Computer Science - Journal Articles

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 5 of 184
  • Item
    A mobile e-learning application for enhancement of basic mathematical skills in visually impaired children
    (Springer Nature Ltd., 2023-03-17) Shoaib, Muhammad; Khan, Shakeel; Fitzpatrick, Donal; Pitt, Ian; Science Foundation Ireland
    Although smartphones are equipped with accessibility functions, they still pose significant problems for visually impaired people. Sometimes these functions cannot fulfil the expectations of users. Early mobile devices had physical buttons and a keypad, and visually impaired users could navigate around the keypad using the tactile markers on the buttons. However, the lack of tactile markers makes it much more difficult to operate a touchscreen device. This paper describes an e-learning platform that is designed to improve the accessibility of smartphone applications for students who are visually impaired but have some useful vision. A User-Centered Design approach was used to develop an effective solution for visually impaired students. A study was conducted during the development of the described platform, and the results showed that our suggested design improves task completion time as compared to the initial version. Participants also expressed higher levels of satisfaction when using the improved design of this platform. The modified design was also assessed using the Mobile Application Rating Scale (MARS), and the results indicate that it is quite reliable and rated well among visually impaired children. Furthermore, developers can use our suggested design guidelines such as clear navigation, color contrast, immediate feedback, icon arrangements, button and text size in the development of new applications.<
  • Item
    Exploring unknown plant configurations under a multiple model adaptive control framework
    (Elsevier, 2023-11-22) Jesús Ares-Milián, Marlon; Provan, Gregory; Sohège, Yves; Quinones-Grueiro, Marcos; Science Foundation Ireland
  • Item
    A narrowband ultrasonic ranging method for multiple moving sensor nodes
    (Institute of Electrical and Electronics Engineers Inc., 2019) Ashhar, Karalikkadan; Noor-A-Rahim, Md.; Khyam, Mohammad Omar; Soh, Cheong Boon; Edge Hill University; Horizon 2020; Nanyang Technological University
    Accurate ranging using narrow-band ultrasonic transducers in small-scale environments can be used for indoor localization, human motion capture, and robotic navigation. One of the main problems faced by the ultrasonic localization systems is the ranging error due to the Doppler shift. Existing methods for Doppler correction employ a bank of matched filters at the receiver end which is computationally intense and complex. On the other hand, enabling multiple access for the ultrasonic localization systems is a challenging task due to multiple access interference. We propose a method to measure the range between multiple ultrasonic mobile nodes and static anchors in which we track the Doppler velocity and correct the errors between the transmitted and the received signals due to the Doppler effect. We utilize range-Doppler coupling to estimate the Doppler shift and adjust the range values calculated by correlation. In our method, a unique set of two chirp signals are used for each transmitter to get one sample reading. The simulation results show high ranging accuracy and robustness using the proposed method as the Doppler velocity increases. A pendulum experiment was conducted to validate the method using narrowband ultrasonic sensors. The multiple access interference problem was tackled by orthogonal coding, the chirp signals and Doppler correction. An improvement in the ranging accuracy was observed over traditional methods using chirp signals without Doppler correction. © 2019 IEEE.
  • Item
    Risk as a driver for AI framework development on manufacturing
    (Springer, 2022-05-11) Vyhmeister, Eduardo; Gonzalez-Castane, Gabriel; Östbergy, P.-O.; Science Foundation Ireland
    Incorporating ethics and values within the life cycle of an AI asset means to secure, under these perspectives, its development, deployment, use and decommission. These processes must be done safely, following current legislation, and incorporating the social needs towards having greater well-being over the agents and environment involved. Standards, frameworks and ethical imperatives—which are also considered a backbone structure for legal considerations—drive the development process of new AI assets for industry. However, given the lack of concrete standards and robust AI legislation, the gap between ethical principles and actionable approaches is still considerable. Different organisations have developed various methods based on multiple ethical principles to facilitate practitioners developing AI components worldwide. Nevertheless, these approaches can be driven by a self-claimed ethical shell or without a clear understanding of the impacts and risks involved in using their AI assets. The manufacturing sector has produced standards since 1990’s to guarantee, among others, the correct use of mechanical machinery, workers security, and environmental impact. However, a revision is needed to blend these with the needs associated with AI’s use. We propose using a vertical-domain framework for the manufacturing sector that will consider ethical perspectives, values, requirements, and well-known approaches related to risk management in the sector.
  • Item
    A responsible AI framework: pipeline contextualisation
    (Springer, 2022-04-19) Vyhmeister, Eduardo; Castane, Gabriel; Östberg, P.-O.; Thevenin, Simon
    Incorporating ethics and values within the life cycle of an AI asset means securing its development, deployment, use, and decommission under these perspectives. These approaches depend on the market domain where AI is operational – considering the interaction and the impact on humans if any process does not perform as expected – and the legal compliance, both required to ensure adequate fulfilment of ethics and values. Specifically, in the manufacturing sector, standards were developed since the 1990’s to guarantee, among others, the correct use of mechanical machinery, systems robustness, low product variability, workers safety, system security, and adequate implementation of system constraints. However, it is challenging to blend the existing practices with the needs associated with deployments of AI in a trustworthy manner. This document provides an extended framework for AI Management within the Manufacturing sector. The framework is based on different perspectives related to responsible AI that handle trustworthy issues as risk. The approach is based on the idea that ethical considerations can and should be handled as hazards. If these requirements or constraints are not adequately fulfilled and managed, it is expected severe negative impact on different sustainable pillars. We are proposing a well-structured approach based on risk management that would allow implementing ethical concerns in any life cycle stages of AI components in the manufacturing sector. The framework follows a pipeline structure, with the possibility of being extended and connected with other industrial Risk Management Processes, facilitating its implementation in the manufacturing domain. Furthermore, given the dynamic condition of the regulatory state of AI, the framework allows extension and considerations that could be developed in the future.