loss correction and sample selection add training complexity and generally assume the noise rate is known or estimable. This paper investigates whether robustness can be obtained architecturally, by routing a frozen backbone's features through a low-dimensional bounded bottleneck and classifying them with a head whose function class is intrinsically smooth. Variational quantum circuits with angle encoding and a linear cost function realise exactly such a class. Their use in medical imaging, however, has been limited by the small number of qubits available on noisy intermediate-scale devices, which typically restricts inputs to low-resolution grayscale images. We therefore couple a frozen ImageNet-pretrained ViT-B/16 backbone to a trainable linear bottleneck and an eight-qubit variational quantum circuit, allowing 224x224 RGB inputs to be processed. Under clean labels the model leads five of six MedMNISTv2 benchmarks against published hybrid quantum-classical models, with margins of 17.4 and 15.7 percentages on BloodMNIST and PathMNIST. The advantage emerges under corrupted labels. At symmetric noise rates of 30% and 50% the model outperforms many published quantum and noise-robust classical baselines on all six datasets without any explicit noise-handling component. Against a control that shares the backbone, bottleneck, parameter count and optimizer and replaces only the circuit with a ReLU …

Dry-contact ear-electroencephalography (Ear-EEG) enables wearable neural monitoring. However, motion induced electrode-skin impedance (ESI) mismatches between electrodes can severely degrade signal quality. To the best of our knowledge, this paper presents the first proof-of-concept dry-contact EarEEG system that uses a driven-right-leg (DRL) stimulus for continuous ESI mismatch monitoring, enabling online adaptive motion artifact cancellation. A 1 kHz sinusoidal stimulus is injected through the DRL electrode. The resulting response to the injected carrier is separated from the EEG using bandpass filtering and demodulation, and then used to extract the ESI mismatch information as the reference input for a normalized least-mean-square adaptive filter followed by a Hampel filtering stage. To evaluate artifact suppression and preservation of neural activity, alpha-band EEG activity was analyzed involving four healthy participants performing head nodding, electrode tapping, and jaw clenching. The system achieved artifact power reductions of 6.5, 12.6, and 9.0 dB (77.6%, 92.8%, and 86.4%, respectively) while alpha-band modulation remained clearly observable after processing. This demonstrates the feasibility of DRL-stimulusbased ESI mismatch monitoring for motion artifact cancellation in wearable dry-contact Ear-EEG.

The radio frequency (RF) cochlea, a biomimetic LCR transmission-line filter bank that performs O(N) broadband spectrum analysis, has been demonstrated in active CMOS and as passive microwave channelizers but has remained a one-dimensional (1-D) structure since its introduction two decades ago. We argue that the natural next step is to add a second dimension, and we explore three complementary aspects of this extension. First, we review existing 1-D RF cochlea architectures and present a 20-channel, 1 GHz constant-bandwidth passive channelizer as a representative implementation. Second, we analyze the two-dimensional (2-D) cochlear-duct geometry of Watts and Neely using finite-difference and Liouville–Green simulations: the second dimension introduces a cut-off mode whose interference with the traveling-wave mode produces an upper-skirt roll-off 1.6–1.7× steeper than the 1-D long-wave limit …

This paper presents a multi agent neurosymbolic artificial intelligence architecture to dynamically adapt operating parameters of radio frequency (RF) transceivers. The proposed dual branch architecture combines deep learning feature extraction with deterministic symbolic reasoning, leveraging sensed physical parameters such as signal power and spectrum occupancy, to ensure self-adapting and robust hardware safety. Component specific control agents are trained using digital twins and integrated with physical hardware via shared memory space and socket-based inter-process communication for low latency. Experimental results demonstrate accurate modeling and rapid parameter adaptation for error vector magnitude optimization, providing a scalable foundation for intelligent self-adapting RF transceivers.

Sensing and early detection of small unmanned aerial systems (sUAS) are critically important in modern-day defense. In dense urban and indoor environments, detection becomes extremely challenging due to dense multipath, fading, low-altitude flight, and non-line-of-sight (NLOS) radio-frequency propagation. This paper presents a continuous-wave multiple-input multiple-output radar and a deep learning model for sUAS detection using NLOS signals. The radar operates at 2.47 GHz, and spectral correlation densities derived from rotational micro-Doppler signatures from the rotor blades are used as inputs to the deep learning model. Experimental results demonstrate an overall detection accuracy of across a dataset of five drone types, confirming the feasibility of sUAS detection in dense urban environments without direct line-of-sight conditions.

This paper presents the design and implementation of a multi-band multi-mode radar for reliable detection and identification of micro unmanned aerial systems (UASs). A rotational micro-Doppler continuous-wave radar operating at 5.85 GHz and a frequency-modulated continuous-wave (FMCW) radar operating with 77–80 GHz bandwidth are used for multi-modal radio frequency (RF) sensing, localization and detection. Fusion of the two radars is achieved with a neurosymbolic artificial intelligent model. Cyclostationary feature extraction is used for the micro-Doppler signature extraction. Wavelet domain feature extraction is used on the FMCW radar outputs. A custom neural engine is used for multi-modal sensor fusion across the two RF bands and radar types.

The optimal selection of approximate computing units towards low-complexity FPGA-based hardware architectures for approximate discrete cosine transform (ADCT) and approximate discrete Fourier transform (ADFT) are explored. The proposed methodology employs an existing library of FPGA based approximate adders to select Pareto-optimal 1 approximate adders for cascaded signal flow architectures found in ADCT and ADFT operations. Benefits are presented with examples from 8-point ADCT based image compression and 16-point ADFT based digital multi-beamforming applications. Examples demonstrate a nearly 25% LUT reduction in FPGA utilization compared to error-free computing, with a corresponding degradation of nearly 1 dB in terms of PSNR in image compression and 0.3 dB loss in SNR improvement in beamforming.

Low-complexity digital multi-beamforming via multiplier-less approximations for discrete spatial Fourier transform (DSFT) is explored. The proposed approach employs an approximate-DSFT (ADSFT) which - for a uniform linear array with N antennas producing N simultaneous beams, reduces the hardware multiplier requirement from 3N 2 to 0 with marginal error in the beam profiles. Importantly, the proposed approach extends the previously reported approximate discrete Fourier transform (ADFT) multi-beamforming systems having fixed beam profiles to enable configurable beam profiles, where the user can obtain N simultaneous beams within a given spatial angular region. Simulations demonstrate that the multi-beam profiles are largely accurate, and approximate selection results in deviations for 8- and 16-element ULAs, with worst-case beam angle errors of 0.3° and 0.2°, and worst-case sidelobe deviations of …

The 6-24 GHz upper midband - FR3 range - is the next generation spectrum for mobile wireless applications. Traditionally allocated for defense and scientific use cases, the possible adoption of FR3 frequencies for commercial applications opens the possibility for severe interference between different commercial and scientific/defense systems. We demonstrate lowcomplexity adaptive array processing in the FR3 range using realtime implementation in the 10.7-10.8 GHz band, with 100 MHz of bandwidth using Xilinx Virtex-6 Sx475T FPGA technology. The demonstration supports a uniform linear array with 8 Vivaldi antennas (6-24 GHz) and can provide up to 6 nulls in the aperture pattern in addition to the desired RF beam. The FPGA back-end utilizes sampling at 200 MS/s and exploits digital signal processing to furnish up to 100 MHz of bandwidth at IF.

Substantial data losses occur during transmission between the sensor nodes of a wireless sensor network due to various causes such as the instability of wireless communication links and network congestion. Most of the data recovery methods proposed are computationally expensive or rely on additional data from neighboring sensors or other types of correlated data which may not always be available. In this paper, we instead propose a lightweight real-time method of missing data recovery based on chromatic derivatives (CDs), a noise robust alternative to standard derivatives that enables high-fidelity local signal approximation. Using the bandlimited nature of the measured signals, our method interpolates the missing data using CDs-based non-uniform sample reconstruction. In contrast to many state-of-the-art methods, our approach relies solely on the received data stream from the transmitting sensor for …

This paper proposes a secure and cost-effective communication and management approach for distributed disaster early warning networks to ensure reliable, low-latency alert dissemination. While decentralized architectures reduce latency by enabling direct device communication, they are highly vulnerable to attacks due to their exposure in public community settings and the challenges posed by Network Address Translation (NAT) and firewalls. Traditional NAT traversal techniques often lack the built-in security required for such sensitive infrastructure. We identify Nebula, an open-source overlay networking tool, as a viable solution because it is lightweight enough for low-resource devices such as the Raspberry Pi typically found in decentralized early warning systems, supports NAT traversal, and provides endto-end encryption. Preliminary experiments conducted in an AWS environment—designed to simulate real-world Raspberry Shake sensor deployments—confirm Nebula’s ability to establish direct peer-to-peer (P2P) connectivity with a single hop and effectively encrypt traffic