Ai Approaches For Designing And Evaluating Interactive Intelligent Systems

Designing, building, and evaluating Interactive and Intelligent Systems (IIS) has highly impacted the progress of Artificial Intelligence (AI) techniques due to advancements in the fields of Deep Learning (DL) and Natural Language Processing (NLP). This book presents in a structured way several practical use cases of the interplay between IIS and DL/NLP, from cognitive assistants, adaptive navigation systems, virtual reality, offensive comment and cyberbullying detection, 3D modelling, and driving behaviour detection. The convergence of AI and Human-Computer Interaction (HCI) has been proven to foster the IIS development that nowadays represents the most used context by actively integrating AI techniques in merely any layer of modern applications. The main goal of this book is to provide a practical reference with a rich set of approaches and applications consisting of selected and revised papers from the International Conference on Human-Computer Interaction (RoCHI) 2022 that was held on 6-7 October 2022 at the University of Craiova, Romania. The book addresses researchers and practitioners with experience in IIS and AI (mainly DL and NLP) who want to study successfully developed workflows and applications that may be useful in their attempts to tackle issues from their contexts. Although the book nicely integrates concepts from various areas, each chapter may be considered a standalone topic with its research issue, proposed approach, experimental results, and discussions.

To design and develop capable, dependable, and affordable intelligent systems, their performance must be measurable. Scienti?c methodologies for standardization and benchmarking are crucial for quantitatively evaluating the performance of eme- ing robotic and intelligent systems’ technologies. There is currently no accepted standard for quantitatively measuring the performance of these systems against user-de?ned requirements; and furthermore, there is no consensus on what obj- tive evaluation procedures need to be followed to understand the performance of these systems. The lack of reproducible and repeatable test methods has precluded researchers working towards a common goal from exchanging and communic- ing results, inter-comparing system performance, and leveraging previous work that could otherwise avoid duplication and expedite technology transfer. Currently, this lack of cohesion in the community hinders progress in many domains, such as m- ufacturing, service, healthcare, and security. By providing the research community with access to standardized tools, reference data sets, and open source libraries of solutions, researchers and consumers will be able to evaluate the cost and be- ?ts associated with intelligent systems and associated technologies. In this vein, the edited book volume addresses performance evaluation and metrics for intel- gent systems, in general, while emphasizing the need and solutions for standardized methods. To the knowledge of the editors, there is not a single book on the market that is solely dedicated to the subject of performance evaluation and benchmarking of intelligent systems.

to date,="" research="" on="" interactive="" intelligent="" systems="" has="" largely="" focused="" either="" the="" realisation="" of="" systems’="" capabilities="" or="" cognitive="" processes="" and="" behaviour="" their="" users.="" with="" rapid="" development="" internet-based="" technologies,="" design="" is="" facing="" many="" emerging="" issues="" challenges="" such="" as="" investigating="" ways="" that="" artificial="" agents="" human="" intelligence="" can="" collaborate="" for="" better="" performance,="" understanding="" user="" requirements="" processes,="" safeguarding="" privacy,="" etc.="" divThis book provides the latest research findings and developments in the field of interactive intelligent systems, addressing diverse areas such as autonomous systems, Internet and cloud computing, pattern recognition and vision systems, mobile computing and intelligent networking, and e-enabled systems. It gathers selected papers from the International Conference on Intelligent and Interactive Systems and Applications (IISA2016) held on June 25–26, 2016 in Shanghai, China./divdivbr/divdivInteractive intelligent systems are among the most important multi-disciplinary research and development domains of artificial intelligence, human–computer interaction, machine learning and new Internet-based technologies. Accordingly, these systems embrace a considerable number of application areas such as autonomous systems, expert systems, mobile systems, recommender systems, knowledge-based and semantic web-based systems, virtual communication environments, and decision support systems, to name a few./divdivbr/divdivTo date, research on interactive intelligent systems has largely focused either on the realisation of the systems’ capabilities or on the cognitive processes and/or behaviour of their users. With the rapid development of Internet-based technologies, the design of interactive intelligent systems is facing many emerging issues and challenges such as investigating the ways that artificial agents and human intelligence can collaborate for better performance, understanding user requirements and user cognitive processes, safeguarding user privacy, etc. /divdivbr

Many current AI and machine learning algorithms and data and information fusion processes attempt in software to estimate situations in our complex world of nested feedback loops. Such algorithms and processes must gracefully and efficiently adapt to technical challenges such as data quality induced by these loops, and interdependencies that vary in complexity, space, and time. To realize effective and efficient designs of computational systems, a Systems Engineering perspective may provide a framework for identifying the interrelationships and patterns of change between components rather than static snapshots. We must study cascading interdependencies through this perspective to understand their behavior and to successfully adopt complex system-of-systems in society. This book derives in part from the presentations given at the AAAI 2021 Spring Symposium session on Leveraging Systems Engineering to Realize Synergistic AI / Machine Learning Capabilities. Its 16 chapters offer an emphasis on pragmatic aspects and address topics in systems engineering; AI, machine learning, and reasoning; data and information fusion; intelligent systems; autonomous systems; interdependence and teamwork; human-computer interaction; trust; and resilience.

This book on data visualization is the eighth in a planned series of books that examine key topics (e.g., learner modeling, instructional strategies, authoring, domain modeling, assessment, team tutoring, self-improving systems, data visualization, and competency based scenario design) in intelligent tutoring system (ITS) design. This book focuses on data visualization and how it is applied in ITSs. The chapters within this book specifically examine topics in relationship to the Generalized Intelligent Framework for Tutoring (GIFT) (Sottilare, Brawner, Goldberg & Holden, 2012; Sottilare, Brawner, Sinatra, & Johnston, 2017). GIFT is an open-source, domain-independent, modular, service-oriented architecture for ITSs. The design of GIFT allows for reusability, reduction in authoring time, and reducing the skill level needed to create an ITS. GIFT provides functionality to create ITSs, distribute ITSs to learners through the Cloud, conduct research to evaluate ITSs, and to examine instructional outcomes. Data visualization is an important topic for ITSs, as there are many different users of the systems (including learners, instructors, researchers, subject matter experts). The data that is collected by the ITS can be organized and displayed in a number of different ways. The current book includes a general discussion of how data visualizations can be applied in ITSs, as well as detailed specific examples of existing implementations, and technical details related to incorporating data visualization in ITSs. We believe this book can be used as a design tool for data visualization interfaces in ITSs.

The four-volume set LNCS 11583, 11584, 11585, and 11586 constitutes the proceedings of the 8th International Conference on Design, User Experience, and Usability, DUXU 2019, held as part of the 21st International Conference, HCI International 2019, which took place in Orlando, FL, USA, in July 2019. The total of 1274 papers and 209 posters included in the 35 HCII 2019 proceedings volumes was carefully reviewed and selected from 5029 submissions. DUXU 2019 includes a total of 167 regular papers, organized in the following topical sections: design philosophy; design theories, methods, and tools; user requirements, preferences emotions and personality; visual DUXU; DUXU for novel interaction techniques and devices; DUXU and robots; DUXU for AI and AI for DUXU; dialogue, narrative, storytelling; DUXU for automated driving, transport, sustainability and smart cities; DUXU for cultural heritage; DUXU for well-being; DUXU for learning; user experience evaluation methods and tools; DUXU practice; DUXU case studies.

Provides a valuable overview of human-machine interaction in technological systems, with particular emphasis on recent advances in theory, experimental and analytical research, and applications related to man-machine systems. Topics covered include: Automation and Operator - task analysis, decision support, task allocation, management decision support, supervisory control, artificial intelligence, training and teaching, expert knowledge; System Concept and Design - software ergonomics, fault diagnosis, safety, design concepts; Man-machine Interface - interface design, graphics and vision, user adaptive interfaces; Systems Operation - process industry, electric power, aircraft, surface transport, prostheses and manual control. Contains 53 papers and three discussion sessions.