1,721,007 research outputs found
Understanding each-other: Engineering challenges and opportunities for users and systems in the deep learning era
Full text linkIn this paper, we discuss the impact of Deep Learning (DL) techniques in the present and future of the interactive system engineering. On the one hand, the support for more complex vocabularies offers opportunities in better shaping the communication between the user and the system. On the other hand, we identify challenges related to the lack of transparency and explainability in the trained models, which have a negative impact on system understanding for both developers and users
DG3: Exploiting Gesture Declarative Models for Sample Generation and Online Recognition
No full textIn this paper, we introduce DG3, an end-to-end method for exploiting gesture interaction in user interfaces. The method allows to declaratively model stroke gestures and their sub-parts, generating the training samples for the recognition algorithm. In addition, we extend the algorithms of the $-family for supporting the online (i.e., real-time ) stroke recognition and their parts, as declared in the models. Finally, we show that the method outperforms existing approaches for online recognition and has comparable accuracy with offline methods after a few gesture segments
Split and mill: User assisted height-field block decomposition for fabrication
No full textWe present here Split and Mill: an interactive system for the manual volume decomposition of free form shapes. Our primary purpose is to generate portions respecting the properties allowing to mill them with a 3-axis milling machine. We show that a manual decomposition is competitive with the automatic partitioning when the user is skilled enough. We, thus, think that our tool can be beneficial for the practitioners in the field, and we release it as free software
Mitigating Human Errors and Cognitive Bias for Human-AI Synergy in Cybersecurity
Full text linkCybersecurity advancements necessitate effective measures to combat rising and sophisticated threats. Artificial Intelligence (AI) and eXplainable AI (XAI) solutions have demonstrated significant capabilities in predicting and responding to cyber threats. Moreover, integrating AI components with Intelligent User Interfaces (IUI) has been explored as a promising approach, emphasizing user experience and interaction policies. Despite these advancements, the primary challenge remains addressing human errors, particularly those induced by cognitive biases. This paper provides an overview of possible recommendations on AI integration with cybersecurity systems and human cognitive bias mitigation solutions
Explaining Through the Right Reasoning Style: Lessons Learnt
No full textCurrent eXplainable Artificial Intelligence (XAI) techniques assist individuals in interpreting AI recommendations. However, research primarily focuses on assessing users’ comprehension of explanations, neglecting important factors influencing decision support, such as whether the explanation uses the correct reasoning style to help the user understand the AI’s advice. In the last two years, our research aimed to fill this gap by examining the effects of factors such as user uncertainty, AI correctness, and the interplay between AI confidence and explanation logic styles in classification tasks. In this paper, we summarise the lesson learnt from this research and discuss its impact on the engineering of AI-based decision support systems
Integrating declarative models and HMMs for online gesture recognition
No full textIn the last years, the introduction of new, precise and pervasive tracking devices has contributed to the popularity of gestural interaction. In general, the effectiveness of such interfaces depends on two components: the algorithm used for accurately recognizing the user movements and the guidance provided to users while executing gestures. In this paper, we discuss a work in progress research for connecting these two components and increasing their effectiveness: the recognition algorithm supports the implementation of feedback the and feed-forward mechanisms, providing information on the identified gesture parts in real time, while developers define complex gestures starting from simple primitives
Applying Long-Short Term Memory Recurrent Neural Networks for Real-Time Stroke Recognition
No full textThis note discusses how to build a real-Time recognizer for stroke gestures based on Long Short Term Memory Recurrent Neural Networks. The recognizer provides both the gesture class prediction and the completion percentage estimation for each point in the stroke while the user is performing it. We considered the stroke vocabulary of the N datasets, and we defined four different architectures. We trained them using synthetic data, and we assessed the recognition accuracy on the original N datasets. The results show an accuracy comparable with state of the art approaches classifying the stroke when completed, and a good precision in the completion percentage estimation
XRSpotlight: Example-based Programming of XR Interactions using a Rule-based Approach
Full text linkResearch on enabling novice AR/VR developers has emphasized the need to lower the technical barriers to entry. This is often achieved by providing new authoring tools that provide simpler means to implement XR interactions through abstraction. However, novices are then bound by the ceiling of each tool and may not form the correct mental model of how interactions are implemented. We present XRSpotlight, a system that supports novices by curating a list of the XR interactions defined in a Unity scene and presenting them as rules in natural language. Our approach is based on a model abstraction that unifies existing XR toolkit implementations. Using our model, XRSpotlight can find incomplete specifications of interactions, suggest similar interactions, and copy-paste interactions from examples using different toolkits. We assess the validity of our model with professional VR developers and demonstrate that XRSpotlight helps novices understand how XR interactions are implemented in examples and apply this knowledge in their projects
First InternationalWorkshop on Detection and Mitigation of Cyber attacks that exploit human vuLnerabilitiES (DAMOCLES)
No full textToday, the pervasive influence of technology has created significant cybersecurity challenges, exacerbated by human error that is often overlooked in system design. Reports show that up to 95% of cyber attacks are due to human factors, such as susceptibility to phishing and lax software maintenance. Italian public administrations (PAs) face heightened cyber risks due to underinvestment compared to the private sector. To address these challenges, the DAMOCLES research project provides a tailored framework focusing on Human Vulnerability Assessment (HVA) and Human Vulnerability Mitigation (HVM). HVA activities include behavior-based assessments and controlled cyber-Attack testing using Digital Twins (DT) to mirror user behavior. HVM uses insights from HVA to develop customized training programs, supported by non-coding approaches for easy adoption. DAMOCLES aims to improve cybersecurity in Italian government agencies by effectively addressing human-related security vulnerabilities
- …
