Human-computer Collaboration Research Articles

Artificial Intelligence Applications in Medical Mycology: Current and Future

The application of artificial intelligence (AI) in the medical mycology field represents a new era in the diagnosis and management of fungal infections. AI technologies, particularly machine learning (ML) and deep learning (DL) methods, enhance diagnostic accuracy by leveraging large datasets and complex algorithms. This review examines current applications of AI in laboratory and clinical settings for fungal diagnostics. In the laboratory, AI models analyze microscopic images from potassium hydroxide (KOH) examinations, fungal culture tests, and histopathologic slides, which improves the detection rates of fungal pathogens significantly. In the clinical setting, AI assists the diagnosis of fungal infections using medical images, exhibiting high efficacy in binary classification tasks. However, challenges include small sample sizes, class imbalances, reliance on expert-labeled data, and the black box nature of AI models. Explainable AI offers potential solutions by providing human-comprehensible insights into AI decisionmaking processes. In addition, human-computer collaboration can enhance diagnostic accuracy, particularly for less experienced clinicians. The development of generative AI models, e.g., large language models and multimodal AI, promises to create extensive datasets and integrate various data sources for comprehensive diagnostics. Addressing these limitations through prospective clinical validation and continuous feedback will be essential for realizing the full potential of AI in medical mycology.

Strategies and Implementation of Exploring the Integration of Artificial Intelligence in Ideological and Political Education

The rapid evolution of artificial intelligence (AI) technology heralds significant transformations in education, especially in ideological and political education, where traditional teaching methods are being reassessed due to mounting challenges. This paper embarks on a mission to investigate how AI technology can revolutionize the delivery of political science courses by adopting a “human-computer collaboration” model. The central aim is to enhance the effectiveness and quality of teaching while stimulating students' critical thinking skills. It delves into the landscape and potential applications of AI technology in this field, emphasizing the role of intelligent teaching assistants in augmenting teachers' capabilities for lesson planning and delivery. This study not only outlines the design and implementation of AI tools but also emphasizes their potential to foster a more engaging and intelligent learning environment. By doing so, it contributes to the discourse on leveraging AI to advance teaching platforms and classroom practices, thereby enhancing the educational experience.

Research on the Efficiency Improvement of Human-Machine Collaboration in Manufacturing Production Process

In modern manufacturing, human-computer collaboration has become an important means to improve productivity and product quality. However, the existing human-computer collaboration process and human-computer interaction interface design still has many deficiencies, which affects its efficiency and safety. This paper aims to explore how to improve the efficiency and safety of human-computer collaboration in the production process by optimising the human-computer collaboration process and designing the human-computer interaction interface. It is found that the efficiency and safety of human-computer collaboration can be significantly improved by optimising the collaboration process, improving the working environment and standardising the workflow through the lean manufacturing theory, and adopting a user-friendly interface design with high information visualisation and ease of operation.

Ethical Failures of Generative AI in News Production, Implications and Countermeasures

Generative AI is recognized by the media (people) for its high-quality dialogue, complex reasoning and other emergent capabilities in content generation, and human-machine collaboration will gradually become the norm in news production, with application advantages in news production, news distribution and other news survival links. While generative AI assists news production and promotes innovation in news reporting, it also has problems such as providing inaccurate facts, opaque algorithms, and controversial boundaries of application, etc. For this reason, the media should regulate the ethics of human-computer collaboration in terms of optimizing the editing process, disclosing information about algorithms, and setting the boundaries of application of machines.

GuidingBand: Evaluating Speed, Precision and Accuracy of a Vibrotactile Hand Guidance System

Abstract Computerized tactile guidance systems can potentially help in human visual perception tasks such as identifying a desired object in a collection of similar objects. We designed a wrist-wearable tactile guidance system called GuidingBand that provides vibrational cues to help the user pick visual targets out of an array. We conducted three studies to systematically investigate the interplay of machine-led tactile guidance and human visual perception. The studies involve presenting visual targets to users on a screen and giving them visual search tasks. In Study 1, we identified the error rate of our guidance system. We presented participants (N=20) with arrays of identical, square targets to pick from, progressively reduced the target sizes and evaluated error rates for each size. Notably, we observed a 4% error rate at a target size of 10 mm. In Study 2, we compared the error rate of the guidance system with and without the help of human visual perception in a visual search task. We constructed a task that involved showing users an array of distractor rectangles (set sizes 2 to 10) varying only in length and asked them to identify the correct target that was previously shown to them. Participants (N=13) had fewer errors when they tried to identify targets with tactile guidance alone, followed by guidance and perception combined and perception alone. In Study 3, we had the same task as Study 2 but the distractor set sizes were larger (varying from 4 to 28), we had more participants (N=30) and measured errors and task time. While perception alone was the fastest, it was also the most error prone. The combined mode was faster and less error prone than guidance only mode, as expected, indicating that human–computer collaboration yielded the best performance.

Aesthetic Education in the Age of Artificial Intelligence: Challenges, Opportunities, and Prospects

The rapid development of artificial intelligence is profoundly affecting various fields, and aesthetic education is no exception. This paper explores the opportunities and prospects of aesthetic education in the age of artificial intelligence. It first discusses the challenges that artificial intelligence brings to aesthetic education, including the automation of artistic creation and the virtualization of aesthetic experience. It then analyzes the opportunities brought by artificial intelligence to aesthetic education, such as improving teaching efficiency, enriching teaching methods, and cultivating interdisciplinary abilities. Finally, it looks forward to the development prospects of aesthetic education in the age of artificial intelligence, emphasizing the reshaping of humanistic values, strengthening human-computer collaboration, and promoting interdisciplinary integration.

Hybrid Intelligence: Design for Sustainable Multiverse via Integrative Cognitive Creation Model through Human–Computer Collaboration

The unprecedented development of artificial intelligence (AI) makes it possible for computers to imitate and surpass human intelligence (HI). Hybrid intelligence is the result of the co-evolution of AI and HI and has huge application potential in promoting the sustainable development of human society. This study starts from the similarities and differences between biological neural networks and artificial neural networks, compares the cognitive foundations of human intelligence and artificial intelligence, highlights the difference and connection between AI and HI, and puts forward the necessity and inevitability of their co-evolution to achieve hybrid intelligence with complementary advantages. Hybrid intelligence stands to become the pivotal force driving purposeful and planned sustainable creative behavior in the artificial intelligence era. This study proposes a design cognitive creation model based on human–computer collaboration that considers computational design thinking as the central concept. Moreover, the paradigm shift of design under hybrid intelligence intervention are explored from five aspects: “tool evolution”, “response mode”, “output result”, “iterative optimization” and “system innovation”. Finally, this article constructs a creative intervention mechanism of design creation driven by hybrid intelligence and discusses its role playing in the design activities of sustainable multiverse construction in the future. The proposal of the multiverse model transcends the confines of the metaverse’s virtual worldview and embraces sustainable development for value guidance. It advocates a future trajectory for humanity that hinges on technological progress, fostering a prosperous, balanced, and harmonious coexistence between the natureverse, socialverse, and digitalverse. This approach is not only rational and scientific, but also inherently sustainable.

Extended Reality (XR) Training in the Construction Industry: A Content Review

As modern information technology advances and equipment devices update, extended reality (XR) technologies, including virtual reality (VR), augmented reality (AR), and augmented virtuality (AV) have witnessed an increasing use and application in construction training. This review aims to comprehensively examine the evolution of XR training in the construction domain. To achieve this, a systematic literature review of 74 journal papers from the Scopus database was conducted. This paper outlines the progression of XR training from 2009 to 2023, detailing related technologies like development platforms, display devices, and input devices. The literature review reveals that XR application in construction training spans five main areas: (1) safety management, (2) skill/knowledge acquisition, (3) equipment operation, (4) human–computer collaboration, and (5) ergonomics/postural training. Additionally, this review explores the impact of trainee roles on XR training outcomes and identifies the challenges faced by XR technology in construction training applications. The findings of this literature review are hoped to assist researchers and construction engineering trainers in understanding the latest advancements and challenges in XR, thereby providing valuable insights for future research.

Enhancing Efficiency with an AI-Augmented Clinician in Neurology.

Integrating artificial intelligence (AI) technologies into neurology promises increased patient access, engagement, and quality of care, as well as improved quality of work life for clinicians. While most studies have focused on comparing AI models to expert performance, we argue for a more practical approach: demonstrating how AI can augment clinical practice. This article presents a framework for pragmatic AI augmentation, addressing the shortage in neurology practices, exploring the potential of AI in opportunistic screening, and encouraging the concept of AI serving as a "co-pilot" in neurology. We discuss recommendations for future studies designed to emphasize human-computer collaboration, ensuring AI enhances rather than replaces clinical expertise.

Empowering Vocational Education New Media Marketing Teaching Reform and Practical Exploration with AIGC

The AIGC has revolutionized traditional content production models and has had a disruptive impact on the new media industry, posing serious challenges to talent in new media marketing. Based on this current situation, this study identifies deficiencies in the teaching content, teaching methods, teaching staff, and teaching evaluation of new media marketing in vocational education, and proposes the following four suggestions for reforming vocational education in new media marketing through the empowerment of AIGC. Firstly, adjust talent cultivation programs to enable rapid iteration and upgrading of AIGC-enabled content. Secondly, empower teaching methods with AIGC to prompt and guide transformation. Thirdly, promote human-computer collaboration to enhance the cutting-edge technology of the teaching team through AIGC. Fourthly, incorporate AIGC into teaching evaluation criteria and enrich the teaching evaluation system.

THE INFLUENCE MECHANISM OF AI TECHNOLOGY LEARNING ANXIETY IN THE HUMAN-COMPUTER COLLABORATION CONTEXT: THE MODERATING EFFECT OF UNCERTAINTY AVOIDANCE AND THE MEDIATING EFFECT OF SELF-EFFICACY

Taking 636 enterprise employees who use robots or intelligent technology products to assist in their work as the research object, with self-efficacy as the mediator variable and uncertainty avoidance as the moderating variable, the artificial mechanism of action of intelligent technology learning anxiety (AI technology learning anxiety). The research results show that: (1) There is a positive correlation between human-computer collaboration and employees’ AI technology learning anxiety, that is, the higher the degree of human-computer collaboration, the easier it is for employees to have AI technology learning anxiety or the stronger their sense of AI technology learning anxiety. (2) Uncertainty avoidance moderates the positive relationship between human-computer collaboration and AI technology learning anxiety, that is, the higher the uncertainty avoidance, the stronger the positive relationship between human-computer collaboration and AI technology learning anxiety.When uncertainty avoidance is low, AI technology learning anxiety is weakened. (3) Self-efficacy plays a mediating role in the process of human-machine collaboration affecting AI technology learning anxiety.

Intentional Understanding and Human-Computer Collaboration: A Smart Pen for Solid Geometry Teaching

The current teaching mode in geometry mainly focuses on two-dimensional levels, and the teaching tools utilized are static and not interactive. This paper proposes the use of a smart pen for three-dimensional geometry experimental teaching and a multimodal intention understanding and human-computer collaboration algorithm for the smart pen. The primary innovations of this paper lie in the development of a smart pen and a virtual platform for geometry education tailored for geometry experimental instruction. This system can promptly perceive and comprehend user behavior in real-time. Furthermore, a standardized topological equivalence model is proposed as the basis for a point selection strategy. By establishing correspondence between the modeled point selection model and the actual operation scene, the behavioral intent imposed on the model is applied to the operation object of the actual scene. Additionally, CNN-based and information entropy-based multimodal fusion intention understanding models are proposed for different input modalities to capture the operational intention of users by fusing their multimodal input data. The algorithm further improves the accuracy rate through an error correction mechanism based on implicit interaction to achieve better human-computer collaboration. The algorithm proposed in this paper has resulted in a 0.47-second improvement in point selection average time and achieved an intent understanding accuracy of 98.21%. This improvement leads to better fault tolerance and fluency during human-computer interaction, reduces the cognitive load on the user, and improves the overall user experience.

Analysis of the Characteristics and Ideas of Ancient Urban Land-Use Based on GIS and an Algorithm: A Case Study of Chang’an City in the Sui and Tang Dynasties

As ancient cities are spaces that represent the development of civilization, it is worth exploring and studying their characteristics and conceptions of land use. In this regard, the focus has turned to the issue of how to achieve the efficient mining of massive urban remote sensing data through human–computer collaboration. In this paper, a new intelligent method of analyzing urban land use characteristics and their cultural significance is proposed; it is feasible, effective, accurate, manageable, and portable. The method is based on a geographic information system (GIS) and a specific algorithm. The city plan was calibrated with the help of satellite remote sensing images and sites. By constructing the “urban element area acquisition and analysis model”, various operations for areas in the city plan were realized, including an area value calculation, land use structure calculation, area modulus analysis, area ratio analysis between areas, and determination of the cultural significance of numbers and ratios. Taking the Sui and Tang dynasties capital city of Chang’an as an example, we found the existence of a set of urban planning techniques through area modulus (standard area units) for the first time; it took the market area as the modulus A and the area of Daxing Palace as the expanded modulus 2A, made the area of important areas in the city an integer multiplied by the modulus value (for example, the overall scope of the city is 100A, the rectangular urban area is 90A, and the small city area is 10A), and made the key values and numerical ratios have a cultural significance (such as 4.5, 5.5, 10, 25, 30, 100, 12:10, 1.618:1, 9:5, 45:1, 2:1), reflecting the planning and design concept of the capital city, into which the ancient Chinese deliberately integrated “number, shape and meaning”. In addition, we carried out supplementary verification with the Roman city of Timgad and the Japanese city of Heijo-kyo, discovering that they also have design methods for area planning. We believe that land use planning can better meet the practical needs of urban resource distribution. Compared with urban form design, it might have chronological precedence. By setting the area modulus and the modulus value of each area, the grid-shaped city achieves the rational distribution of land and the establishment of order in an efficient way, and this thought and operation method greatly contributed to the advancement of ancient civilizations.

Human–Computer Collaboration for Visual Analytics: an Agent‐based Framework

AbstractThe visual analytics community has long aimed to understand users better and assist them in their analytic endeavors. As a result, numerous conceptual models of visual analytics aim to formalize common workflows, techniques, and goals leveraged by analysts. While many of the existing approaches are rich in detail, they each are specific to a particular aspect of the visual analytic process. Furthermore, with an ever‐expanding array of novel artificial intelligence techniques and advances in visual analytic settings, existing conceptual models may not provide enough expressivity to bridge the two fields. In this work, we propose an agent‐based conceptual model for the visual analytic process by drawing parallels from the artificial intelligence literature. We present three examples from the visual analytics literature as case studies and examine them in detail using our framework. Our simple yet robust framework unifies the visual analytic pipeline to enable researchers and practitioners to reason about scenarios that are becoming increasingly prominent in the field, namely mixed‐initiative, guided, and collaborative analysis. Furthermore, it will allow us to characterize analysts, visual analytic settings, and guidance from the lenses of human agents, environments, and artificial agents, respectively.

Current Status, Hotspots and Future Prospects of Intelligent Education Research in China

With the application of a new generation of intelligent technologies in education, represented by cloud computing, big data, Internet of Things, artificial intelligence and blockchain, China's education is increasingly moving into the era of intelligence. The article takes some academic papers related to the topic of "intelligent education" collected in CNKI database from 2017 to 2022 as the research object, and uses CiteSpace software to profile and analyze the current situation of domestic intelligent education research and research hotspots. The study found that the overall number of articles published showed a trend of "intelligent education". The study found that the number of articles published showed an overall increasing trend, and the research hotspots mainly focused on smart education technology and application, smart education ethics, and human-computer collaboration in the age of intelligence. Deep learning, smart education, learning analytics, knowledge mapping and education ethics are the future research trends.

Deep learning predicts malignancy and metastasis of solid pulmonary nodules from CT scans.

In the clinic, it is difficult to distinguish the malignancy and aggressiveness of solid pulmonary nodules (PNs). Incorrect assessments may lead to delayed diagnosis and an increased risk of complications. We developed and validated a deep learning-based model for the prediction of malignancy as well as local or distant metastasis in solid PNs based on CT images of primary lesions during initial diagnosis. In this study, we reviewed the data from multiple patients with solid PNs at our institution from 1 January 2019 to 30 April 2022. The patients were divided into three groups: benign, Ia-stage lung cancer, and T1-stage lung cancer with metastasis. Each cohort was further split into training and testing groups. The deep learning system predicted the malignancy and metastasis status of solid PNs based on CT images, and then we compared the malignancy prediction results among four different levels of clinicians. Experiments confirmed that human-computer collaboration can further enhance diagnostic accuracy. We made a held-out testing set of 134 cases, with 689 cases in total. Our convolutional neural network model reached an area under the ROC (AUC) of 80.37% for malignancy prediction and an AUC of 86.44% for metastasis prediction. In observer studies involving four clinicians, the proposed deep learning method outperformed a junior respiratory clinician and a 5-year respiratory clinician by considerable margins; it was on par with a senior respiratory clinician and was only slightly inferior to a senior radiologist. Our human-computer collaboration experiment showed that by simply adding binary human diagnosis into model prediction probabilities, model AUC scores improved to 81.80-88.70% when combined with three out of four clinicians. In summary, the deep learning method can accurately diagnose the malignancy of solid PNs, improve its performance when collaborating with human experts, predict local or distant metastasis in patients with T1-stage lung cancer, and facilitate the application of precision medicine.

Developing and Validating a Prediction Model For Death or Critical Illness in Hospitalized Adults, an Opportunity for Human-Computer Collaboration.

Retrospective and prospective cohort study. Academic tertiary care hospital. Adult general internal medicine hospitalizations. We developed and validated a neural network model to predict in-hospital death and ICU admission in 23,528 hospitalizations between April 2011 and April 2019. We then compared model predictions with 3,374 prospectively collected predictions from nurses, residents, and attending physicians about their own patients in 960 hospitalizations between April 30, and August 28, 2019. ML model predictions achieved clinician-level accuracy for predicting ICU admission or death (ML median F1 score 0.32 [interquartile range (IQR) 0.30-0.34], AUC 0.77 [IQ 0.76-0.78]; clinicians median F1-score 0.33 [IQR 0.30-0.35], AUC 0.64 [IQR 0.63-0.66]). ML predictions were more accurate than clinicians for ICU admission. Of all ICU admissions and deaths, 36% occurred in hospitalizations where the model and clinicians disagreed. Combining human and model predictions detected 49% of clinical deterioration events, improving sensitivity by 16% compared with clinicians alone and 24% compared with the model alone while maintaining a positive predictive value of 33%, thus keeping false alarms at a clinically acceptable level. ML models can complement clinician judgment to predict clinical deterioration in hospital. These findings demonstrate important opportunities for human-computer collaboration to improve prognostication and personalized medicine in hospital.

A Note on Digital Humanities Research on the Reception of Matsuo Bashō in Modern Japan ：Crossing Borders between Human Reading and Machine Reading

In this essay, I provided a brief report and perspective on digital humanities research related to the study of modern Japanese literature. First, I reviewed the recent increase in the availability of digital full-text databases, including Aozora Bunko, the National Diet Library’s Next Digital Library, Maruzen eBook Library, and Google Books. Next, as an example of digital humanities-based literary studies using the Next Digital Library, I attempted to study the reception of Matsuo Bashō between 1868 and 1945. Specifically, I searched the Next Digital Library—which currently has about 280,000 modern books available for full-text search—for Bashō’s <i>haiku</i> and found over a thousand works by him, although the total number differs depending on the counting method. I researched the <i>haikus</i> individually for the full-text data in books published between 1868 and 1945, using the computer language Python to automate the search and retrieve the results. Consequently, the top 30 most frequently cited works were identified. For the top five, the number of mentions by year of publication was also investigated. Results between the human- and computer-based reception studies were compared, and the strengths and weaknesses in understanding the context were highlighted. As for future prospects, I discussed the importance of human-computer collaboration, the necessity for combining large-scale full-text data sets with other databases, and the possibilities for structuring text using TEI and other methods.

The Seven-Times-Pass Method: Beneficial to the Optimization of Computer-Aided Teaching System

The background of this paper is mainly based on the socialized practice of teaching, management, learning and application of Rongzhixue or Smart System Studied (SSS). Relevant research achievements and progress reviews at home and abroad are scattered in the actual activities of education and teaching. On the one hand, the scientific and technological problems to be solved in this paper are mainly the problems faced by the general courses and general skills courses of social application of SSS (series of courses of SSS in the rain classroom of Tsinghua University), on the other hand, its main theories, methods and basic ideas are the decades of experience explored by Xiaohui Zou, the founder of SSS (he made a systematic introduction in the expert circle at the interdisciplinary high-level forum of Peking University, and also taught in the rain class of Tsinghua University for several years). This paper aims to combine the seven-times-pass teaching method with the eight-person group management method through years of accumulated teaching and management experience, and further explore: computer-aided application of the seven-times-pass method for cognitive computing and system design. The method is: first, systematically review and summarize multiple series of seven-times-pass steps, then, extract the cognitive content of interpersonal communication, make necessary preparations for computer modeling, and finally, focus on human-computer interaction and human-computer collaboration. The characteristics are the compatibility of individualization and standardization. The results not only summarize the cognitive innovation of the combination of the seven-times-pass teaching method and the eight-person-group management method, but also further explore the optimization methods of computer- aided application of seven-times-pass method cognitive computing and system design, enriching teaching practice and management practices. Its significance lies in that it not only has a positive effect on the comprehensive quality improvement of all aspects of school education at all levels, such as teaching, review and examination, but also has a positive effect on quality education, vocational education and lifelong education, among which, especially it has many enlightening effects on the computer-aided teaching system design. Typically, it can involve better self-learning computer-aided teaching systems and mobile device-assisted teaching software tools based on the seven-times-pass teaching method.

Research on Hybrid Teaching Model Based on Human-Machine Collaboration

The information technology in education promotes the innovation of blended teaching mode with technical support. This paper constructs an online and offline hybrid teaching model based on the concept of human-computer collaboration. In addition, the experimental research method was used to investigate the effect of the hybrid teaching mode on the teaching effectiveness of the course "University Computer Fundamentals" as an example. The study found that learners who participated in the blended learning classroom performed better than traditional multimedia instruction, and that the different learning behaviors of learners correlated with their final grades. This shows that the online and offline hybrid teaching based on human-computer collaboration can improve the learning effectiveness of learners.