Intelligent Interface Research Articles

Designing a Tactile Document UI for 2D Refreshable Tactile Displays: Towards Accessible Document Layouts for Blind People

Understanding document layouts is vital for enhancing document exploration and information retrieval for sighted individuals. However, for blind and visually impaired people, it becomes challenging to have access to layout information using typical assistive technologies such as screen readers. In this paper, we examine the potential benefits of presenting documents on two-dimensional (2D) refreshable tactile displays. These displays enable the tactile perception of 2D data, offering the advantage of dynamic and interactive functionality. Despite their potential, the development of user interfaces (UIs) for such displays has not advanced significantly. Thus, we propose a design of an intelligent tactile user interface (TUI), incorporating touch and audio feedback to represent documents in a tactile format. Our exploratory study for evaluating this approach revealed satisfaction from participants with the experience of directly viewing documents in their true form, rather than relying on screen-reading interpretations. Additionally, participants offered recommendations for incorporating additional features and refining the approach in future iterations. To facilitate further research and development, we have made our dataset and models publicly available.

Synthesizing a three Layer Architectural Framework for Adaptive Intelligent User Interfaces for the Disabled Community

Knowledge acquisition has been a bottleneck in the design for efficient User Interfaces for Disabled Community. The best suited interfaces have been oriented towards adaptability that is the User Interface needs to adapt and configure itself according to the needs and likes of the user. Such user interfaces can arouse interest in the mind of the disabled and motivate them to become an asset to the nation, and use their intellect to contribute to the society. This study pioneers an innovative approach, aiming to develop User Interfaces (UIs) for the Disabled Community. The research introduces a comprehensive three-layer architectural framework employing Learning, Trust, and Knowledge Models. Unlike conventional approaches, this Architectural Framework is designed to learn not only from the Disabled but also from their Assistants/Guides, employing principles of knowledge engineering. While the former offers static context, the latter contributes dynamic insights by observing behaviors, responses, and actions of the Disabled. This symbiotic relationship forms the foundational basis for developing intelligent adaptive UI’s that not only accommodate but actively engage and motivate the Disabled Community. The proposed research methodology involves a meticulous gathering of data through extensive user studies and interactions. By using the Human Computer Interface technology, the study aims to develop a robust framework capable of comprehensively understanding the preferences, needs, and nuances of disabled users. The expected outcomes include the development of a prototype adaptive UI, validated through rigorous testing and feedback from the disabled community. Additionally, the study anticipates contributing a comprehensive set of guidelines and best practices for designing intelligent adaptive UIs, ensuring comfort and ease for impaired users, boosting their confidence and encouraging greater involvement in socio-development activities.

Research On the Design of Public Transit Services for The Elderly in China

As China enters an aging society, the elderly in China are increasingly becoming an important user group of public transportation. This study uses service design thinking to optimize the inclusiveness of Chinese elderly people's travel by bus and subway, and explores the feasibility of applying service design thinking to the field of public transportation. This paper adopts the observation method, with Guangzhou and Beijing as the research areas. The researchers conduct service design research based on the entire process of elderly travel, summarize the travel needs and pain points of elderly passengers, optimize the station guidance system, intelligent interface and service platform, make the public transportation service environment more friendly, and thus make the public transportation service environment more inclusive. Analyze the passenger flow, contact points, and stakeholders of the station, draw character portraits and journey maps, and output service design strategies to improve the travel experience of Chinese elderly passengers. In summary, this study aims to improve the convenience of Chinese elderly passengers taking public transportation and provide theoretical support for the transformation and optimization of China's public transportation services.

Accessing information provided via artificial intelligence regarding reverse and anatomic total shoulder arthroplasty

BackgroundThe purpose of this study is to analyze the quality, accuracy, and readability of information provided by an artificial intelligence (AI) interface ChatGPT (OpenAI, San Francisco). We searched ChatGPT for commonly asked questions by patients regarding anatomic total shoulder arthroplasty (aTSA) and reverse total shoulder arthroplasty (rTSA). MethodsChatGPT was used to answer 30 commonly asked questions by patients regarding aTSA and rTSA, inputted as “total shoulder replacement” and “reverse shoulder replacement”. These questions were categorized based on the Rothwell criteria into Fact, Policy, and Value. The answers generated were analyzed for quality, accuracy, and readability using the DISCERN scale, JAMA benchmark criteria, Flesch-Kincaid Reading Ease Score (FRES) and Grade Level (FKGL). ResultsFor both rTSA and aTSA the DISCERN score for Fact questions was 57, Policy questions was 61, and for Value questions was 58 (all were all considered “good”). The JAMA benchmark criteria was 0, representing the lowest score for Fact, Policy, and Value questions for both rTSA and aTSA questions. The FRES score for the aTSA answers for Fact was 15.15, for Policy was 11.14, and for Value questions was 10.95. The FRES score for rTSA questions for Fact is 48.02, Policy is 12.51, and Value is 17.22. The FKGL for aTSA answer for Fact was 17.48, Policy was 17.72 and Value was 17.96. The FKGL for rTSA questions for Fact are 8.10, Policy is 17.27, and Value is 16.56. ConclusionOverall, the quality of answers provided by AI open model, ChatGPT was considered “good.” The information provided had lower reliability, and lack of information regarding funding and disclosures. Most of the information generated by ChatGPT was also found to have the readability of “academic level text”, while Fact related information on reverse shoulder arthroplasty was found to have the readability of 9th grade level, which may be too complex for most patients. Overall, these results indicate that ChatGPT can provide correct answers to questions about aTSA and rTSA, although we would caution patients from utilizing this resource due to the lack of citations and complexity of the output that ChatGPT provides. Importantly, all answers provided by AI suggested reaching out to physicians to get more accurate and personalized advise, to factor into the shared decisions making model.

Generative AI as a Strategic Intelligent User Interface for Human-AI Collaboration

Generative AI as a Strategic Intelligent User Interface for Human-AI Collaboration

AI-driven English Language Learning Program and Academic Writing Integrity in the Era of Intelligent Interface

AI-driven English Language Learning Program and Academic Writing Integrity in the Era of Intelligent Interface

Dynamic Covalent Bonds Regulate Zinc Plating/Stripping Behaviors for High-Performance Zinc Ion Batteries.

Artificial interfaces provide a comprehensive approach to controlling zinc dendrite and surface corrosion in zinc-based aqueous batteries (ZABs). However, due to consistent volume changes during zinc plating/stripping, traditional interfacial layers cannot consistently adapt to the dendrite surface, resulting in uncontrolled dendrite growth and hydrogen evolution. Herein, dynamic covalent bonds exhibit the Janus effect towards zinc deposition at different current densities, presenting a holistic strategy for stabilizing zinc anode. The PBSC intelligent artificial interface consisting of dynamic B-O covalent bonds is developed on zinc anode to mitigate hydrogen evolution and restrict dendrite expansion. Owing to the reversible dynamic bonds, PBSC exhibits shape self-adaptive characteristics at low current rates, which rearranges the network to accommodate volume changes during zinc plating/stripping, resisting hydrogen evolution. Moreover, the rapid association of B-O dynamic bonds enhances mechanical strength at dendrite tips, presenting a shear-thickening effect and suppressing further dendrite growth at high current rates. Therefore, the assembled symmetrical battery with PBSC maintains a stable cycle of 4500 hours without significant performance degradation and the PBSC@Zn||V2O5 pouch cell demonstrates a specific capacity exceeding 170 mAh g-1. Overall, the intelligent interface with dynamic covalent bonds provides innovative approaches for zinc anode interfacial engineering and enhances cycling performance.

Dynamic Covalent Bonds Regulate Zinc Plating/Stripping Behaviors for High‐Performance Zinc Ion Batteries

AbstractArtificial interfaces provide a comprehensive approach to controlling zinc dendrite and surface corrosion in zinc‐based aqueous batteries (ZABs). However, due to consistent volume changes during zinc plating/stripping, traditional interfacial layers cannot consistently adapt to the dendrite surface, resulting in uncontrolled dendrite growth and hydrogen evolution. Herein, dynamic covalent bonds exhibit the Janus effect towards zinc deposition at different current densities, presenting a holistic strategy for stabilizing zinc anode. The PBSC intelligent artificial interface consisting of dynamic B−O covalent bonds is developed on zinc anode to mitigate hydrogen evolution and restrict dendrite expansion. Owing to the reversible dynamic bonds, PBSC exhibits shape self‐adaptive characteristics at low current rates, which rearranges the network to accommodate volume changes during zinc plating/stripping, resisting hydrogen evolution. Moreover, the rapid association of B−O dynamic bonds enhances mechanical strength at dendrite tips, presenting a shear‐thickening effect and suppressing further dendrite growth at high current rates. Therefore, the assembled symmetrical battery with PBSC maintains a stable cycle of 4500 hours without significant performance degradation and the PBSC@Zn||V2O5 pouch cell demonstrates a specific capacity exceeding 170 mAh g−1. Overall, the intelligent interface with dynamic covalent bonds provides innovative approaches for zinc anode interfacial engineering and enhances cycling performance.

AutoRL X: Automated Reinforcement Learning on the Web

Reinforcement Learning (RL) is crucial in decision optimization, but its inherent complexity often presents challenges in interpretation and communication. Building upon AutoDOViz — an interface that pushed the boundaries of Automated RL for Decision Optimization — this paper unveils an open-source expansion with a web-based platform for RL. Our work introduces a taxonomy of RL visualizations and launches a dynamic web platform, leveraging backend flexibility for AutoRL frameworks like ARLO and Svelte.js for a smooth interactive user experience in the front end. Since AutoDOViz is not open-source, we present AutoRL X, a new interface designed to visualize RL processes. AutoRL X is shaped by the extensive user feedback and expert interviews from AutoDOViz studies, and it brings forth an intelligent interface with real-time, intuitive visualization capabilities that enhance understanding, collaborative efforts, and personalization of RL agents. Addressing the gap in accurately representing complex real-world challenges within standard RL environments, we demonstrate our tool's application in healthcare, explicitly optimizing brain stimulation trajectories. A user study contrasts the performance of human users optimizing electric fields via a 2D interface with RL agents’ behavior that we visually analyze in AutoRL X, assessing the practicality of automated RL. All our data and code is openly available at: https://github.com/lorifranke/autorlx .

Performance of an online chat-based artificial intelligence interface for patient education on atrial fibrillation ablation

Abstract Background Chat-based artificial intelligence (AI) web interfaces that aim to mimic human conversation have increasing utilization in healthcare to help with simple tasks such as scheduling appointments, and even more complex tasks such as providing patient educational responses to COVID-19 questions as done by the World Health Organization.1 Chat-based AI has also been shown to provide accurate responses to cardiovascular disease prevention questions.2 Its ability to provide patient education for more complex treatments like atrial fibrillation (AF) ablation has not been explored. Purpose To evaluate the quality of a popular chat-based AI program’s answers to patient questions about AF ablation. Methods Twenty commonly asked questions ("prompts") regarding AF ablation were entered into ChatGPT (Chat Generative Pre-trained Transformer), a large language model-based AI program (Fig. 1). Prompts were written in plain language; technical terms were avoided except for "radiofrequency", "cryoablation" and "pulsed field ablation" (PFA). SMOG readability calculator was used to assess responses for difficulty and grade-level, as healthcare organizations recommend ≤ 8th-grade level complexity for patient information. Response content was graded by 3 experienced cardiac electrophysiologists as "reasonable", "missing important elements/some inaccuracies" or "misleading/inappropriate". Responses are presented in mean +/- standard deviation and percentages. Results Responses averaged 118±67 words (Fig. 1). Of 20 responses, 17 (85%) were deemed reasonable, 3 (15%) missing important elements/some inaccuracies and none inappropriate or misleading; 16 (80%) emphasized discussion of issues with the healthcare team (Fig. 2). Responses missing important elements/some inaccuracies were those about risks/complications of ablation [missing phrenic nerve palsy, atrioesophageal fistula (AEF), potential need for emergent cardiac surgery or pacemaker, death], concerning symptoms post-procedure (missing symptoms of hematoma, AEF, stroke), and that PFA is not yet approved for use in all regions. Average reading grade level of responses was 13.8 (college level or "professional"): 17 (85%) responses were 12th grade level, 11 (55%) were college-level or higher, and 6 (30%) were college-graduate level ("extremely difficult"). None were ≤ 8th grade level (Fig. 2). Conclusions A majority of ChatGPT responses to common patient questions about AF ablation had reasonable content quality that frequently emphasized the importance of discussion with the healthcare team. However, responses to more difficult questions regarding risks, symptoms of potential complications, or newer technology missed important details; more than half of responses required college-level reading skills. While use of Chat-AI for patient education on EP topics appears promising, patients should be advised to use caution. Further AI training to improve content and readability should be explored.

Accelerating Scientific Paper Skimming with Augmented Intelligence Through Customizable Faceted Highlights

Scholars need to keep up with an exponentially increasing flood of scientific papers. To aid this challenge, we introduce Scim, a novel intelligent interface that helps scholars skim papers to rapidly review and gain a cursory understanding of its contents. Scim supports the skimming process by highlighting salient content within a paper, directing a scholar’s attention. These automatically-extracted highlights are faceted by content type, evenly distributed across a paper, and have a density configurable by scholars. We evaluate Scim with an in-lab usability study and a longitudinal diary study, revealing how its highlights facilitate the more efficient construction of a conceptualization of a paper. Finally, we describe the process of scaling highlights from their conception within Scim, a research prototype, to production on over 521,000 papers within the Semantic Reader, a publicly-available augmented reading interface for scientific papers. We conclude by discussing design considerations and tensions for the design of future skimming tools with augmented intelligence.

Impact of example-based XAI for neural networks on trust, understanding, and performance

The purpose of this study is to examine the impact of an example-based explainable artificial intelligence (XAI) interface on trust, understanding, and performance in highly-technical populations. XAI studies often focus on general users in low-risk domains. This study examined the impact of showing the closest matches from the training data from two classes on trust, understanding, and performance for highly-technical users in a high-risk domain. We found that providing example-based explanations significantly increased trust and understanding without decreasing performance. Showing the most similar examples from two classes increased trust more than showing examples from only one class. Participants did not treat different classes the same. The most important features for predicting how well an interface was understood were the helpfulness of the provided examples and the person's trust in the human-machine team. We found priming of highly-technical participants to be particularly important for running XAI studies to mitigate the fear of their jobs being impacted.

A Step Toward Better Care: Understanding What Caregivers and Residents in Assisted Living Facilities Value in Health Monitoring Systems

The past several decades have seen significant advances in monitoring older adults' health and well-being. However, creating viable, practical monitoring systems for informing caregivers requires understanding which behaviors and signs to track and what approaches best present that information. To investigate how technology can be leveraged to better augment caregivers' workflows, we take a multi-stage, qualitative approach to gain insights into the needs of caregivers and the older adults receiving care. Specifically, we use a series of domain expert interviews, cognitive walkthroughs, and semi-structured interviews with residents, and we synthesize our takeaways using thematic analysis at each phase. Our results show that this type of monitoring technology has great potential to reduce the effort needed by caregivers to complete their responsibilities and communicate with their teams. Additionally, we found that older adults are receptive to the technology but their privacy and autonomy must be prioritized for the sake of their mental wellbeing. These insights will facilitate greater intelligent interface development for Person-Centered Care by identifying important design considerations and vital features that require system support.

New Approach to SCADA System Screen Configuration Based on the Model of Oil and Gas Pipeline Network

INTRODUCTION： With the continuous progress of science and technology, the monitoring and control of oil and gas pipeline networks have become more and more critical; SCADA systems, as a kind of technology widely used in industrial control, play a key role. The screen configuration of the SCADA system is the core part of its user interface, which is directly related to the operator's mastery of the status of the pipeline network. In order to improve the monitoring efficiency and reduce the operation risk, this study is devoted to exploring a new method of SCADA system screen configuration based on the oil and gas pipeline network model.PURPOSE: The purpose of this study is to develop an innovative SCADA system screen configuration method to present the operating status of the oil and gas pipeline network more intuitively and efficiently. The design based on the pipeline network model aims to enhance the operators' understanding of essential information, such as pipeline network topology, fluid flow, etc., so as to make monitoring and control more intelligent.METHODS: The study adopts a new method of SCADA system screen configuration based on the oil and gas pipeline network model. First, the topology, sensor data, and control nodes of the oil and gas pipeline network are comprehensively modelled. Then, through the design principle of human-computer interaction, the modelling results are integrated into the screen configuration of the SCADA system to realize the intuitive presentation of information. At the same time, advanced visualization technology is introduced so that the operators can understand the real-time changes in the pipe network status more clearly.RESULTS: After experimental verification, the new method shows significant advantages in oil and gas pipeline network monitoring. The operators can recognize the abnormalities of the pipeline network more quickly and accurately through the SCADA system screen configuration, which improves the efficiency of troubleshooting and treatment. The visualized interface design makes the operation more intuitive and reduces the possibility of operating errors, thus improving the safety and reliability of the pipeline network.CONCLUSION: The new method of SCADA system screen configuration based on the oil and gas pipeline network model has achieved significant results in improving monitoring efficiency and reducing operational risks. Through a more intuitive and intelligent interface design, operators can have a more comprehensive understanding of the operating status of the pipeline network, which provides practical support for rapid response and decision-making. This approach introduces new ideas to the field of oil and gas pipeline network monitoring, which is of positive significance for improving the overall performance of the system. Future work can be carried out to optimize the interface design further and expand the applicable scenarios.

Location-Independent Intelligent Interface Customized to the Aid and Response of the Differently Abled

Today, the most feasible and easy form of Human-Computer Interaction (HCI) is the use of mobile applications. Mobile applications have become an integral part of our day-to-day lives reaching out to each corner of society and catering to the problems. The applications available are customized, but the incorporation of intelligence especially for the disabled to assist their lives is absent. This motivates the research work specified in this paper is non-commercial application development for society. Designing applications that are highly scalable and intelligent to minimize problems faced by differently abled, is explicitly covered here. The proposed system makes use of Speech-To-Text and Text-To-Speech conversion techniques for the back end and provides enhanced scalability by allowing users to regulate the functionality of the application, customized based on their preferred region, topic, and time stamps. Applications and devices meant for the differently abled do exist, however, most of them have unidirectional and singular functionality with minimum customizability. In most cases, very complicated hardware systems are associated with the proposed work which in turn makes it expensive to maintain. The proposed application aims to offer voice-based functionality automation, remote health monitoring, and pattern recognition for recommendation systems, explicitly for the visually impaired and the solitary elderly. The reading of remote health monitoring is close to the actual value with a standard deviation of 1.45% or 0.76 on the average which validates the working methodology adopted.

Towards a general user model to develop intelligent user interfaces

The way end-users interact with a system plays a crucial role in the high acceptance of software. Related to this, the concept of Intelligent User Interfaces has emerged as a solution to learn from user interactions with the system and adapt interfaces to the user’s characteristics and preferences. However, existing approaches to designing intelligent user interfaces are limited by their user models, which are not capable of representing each and every user characteristic valid for any context. This work aims to address this limitation by presenting a user model that can abstractly represent a wide set of user characteristics in any context of interaction. The model is based on a synthesis of previous works that have proposed specific user models. After the analysis of these works, a more sophisticated user model has been defined, including some required characteristics not existing in previous works. This model has been validated with 62 real end-users who have expressed the users’ characteristics that they consider as relevant to adapt the interaction. The results show that most of these characteristics can be represented by the proposed user model. This user model is the first step towards creating intelligent user interfaces that can adapt interactions to users with similar characteristics and preferences in similar contexts.

A conceptual framework for context-driven self-adaptive intelligent user interface based on Android

Adaptive User Interface (AUI) can change its layout, appearance, and/or elements based on the needs of its user requirements and current usage context. The AUIs are used in state-of-the-art software products, applications for mobile devices, and websites. Moreover, AUI is an emerging research field in a mobile context, as it can enhance usability, performance, and user satisfaction. This study aims to propose a conceptual framework for developing a real-time self-adaptive user interface based on the Android Operating System (OS). Furthermore, the focus is on developing the core algorithms for the modules of the proposed framework. To evaluate the performance of the proposed framework, three case studies have been designed based on the daily and weekly activities of the user. Moreover, an expert-based validation approach is employed to obtain the expert’s feedback regarding the proposed framework. The result indicates that the proposed framework helps improve user satisfaction and experience by making an intelligent mobile device interface. The results of the framework’s evaluation and validation show the proposed framework’s feasibility and effectiveness. We conclude that the current work is beneficial in filling the identified research gap. Moreover, this research shows the significance of an adaptive interface in an Android OS-based context. In addition, it not only helps in improving the user interest and satisfaction but also enhances the overall performance of the mobile device.

Intelligent Optimization Method of Human–Computer Interaction Interface for UAV Cluster Attack Mission

In modern warfare, it is often necessary for the operator to control the UAV cluster from a ground control station to perform an attack task. However, the absence of an effective method for optimizing the human–computer interface in ground control stations for UAV clusters leads to usability difficulties and heightens the probability of human errors. Hence, we propose an optimization framework for human–computer interaction interfaces within UAV ground control stations, rooted in interface-essential elements. Specifically, the interface evaluation model was formulated by combining the Salient, Effort, Expectancy, and Value (SEEV) framework with the essential factor mutation cost of the quantified interface. We employed the SEEV–ant colony algorithm to address the challenge of optimizing the interface design within this context. For a typical UAV cluster attack mission, we optimized the human–computer interaction interfaces of the three mission stages based on the proposed SEEV-AC model. We conducted extensive simulation experiments in these optimized interfaces, and used eye-movement indicators to evaluate the effectiveness of the interface optimization model. Based on the experimental results, divergence is reduced by 11.59%, and the fitness of the optimized interface is increased from 1.34 to 3.42. The results show that the proposed intelligent interface optimization method can effectively improve the interface design and reduce the operator’s workload.

Ontology-Based Intelligent Interface Personalization for Protection Against Phishing Attacks

Millions of users on the Internet have fallen into phishing website traps. Detection tools are designed to warn users against such attacks, but often fail to achieve this purpose. One crucial reason behind this is that users rarely have a chance to interact and build a relationship with a detection tool that stealthily runs at the backend. A warning message on a rarely seen interface from such a tool hardly inspires users’ trust in its authenticity and accuracy. In this study, we propose an ontology-based intelligent interface personalization (OBIIP) design for the warning interfaces of phishing website detection tools. We first constructed an ontology of warning interface elements (OWIE), which is a comprehensive knowledgebase for warning interface design. We then used OWIE in the design and creation of an OBIIP prototype and assessed it in a laboratory experiment and an online experiment. The results show the significant value of OBIIP in improving users’ performance in terms of self-protection against website phishing attacks and building a stronger relationship with the detection tool in terms of trust in and use of the tool.

Modern linguistic resources and IT applications for the Tatar language: Regional practices

The issue of preserving the language of an ethnic group as a language of communication, as well as a carrier of cultural codes, has now acquired particular urgency and relevance. How to preserve and develop a language in the conditions of globalization and widespread digitalization, in the conditions of coming, and in many ways already real, information chaos and in conditions when in the near future most of the known languages are threatened with complete extinction. Obviously, one of the reliable and promising solutions is embedding a language in the digital space as a language of accumulation, processing and transmission of information; a language of communication in the global Internet network. Currently, in the Republic of Tatarstan, a set of organizational and policy measures has been almost completely implemented and the necessary information and technological base has been created to ensure full functioning of the Tatar language in computer technologies, including business and management spheres, publishing, educational activities, linguistic research and development. Another effective and very promising activity is the research and use of the language as a cognitive-conceptual tool that can enrich the mental and spiritual space of civilization as a linguistic-semiotic resource that has the necessary potential for creating new knowledge processing technologies and an intelligent interface. This paper presents the experience of research and practical activities of the Institute of Applied Semiotics of the Academy of Sciences of the Republic of Tatarstan in one of the important areas of artificial intelligence called “Natural Language Processing”. Research and development are carried out in three theoretical and applied areas: 1) Tatar national localization of infocommunication technologies, 2) Development of software tools, systems and technologies for natural language processing and creation of linguistic resources, 3) Creation of new intelligent information processing technologies based on the research the cognitive potential of the Tatar language.