Explanation User Interfaces: A Systematic Literature Review

Artificial Intelligence (AI) is one of the major technological advancements of this century, bearing incredible potential for users through AI-powered applications and tools in numerous domains. Being often black-box (i.e., its decision-making process is unintelligible), developers typically resort to eXplainable Artificial Intelligence (XAI) techniques to interpret the behaviour of AI models to produce systems that are transparent, fair, reliable, and trustworthy. However, presenting explanations to the user is not trivial and is often left as a secondary aspect of the system's design process, leading to AI systems that are not useful to end-users. This paper presents a Systematic Literature Review on Explanation User Interfaces (XUIs) to gain a deeper understanding of the solutions and design guidelines employed in the academic literature to effectively present explanations to users. To improve the contribution and real-world impact of this survey, we also present a framework for Human-cEnteRed developMent of Explainable user interfaceS (HERMES) to guide practitioners and academics in the design and evaluation of XUIs.

Explanation-Driven Interventions for Artificial Intelligence Model Customization: Empowering End-Users to Tailor Black-Box AI in Rhinocytology

The integration of Artificial Intelligence (AI) in modern society is heavily shifting the way that individuals carry out their tasks and activities. Employing AI-based systems raises challenges that designers and developers must address to ensure that humans remain in control of the interaction process, particularly in high-risk domains. This article presents a novel End-User Development (EUD) approach for black-box AI models through a redesigned user interface in the Rhino-Cyt platform, a medical AI-based decision-support system for medical professionals (more precisely, rhinocytologists) to carry out cell classification. The proposed interface empowers users to intervene in AI decision-making process by editing explanations and reconfiguring the model, influencing its future predictions. This work contributes to Human-Centered AI (HCAI) and EUD by discussing how explanation-driven interventions allow a blend of explainability, user intervention, and model reconfiguration, fostering a symbiosis between humans and user-tailored AI systems.

Towards a Novel Ultrasound System Based on Low-Frequency Feature Extraction From a Fully-Printed Flexible Transducer

Ultrasound is a key technology in healthcare, and it is being explored for non-invasive, wearable, continuous monitoring of vital signs. However, its widespread adoption in this scenario is still hindered by the size, complexity, and power consumption of current devices. Moreover, such an application demands adaptability to human anatomy, which is hard to achieve with current transducer technology. This paper presents a novel ultrasound system prototype based on a fully printed, lead-free, and flexible polymer ultrasound transducer, whose bending radius promises good adaptability to the human anatomy. Our application scenario focuses on continuous blood flow monitoring. We implemented a hardware envelope filter to efficiently transpose high-frequency ultrasound signals to a lower-frequency spectrum. This reduces computational and power demands with little to no degradation in the task proposed for this work. We validated our method on a setup that mimics human blood flow by using a flow phantom and a peristaltic pump simulating 3 different heartbeat rhythms: 60, 90 and 120 beats per minute. Our ultrasound setup reconstructs peristaltic pump frequencies with errors of less than 0.05 Hz (3 bpm) from the set pump frequency, both for the raw echo and the enveloped echo. The analog pre-processing showed a promising reduction of signal bandwidth of more than 6x: pulse-echo signals of transducers excited at 12.5 MHz were reduced to about 2 MHz. Thus, allowing consumer MCUs to acquire and elaborate signals within mW-power range in an inexpensive fashion.