CORA
Cork Open Research Archive (CORA) is UCC’s Open Access institutional repository which enables UCC researchers to make their research outputs freely available and accessible.
UCC Research Communities
Recent Submissions
GOTCHA: Physical intrusion detection with active acoustic sensing using a smart speaker
(Springer Nature, 2024) Pham , Hoang Quoc Viet; Nguyen, Hoang D.; Roedig, Utz; Science Foundation Ireland
Voice Assistants (VAs) in the form of smart speakers such as Amazon Alexa, Google Assistant or Apple Siri are now commonplace. Due to their ubiquitous presence they can be useful as home alarm systems. In this work we present the development and evaluation of a novel physical intrusion detection system GOTCHA based on human presence detection with active acoustic sensing. GOTCHA can execute on simple off-the-shelf smart speaker hardware. Periodic audible chirps are employed to gather data which are then processed by a deep autoencoder trained on the acoustic profile of the empty room. As our evaluation shows, GOTCHA achieves promising results of up to 99.2% for the F1-score. Our experiments show that a person can be detected without fail while the system barely generates false alarms. GOTCHA is a viable alternative to passive sensing solutions for physical intrusion detection.
Detection of wake word jamming
(Association for Computing Machinery, 2024-11-22) Sagi, Prathyusha; Sankar, Arun; Roedig, Utz; Science Foundation Ireland
Personal Voice Assistants (PVAs) such as Apple's Siri, Amazon's Alexa and Google Home continuously monitor the acoustic environment for a wake word to start interaction with the user. However, the wake word detection is susceptible to disruptions caused by acoustic interference. Interference might be by noise (e.g. background music, chatter, engine sounds) or a targeted jamming signal designed to disrupt PVA operations. As PVAs are increasingly used for critical applications such as medicine and the military, it is necessary to identify an attack. In this work, we re-design the wake word detection algorithm such that it is not only robust against an attack but is also able to identify an attack. Only if it is possible to identify an ongoing attack it is possible to employ appropriate countermeasures, i.e. remove the attacker. We modify the wake word detection model to function as a three-class classifier that accurately differentiates between clean wake words, wake words mixed with jamming signals and non-wake words. We further improve the classification results by examining the Direction of Arrival (DOA) and the Short Time Energy (STE ) of the audio signal. DOA and STE information is usually available on off-the-shelf PVA which enables implementation of the proposed methods on existing devices.
Embolisation of an acquired uterine arteriovenous malformation
(BMJ Publishing Group, 2024-12-15) Coffey, Aidan John; Galvin, Daniel; Power, Stephen; Hayes-Ryan, Deirdre
A G5P2+2 woman in her 30s presented to hospital with per vaginum (PV) bleeding, approximately 2 weeks post electric vacuum aspiration (EVA) for retained products of conception. Ultrasound and MRI demonstrated a large vascular myometrial lesion, suggestive of a uterine arteriovenous malformation (UAVM). She underwent digital subtraction angiography (DSA) with interventional radiology and simultaneous uterine artery embolisation (UAE). She represented 2 weeks later with recurrent PV bleeding and anaemia. She underwent repeat DSA, demonstrating persistent UAVM, and a repeat embolisation was performed. Symptoms resolved following the second embolisation, and a repeat MRI performed 12 weeks later demonstrated complete resolution of the UAVM. Although UAVMs are rare lesions, they can cause significant haemorrhage and morbidity. The presence of UAVM should particularly be considered after uterine intervention such as EVA or caesarean section. UAE is a safe and effective therapy, which preserves fertility.
Assessing trust in collaborative robotics with different human-robot interfaces
(Institute of Electrical and Electronics Engineers (IEEE), 2024) Menolotto, Matteo; Komaris, Dimitrios-Sokratis; O’Sullivan, Patricia; O’Flynn, Brendan; Enterprise Ireland; Science Foundation Ireland; European Regional Development Fund
Human-robot interfaces (HRIs) serve as the main communication tools for controlling and programming robots in industry 4.0 applications. To be effective, the design of these interfaces should consider not only functional and morphological characteristics, but also factors influencing human interactions, such as trust. A lack of trust is linked to the underutilization or misuse of collaborative robots, leading to ineffective automation implementation and compromised safety. The assessment of human factors is therefore gaining traction in robotics, with the emergence of both objective and subjective methodologies. Nevertheless, the absence of a holistic approach hinders the development of a unified assessment framework. This study introduces a novel assessment methodology that integrates self-reporting questionnaires with human-centric data collected through wearable sensing technologies. The approach aims to offer a comprehensive evaluation of HRIs, considering both perceptual and behavioral dimensions. Empirical testing on three different HRIs substantiates the effectiveness of this methodology. Preliminary results reveal variations in trust levels based on the combination of tasks performed and the specific HRI used for communication with a collaborative robot. These findings not only contribute to advancing our understanding of trust dynamics in human-robot interactions but also lay the groundwork for a more inclusive evaluation framework, enhancing our comprehension of the intricate interplay between humans and robots in the context of smart manufacturing.
Spatial and temporal variation in mortality from avian influenza in Greenland Barnacle Geese Branta leucopsis in their wintering grounds
(Taylor & Francis, 2024-12-23) Percival, Steve; Bowler, John; Cabot, David; Duffield, Steve; Enright, Martin; How, James; Mitchell, Carl; Percival, Tracey; Sigfusson, Arnor
Capsule: Avian influenza caused the loss of more than 20% of the Greenland Barnacle Goose population, but this impact varied between wintering areas and over time. Aims: The primary objective was to investigate the spatial and temporal mortality patterns due to avian influenza (H5N1) in wintering Greenland Barnacle Geese. Methods: We analysed a comprehensive dataset of marked individuals spanning six years, with observations from a network of observers across their wintering range. The study specifically compared the mortality rates of Greenland Barnacle Geese during the H5N1 outbreak years (2021/2022 and 2022/2023) with the three previous winters (2018/2019–2020/2021). Results: The study found significant spatial and temporal variation in mortality resulting from avian influenza outbreaks within the Greenland Barnacle Goose population on their wintering grounds in Scotland and Ireland. Some sites (Islay, Tiree and Sligo) experienced 30–56% reductions in survival rates, while others (Uist and Mayo) showed little or no impact. The timing of the main outbreaks also differed between sites. Excess deaths (in comparison with the previous baseline), estimated using mark-resighting data, indicated that mortality was considerably higher than suggested from direct field counts, reaching at least 20% of the global population in the peak outbreak winter (2022/2023). Conclusion: The results highlight the importance of spatial and temporal dynamics in avian influenza impacts. Disease dynamics should be integrated into population management models and used for setting appropriate thresholds for minimum population levels, to ensure resilience to disease outbreaks and long-term viability.