Search for: All records

Augmentative and alternative communication (AAC) devices are used by many people around the world who experience difficulties in communicating verbally. One form of AAC device which is especially useful for minimally verbal autistic children in developing language and communication skills is the visual scene display (VSD). VSDs use images with interactive hotspots embedded in them to directly connect language to real-world contexts which are meaningful to the AAC user. While VSDs can effectively support emergent communicators (i.e., those who are beginning to learn how to use symbolic communication), their widespread adoption is impacted by how difficult these devices are to configure. We developed a prototype that uses generative AI to automatically suggest initial hotspots on an image to help non-experts efficiently create visual scene displays (VSDs). We conducted a within-subjects user study to understand how effective our prototype is in supporting non-expert users, specifically pre-service speech-language pathologists (SLPs) (N=16) who are not familiar with VSDs as an AAC intervention. Pre-service SLPs are actively studying to become clinically certified SLPs and have domain-specific knowledge about language and communication skill development. We evaluated the effectiveness of our prototype based on creation time, quality, and user confidence. We also analyzed the relevance and developmental appropriateness of the automatically generated hotspots and how often users interacted with (e.g., editing or deleting) the generated hotspots. Our results were mixed with SLPs becoming more efficient and confident. However, there were multiple negative impacts as well, including over-reliance and homogenization of communication options. The implications of these findings reach beyond the domain of AAC, especially as generative AI becomes more prevalent across domains, including assistive technology. Future work is needed to further identify and address these risks associated with integrating generative AI into assistive technology. 

Not AvailableMany conversational user interfaces facilitate linear conversations with turn-based dialogue, similar to face-to-face conversations between people. However, digital conversations can afford more than simple back-and-forth; they can be layered with interaction techniques and structured representations that scaffold exploration, reflection, and shared understanding between users and AI systems. We introduce Feedstack, a speculative interface that augments feedback conversations with layered affordances for organizing, navigating, and externalizing feedback. These layered structures serve as a shared representation of the conversation that can surface user intent and reveal underlying design principles. This work represents an early exploration of this vision using a research-through-design approach. We describe system features and design rationale, and present insights from two formative (n=8, n=8) studies to examine how novice designers engage with these layered supports. Rather than presenting a conclusive evaluation, we reflect on Feedstack as a design probe that opens up new directions for conversational feedback systems. 

Explanations have increasingly been incorporated into intelligent systems to offer insights into the underlying AI models. In this paper, we investigate the impact of AI-generated visual explanations on users’ decision-making processes during an image matching task. Our work examines how these explanations affect correctness, timing, and confidence and explores the role of AI literacy in user behavior. We conducted a mixed-methods user study with 54 participants who were tasked to identify hotels from images using a specialized intelligent system. Participants were randomly assigned to use the system with or without visual explanation capabilities. Results showed that visual explanations did not affect the accuracy of the decision or the confidence of the user in image matching tasks. Participants with high-AI literacy outperformed those with lower literacy, but engaged less with explanations. Distinct matching strategies emerged between high-AI and low-AI participants, with high-AI participants systematically examining high-ranked images and using the explanation for verification purposes, while low-AI participants followed more exhaustive approaches. 

Grid displays are the most common form of augmentative and alternative communication device recommended by speech-language pathologists for children. Grid displays present a large variety of vocabulary which can be beneficial for a users’ language development. However, the extensive navigation and cognitive overhead required of users of grid displays can negatively impact users’ ability to actively participate in social interactions, which is an important factor of their language development. We present a novel interaction technique for grid displays, Predictive Anchoring, based on user interaction theory and language development theory. Our design is informed by existing literature in AAC research, presented in the form of a set of design goals and a preliminary design sketch. Future work in user studies and interaction design are also discussed. 

Not AvailableSoftware Defined Networks (SDN) have been proposed as a possibledevelopment for next generation networking technology. In a SDN,Virtual Network Functions (VNFs) are used to replace the functionsof traditional middleboxes. All of these VNFs can be controlledfrom a centralized controller, which comes with its own securityconcerns. However, there are many benefits that come from havinga centralized controller as traffic can be easily controlled from asingle point. This makes it interesting to further study securitywhen it concerns SDN. This work looks to test intrusion detectionsystem (IDS) performance under different configurations in a SDNin order to make security in SDN more robust. In this work, wetake two IDSs, Snort and Suricata, and test their performance underdifferent configurations and traffic loads. We test four differentconfigurations: single, chain, parallel, and cross. Our findings seemto suggest that the cross configuration has the best performance ofthese IDS configurations.