Computer Science - Conference Items
Permanent URI for this collection
Browse
Recent Submissions
Item 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 IrelandVoice 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.Item Detection of wake word jamming(Association for Computing Machinery, 2024-11-22) Sagi, Prathyusha; Sankar, Arun; Roedig, Utz; Science Foundation IrelandPersonal 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.Item The use of personal learning simulators to improve doctors’ clinical decision making skills(Eurographics Ireland, 2007) Sliney, Aidan; Murphy, David; O'Mullane, JohnThis paper discusses the use of personal simulation within medical learning. Our objective is to show that personal simulators can be used to realise all datasets needed to fully represent medical situations. We developed a high fidelity personal simulator test framework titled JDoc. The paper outlines the construction process and the functionality of the personal simulator. We present a small scale post-test usability study with junior doctors from which we can assess the benefits of personal simulation within a small subcategory of medical users.Item Where care: A patient localization system for nursing homes(Institute of Electrical and Electronics Engineers (IEEE), 2024-10-25) Ronan, Isabel; Tabirca, Sabin; Murphy, David; Cornally, Nicola; Saab, Mohamad; Science Foundation IrelandAs the world's population continues to increase rapidly, there is a growing demand for healthcare services. Nursing homes are becoming more and more populated; the demands placed on care staff continue to grow exponentially. New approaches to care, such as palliative techniques, need to be considered to ensure residents are cared for in years to come. Localization can be used to track changes in behaviour and provide new insights into residents' palliative needs. Low-cost, reliable systems can be developed to help nurses monitor resident locations within nursing homes. This paper proposes a Bluetooth Low Energy localization system called “Where Care”. The proposed system uses smartphones and wireless Bluetooth beacons to localize residents in a test facility. A novel beacon placement technique and localization algorithm are used to provide real-time resident locations. Data collected is displayed in a graphical user interface (GUI) for ease of use. Heat maps and graphs are available in the GUI to allow care staff to make location predictions based on historical resident data. Nurses can also configure a notification service within the system interface to ensure resident safety. The system is implemented and tested in an experimental university space. Results show that the “Where Care” tool provides sufficiently accurate real-time localization measurements and data summaries. Overall, feedback indicates that “Where Care” is a useful tool with the potential for future use in busy, over-burdened nursing homes.Item A hybrid Bayesian approach for pessimistic bilevel problems with a new formulation(2024) Dogan, Vedat; Prestwich, Steven D.; O'Sullivan, Barry; Science Foundation IrelandIn many real-world problems, finding the optimal decision for a decision-maker depends on another decision-maker’s response, and it is called bilevel optimization in mathematical programming. It contains two levels of optimization problems while one appears as a constraint of another one called follower and leader, respectively. In many real-world scenarios, the lower level has multiple global optima and the upper level needs to make worst-case assumptions about the decision of the lower level, called the pessimistic case of the bilevel problem. Various approaches have been implemented over the years to solve generic bilevel problems, but few of them could be extended to pessimistic cases. In this short paper, we first propose a new formulation for the pessimistic case. In this way, we take advantage of the hierarchical structure of bilevel problems to make the results more accurate for pessimistic cases. Then, we implement a black-box approach to solve the pessimistic upper level problem to decrease the necessary function evaluations. The performance of the problem is examined by solving a test benchmark problem from the literature.