Virtual Assistant Research Articles

LAMB: An Open-Source Software Framework to Create Artificial Intelligence Assistants Deployed and Integrated into Learning Management Systems

This paper presents LAMB (Learning Assistant Manager and Builder), an innovative open-source software framework designed to create AI-powered Learning Assistants tailored for integration into learning management systems. LAMB addresses critical gaps in existing educational AI solutions by providing a framework specifically designed for the unique requirements of the education sector. It introduces novel features, including a modular architecture for seamless integration of AI assistants into existing LMS platforms and an intuitive interface for educators to create custom AI assistants without coding skills. Unlike existing AI tools in education, LAMB provides a comprehensive framework that addresses privacy concerns, ensures alignment with institutional policies, and promotes using authoritative sources. LAMB leverages the capabilities of large language models and associated generative artificial intelligence technologies to create generative intelligent learning assistants that enhance educational experiences by providing personalized learning support based on clear directions and authoritative fonts of information. Key features of LAMB include its modular architecture, which supports prompt engineering, retrieval-augmented generation, and the creation of extensive knowledge bases from diverse educational content, including video sources. The development and deployment of LAMB were iteratively refined using a minimum viable product approach, exemplified by the learning assistant: “Macroeconomics Study Coach,” which effectively integrated lecture transcriptions and other course materials to support student inquiries. Initial validations in various educational settings demonstrate the potential that learning assistants created with LAMB have to enhance teaching methodologies, increase student engagement, and provide personalized learning experiences. The system's usability, scalability, security, and interoperability with existing LMS platforms make it a robust solution for integrating artificial intelligence into educational environments. LAMB's open-source nature encourages collaboration and innovation among educators, researchers, and developers, fostering a community dedicated to advancing the role of artificial intelligence in education. This paper outlines the system architecture, implementation details, use cases, and the significant benefits and challenges encountered, offering valuable insights for future developments in artificial intelligence assistants for any sector.

Коммуникационные стратегии для междисциплинарных команд с использованием дизайн-мышления и персонализированного обучения на основе компьютерных технологий в высших учебных заведениях

The paper discusses how Design Thinking and Technology-Enhanced Learning can support multidisciplinary teams in Higher Education working on creative projects. In particular, it proposes the integration of Design Thinking and AI-driven technologies into educational methodology to improve communication, engagement, personalized learning, and interactivity of students. The results of this approach are to address the challenges of Higher Education consisting in students’ assessment of the learning process, developing their creativity, critical thinking, and problem-solving skills. This educational project is designed in collaboration with the Department of Industrial Design and the Learning Mall at Xi’an Jiaotong-Liverpool University. The methodology includes a literature review on Design Thinking and analysis of surveys from the Design School students at Xi’an Jiaotong-Liverpool University and the AI assistants. Dynamic tools such as Articulate Rise 360 and AI have made it possible to visualize concepts and create interactive content for learners. The results include two educational prototypes that introduce a new thinking model to Design Thinking methodology and share experiments with interactive technological features. Applying this approach, teachers can create an environment conducive to the development of skills needed in the 21st century.

Artificial Intelligence Plays Crucial Role in Education Sector of Assam

“AI is a mirror, reflection not only our intellect, but our values and fears” Artificial intelligence (AI) is shaping the future of technology and revolutionizing our education system. Due to evolution of artificial intelligence, we have seen the drastic change in our educational sector throughout the globe. It indicates a positive signal for present and future generations of our country and also throughout the globe. Artificial Intelligence (AI) can play a crucial role in the school functioning process, streamlining and optimizing the procedure for both institutions and applicants. Through AI-driven algorithms, schools can efficiently sift through a large pool of applicants, identifying the most suitable candidates based on predefined criteria such as student’s enrollment according to their academic performance, extracurricular activities, and personal attributes. One of the most remarkable advantages of employing AI in the admission process is its ability to eliminate human bias, ensuring fairness and equal opportunities for all applicants. AI systems are programmed to assess candidates solely based on their qualifications and merit, reducing the influence of subjective factor, viz., race, gender, or socioeconomic background. We have seen the drastic changes in case of new admission in our School and College for last 3 to 4 years in the state of Assam and country as well. Moreover, AI facilitates personalized and efficient communication with applicants, providing them with updates on their application status and guiding them through the admission process. Virtual assistants powered by AI can promptly address queries from applicants, offering them the support they need. Furthermore, AI enables predictive analysis, allowing schools to forecast future trends in admission and tailor their strategies accordingly. By analyzing past admission data and trends, AI systems can provide valuable insights into the preferences and behaviors of prospective students, helping schools make informed decisions and develop targeted recruitment strategies. AI is revolutionizing the school admission process by making it more efficient, transparent, and fair. By leveraging AI technologies, schools can streamline their admission procedures, improve the candidate experience, and ultimately ensure that the most qualified and deserving students are admitted. In Assam, the education department of Government of Assam has introduced Shiksha Setu App to enhance communication between students, parents, teachers, and educational institutions. It facilitates access to various educational resources, attendance tracking of both teachers and students, exam schedules, leave for teachers, and performance reports. Its significance lies in improving transparency, efficiency, and accessibility in the whole education system of Assam, and as result contributing to better student outcomes and parental involvement.

EVOLUTION AND IMPACT OF ARTIFICIAL INTELLIGENCE IN CHATBOTS

Artificial Intelligence (AI) is reshaping the world and technology, no longer a futuristic concept but a present reality in our daily lives. Businesses are rapidly adopting AI to automate processes, leading to the creation of intelligent agents known as chatbots. These chatbots have revolutionized business communication and significantly enhanced customer satisfaction. This paper explores the history and development platforms of chatbots, examining their integration into daily life despite often undefined purposes. Chatbots use pattern recognition to generate responses, raising questions about moral issues, security, and legitimacy due to their growing popularity. A key focus is on ChatKanoon, a multilingual AI chatbot designed for the Indian legal system. This study analyzes its impact on the Indian legal framework and its potential to revolutionize legal aid in India and other developing countries. Additionally, the research paper covers the basic features, connectivity, services offered, accuracy, and technology providers of chatbots and virtual assistants implemented by Indian banks.

Artificial Intelligence-Enabled Intelligent Assistant for Personalized and Adaptive Learning in Higher Education

This paper presents a novel framework, artificial intelligence-enabled intelligent assistant (AIIA), for personalized and adaptive learning in higher education. The AIIA system leverages advanced AI and natural language processing (NLP) techniques to create an interactive and engaging learning platform. This platform is engineered to reduce cognitive load on learners by providing easy access to information, facilitating knowledge assessment, and delivering personalized learning support tailored to individual needs and learning styles. The AIIA’s capabilities include understanding and responding to student inquiries, generating quizzes and flashcards, and offering personalized learning pathways. The research findings have the potential to significantly impact the design, implementation, and evaluation of AI-enabled virtual teaching assistants (VTAs) in higher education, informing the development of innovative educational tools that can enhance student learning outcomes, engagement, and satisfaction. The paper presents the methodology, system architecture, intelligent services, and integration with learning management systems (LMSs) while discussing the challenges, limitations, and future directions for the development of AI-enabled intelligent assistants in education.

Artificial Intelligence-Powered Technologies For Independent Living Among Older Adults: A Review

Abstract Background The ageing populations in Ireland and around the world has led to an increased focus on technologies that support independent living for older adults. Artificial intelligence (AI) has emerged as a promising solution, with various AI-powered technologies being proposed to assist their daily lives. This review aims to synthesize the findings of studies exploring AI-powered technologies for independent living among older adults. Methods A systematic literature search was conducted using relevant databases, including PubMed, IEEE Xplore, and Google Scholar. The search terms included “artificial intelligence” and “independent living”. Studies published between 2009 and 2023 that investigated AI-powered technologies for independent living among older adults were included in the analysis. Results The included studies investigated various AI-powered technologies including tablets, wearable devices like smartwatches, web portals for carers, Internet of Things (IoT) solutions, user-centered design considerations, the integration of AI with sociology and healthcare, smart home technology, and ambient information systems. The pooled results indicated that AI-powered technologies can improve independent living outcomes for older adults. Benefits included real-time monitoring and health deterioration recognition, fall detection, personalised care, cognitive assistance and reduced isolation. User-centered design approaches and the integration of AI with sociology and healthcare were also found to be essential factors in the successful implementation of these technologies. Conclusion This analysis provides evidence supporting the effectiveness of AI-powered technologies in promoting independent living among older adults. IoT solutions and smart home technology appear to be particularly promising. However, the successful implementation of these technologies requires a multidisciplinary approach, incorporating user-centered design and the integration of AI with sociology and healthcare. Further research is needed to explore the long-term impact of AI-powered technologies on the well-being and autonomy of older adults.

Transformer-Based Regression Models for Assessing Reading Passage Complexity: A Deep Learning Approach in Natural Language Processing

Natural Language Processing (NLP) is a vital area in deep learning, widely applied in tasks like text classification, virtual assistants, speech recognition, and autocorrect features in digital devices. It allows machines to understand and generate human language, enhancing user interactions with software. This paper presents a deep learning model using the Transformer architecture for a regression task to predict the complexity of reading passages based on text excerpts. By leveraging the Transformer’s capability to identify complex patterns in text, the model achieves a relative error rate of about 10%. The paper also examines how different architectural choices influence model performance, focusing on one-hot encoding and embeddings. While one-hot encoding provides a simple text representation, embeddings offer a richer, more nuanced understanding of word relationships. The findings highlight the significance of model design and data representation in optimizing NLP tasks, providing insights for future advancements in the field.

AI assistant is my new best friend! Role of emotional disclosure, performance expectations and intention to reuse

In this modern era, high-tech companies are launching their AI assistants, considering their role in shaping consumer behavior. This research sheds light by building a conceptual framework using dual process theory to determine the impact of AI assistant advantage on user engagement and user emotional disclosure, subsequently influencing the intention to reuse AI with the moderating role of performance expectation. Using a random sampling method, a structured questionnaire was used for data collection from 644 consumers. The findings show that AI assistant advantages positively impact user engagement, and user emotional disclosure increases the intention to reuse AI assistants. This impact of user engagement and user emotional disclosure, along with performance expectations, maximizes the reuse intention of AI. Managers and marketers in the AI environment can insinuate the study methods to increase the intention of reuse and may transform their marketing strategies to promote their businesses using AI more effectively.

Can ChatGPT be an author? Generative AI creative writing assistance and perceptions of authorship, creatorship, responsibility, and disclosure

AbstractThe increasing use of Generative AI raises many ethical, philosophical, and legal issues. A key issue here is uncertainties about how different degrees of Generative AI assistance in the production of text impacts assessments of the human authorship of that text. To explore this issue, we developed an experimental mixed methods survey study (N = 602) asking participants to reflect on a scenario of a human author receiving assistance to write a short novel as part of a 3 (high, medium, or low degrees of assistance) X 2 (human or AI assistant) factorial design. We found that, for a human author, the degree of assistance they receive matters for our assessments of their level of authorship, creatorship, and responsibility, but not what or who rendered that assistance, although it was more important to disclose human rather than AI assistance. However, in our assessments of the assisting agent, human assistants were viewed as warranting higher rates of authorship, creatorship, and responsibility, compared to AI assistants rendering the same level of support. These results help us to better understand emerging norms around collaborative human-AI generated text, with implications for other types of collaborative content creation.

Enhancing Clinical Accuracy of Medical Chatbots with Large Language Models.

The rapid advancement of large language models (LLMs) has opened up new possibilities for transforming healthcare practices, patient interactions, and medical report generation. This paper explores the application of LLMs in developing medical chatbots and virtual assistants that prioritize clinical accuracy. We propose a novel multi-turn dialogue model, including adjusting the position of layer normalization to improve training stability and convergence, employing a contextual sliding window reply prediction task to capture fine-grained local context, and developing a local critical information distillation mechanism to extract and emphasize the most relevant information. These components are integrated into a multi-turn dialogue model that generates coherent and clinically accurate responses. Experiments on the MIMIC-III and n2c2 datasets demonstrate the superiority of the proposed model over state-of-the-art baselines, achieving significant improvements in perplexity, BLEU-2, recall at K scores, medical entity recognition, and response coherence. The proposed model represents a significant step in developing reliable and contextually relevant multi-turn medical dialogue systems that can assist patients and healthcare professionals.

Estimates of the accuracy of identification of a nonlinear dynamic system using step test signals

Machine learning (ML) has become widespread in everyday life. On its basis, programs with artificial intelligence work, on the basis of which many virtual assistants have evolved. ML plays an important role in various spheres of activity of many enterprises. ML helps to automate many processes, simplifying the functioning of the company. Named Entity Recognition (NER) models allow to automatically select and search for information according to certain criteria in mobile data extracted, for example, by the logistic method. Support for NER by Python models makes it possible to flexibly program specific requests that are generated in the forensic examination process. Open source creates a unique opportunity to continuously improve the model by training it on datasets. A powerful NER package is the spaCy framework, which helps to simplify data and extract detailed information from input data, train a model, perform model tuning, and more. spaCy is compatible with 64-bit CPython 3.7+ and runs on Unix/Linux, macOS/OS X and Windows. The latest spaCy releases are available over pip and conda.

The Use of AI in Enhancing Patient Communication

Artificial Intelligence (AI) has rapidly evolved in the healthcare sector, significantly transforming patient-provider communication. This paper examines the application of AI, particularly through tools like chatbots and virtual assistants, to enhance patient interaction and address communication barriers. It examines how AI-based tools improve patient accessibility, streamline information exchange, and aid in patient care, particularly in countries like Australia. The study also highlights the benefits and challenges associated with AI-driven communication, including efficiency, patient satisfaction, privacy concerns, and ethical considerations. Ultimately, it suggests that AI technology offers promising solutions for improving patient communication but requires further research and careful implementation to overcome challenges. Keywords: AI in healthcare, patient communication, chatbots, virtual assistants, telemedicine, healthcare technology.

Extended Reality Educational System with Virtual Teacher Interaction for Enhanced Learning

Advancements in technology that can reshape educational paradigms, with Extended Reality (XR) have a pivotal role. This paper introduces an interactive XR intelligent assistant featuring a virtual teacher that interacts dynamically with PowerPoint presentations using OpenAI’s ChatGPT API. The system incorporates Azure Cognitive Services for multilingual speech-to-text and text-to-speech capabilities, custom lip-syncing solutions, eye gaze, head rotation and gestures. Additionally, panoramic images can be used as a sky box giving the illusion that the AI assistant is located at another location. Findings from three pilots indicate that the proposed technology has a lot of potential to be used as an additional tool for enhancing the learning process. However, special care must be taken into privacy and ethical issues.

Cognitive Assistance Systems in Intralogistics - User studies with augmented reality and an AI chatbot

Cognitive Assistance Systems in Intralogistics - User studies with augmented reality and an AI chatbot

A mathematical formulation of learner cognition for personalised learning experiences

The paper focuses on the assessment of cognitive skills within Virtual Learning Environments (VLEs). In response to the global shift to remote learning amid the COVID-19 pandemic, VLEs, which include learning management systems (LMS) and online collaboration platforms, gained prominence. The proposed work leverages an established Cattell–Horn–Carroll (CHC) theory to propose eight metrics, which collectively form a part of Cognitive Evaluation Metrics (CEM). The proposed metrics introduce a novel computational approach for multimode evaluation of learners’ cognitive abilities for each learning task within a learning environment. The paper details the formalism for the evaluation of the metrics and makes a contribution towards the potential of the proposed methodology to evaluate cognitive abilities. Additionally, the work implements CEM integration into the learner module of a Game-Based Learning (GBL) environment. Analysis of simulations in the GBL environment, along with statistical analysis, provides insights into the normal distribution of cognitive metrics. This reveals diverse ranges in various abilities such as long or short term memory, working memory, reasoning, attention, and processing speed. The paper also explores the impact of virtual assistants, which highlights their limited relevance to enhance cognitive abilities but serve as valuable on-demand support resources.

Virtual flight deck crew assistance utilizing artificial intelligence methods to interpret NOTAMs: a user acceptance study

Virtual flight deck crew assistance utilizing artificial intelligence methods to interpret NOTAMs: a user acceptance study

Revolutionizing Maternal Health: The Role of Artificial Intelligence in Enhancing Care and Accessibility.

Maternal health remains a critical global health challenge, with disparities in access to care and quality of services contributing to high maternal mortality and morbidity rates. Artificial intelligence (AI) has emerged as a promising tool for addressing these challenges by enhancing diagnostic accuracy, improving patient monitoring, and expanding access to care. This review explores the transformative role of AI in maternal healthcare, focusing on its applications in the early detection of pregnancy complications, personalized care, and remote monitoring through AI-driven technologies. AI tools such as predictive analytics and machine learning can help identify at-risk pregnancies and guide timely interventions, reducing preventable maternal and neonatal complications. Additionally, AI-enabled telemedicine and virtual assistants are bridging healthcare gaps, particularly in underserved and rural areas, improving accessibility for women who might otherwise face barriers to quality maternal care. Despite the potential benefits, challenges such as data privacy, algorithmic bias, and the need for human oversight must be carefully addressed. The review also discusses future research directions, including expanding AI applications in maternal health globally and the need for ethical frameworks to guide its integration. AI holds the potential to revolutionize maternal healthcare by enhancing both care quality and accessibility, offering a pathway to safer, more equitable maternal outcomes.

VividWav2Lip: High-Fidelity Facial Animation Generation Based on Speech-Driven Lip Synchronization

Speech-driven lip synchronization is a crucial technology for generating realistic facial animations, with broad application prospects in virtual reality, education, training, and other fields. However, existing methods still face challenges in generating high-fidelity facial animations, particularly in addressing lip jitter and facial motion instability issues in continuous frame sequences. This study presents VividWav2Lip, an improved speech-driven lip synchronization model. Our model incorporates three key innovations: a cross-attention mechanism for enhanced audio-visual feature fusion, an optimized network structure with Squeeze-and-Excitation (SE) residual blocks, and the integration of the CodeFormer facial restoration network for post-processing. Extensive experiments were conducted on a diverse dataset comprising multiple languages and facial types. Quantitative evaluations demonstrate that VividWav2Lip outperforms the baseline Wav2Lip model by 5% in lip sync accuracy and image generation quality, with even more significant improvements over other mainstream methods. In subjective assessments, 85% of participants perceived VividWav2Lip-generated animations as more realistic compared to those produced by existing techniques. Additional experiments reveal our model’s robust cross-lingual performance, maintaining consistent quality even for languages not included in the training set. This study not only advances the theoretical foundations of audio-driven lip synchronization but also offers a practical solution for high-fidelity, multilingual dynamic face generation, with potential applications spanning virtual assistants, video dubbing, and personalized content creation.

Molecular interactions of photosystem I and ZIF-8 in bio-nanohybrid materials.

Bio-nanohybrid devices featuring natural photocatalysts bound to a nanostructure hold great promise in the search for sustainable energy conversion. One of the major challenges of integrating biological systems is protecting them against harsh environmental conditions while retaining, or ideally enhancing their photophysical properties. In this mainly computational work we investigate an assembly of cyanobacterial photosystem I (PS I) embedded in a metal-organic framework (MOF), namely the zeolitic imidazolate framework ZIF-8. This complex has been reported experimentally [Bennett et al., Nanoscale Adv., 2019, 1, 94] but so far the molecular interactions between PS I and the MOF remained elusive. We show via absorption spectroscopy that PS I remains intact throughout the encapsulation-release cycle. Molecular dynamics (MD) simulations further confirm that the encapsulation has no noticeable structural impact on the photosystem. However, the MOF building blocks frequently coordinate to the Mg2+ ions of chlorophylls in the periphery of the antenna complex. High-level quantum mechanical calculations reveal charge-transfer interactions, which affect the excitonic network and thereby may reversibly change the fluorescence properties of PS I. Nevertheless, our results highlight the stability of PS I in the MOF, as the reaction center remains unimpeded by the heterogeneous environment, paving the way for applications in the foreseeable future.

Conversational Artificial Intelligence: A Catalyst for Rethinking Assessment in Higher Education

Conversational Artificial Intelligence has disrupted higher education by fundamentally altering its landscape. Fuelled by natural language processing and machine learning this technology has gained widespread adoption particularly since the release of ChatGPT in November 2022. As universities embrace digital transformation, assessment practices must evolve to align with the capabilities of Artificial Intelligence-driven chatbots and virtual assistants. This paper explores how conversational artificial intelligence impacts higher education, in particular, student assessment. A fundamental shift in assessment and evaluation of student competencies is necessary to not only consider knowledge retention but also critical thinking, communication, and adaptability skills. A review of the literature was conducted to understand how assignments should change due to the emergence of this disruptive technology. Conversational Artificial Intelligence and its application within the higher education context is uncertain, with disparate practices—in terms of ethical consideration and understanding—across the sector. A case study was conducted in which MSc Management students undertaking a specific module were tasked to use three Artificial Intelligence tools in their report writing of a business, to verify the sources and content provided by the Artificial Intelligence tool, and to critically evaluate the process as well as the output received for each prompt. The paper proposes a collaborative approach to navigate the ethical implementation and utilization of conversational Artificial Intelligence in higher education, advocating for the co-creation of guidelines through forums like Knowledge Cafés, stressing the need to rethink student assignments and its assessment and the adoption of artificial intelligence technologies by students for assignments.