Intelligence Research Research Articles

Feasibility of cross-vendor linkage of ophthalmic images with electronic health record data: an analysis from the IRIS Registry®.

To link compliant, universal Digital Imaging and Communications in Medicine (DICOM) ophthalmic imaging data at the individual patient level with the American Academy of Ophthalmology IRIS® Registry (Intelligent Research in Sight). A retrospective study using de-identified EHR registry data. IRIS Registry records. DICOM files of several imaging modalities were acquired from two large retina ophthalmology practices. Metadata tags were extracted and harmonized to facilitate linkage to the IRIS Registry using a proprietary, heuristic patient-matching algorithm, adhering to HITRUST guidelines. Linked patients and images were assessed by image type and clinical diagnosis. Reasons for failed linkage were assessed by examining patients' records. Success rate of linking clinicoimaging and EHR data at the patient level. A total of 2 287 839 DICOM files from 54 896 unique patients were available. Of these, 1 937 864 images from 46 196 unique patients were successfully linked to existing patients in the registry. After removing records with abnormal patient names and invalid birthdates, the success linkage rate was 93.3% for images. 88.2% of all patients at the participating practices were linked to at least one image. Using identifiers from DICOM metadata, we created an automated pipeline to connect longitudinal real-world clinical data comprehensively and accurately to various imaging modalities from multiple manufacturers at the patient and visit levels. The process has produced an enriched and multimodal IRIS Registry, bridging the gap between basic research and clinical care by enabling future applications in artificial intelligence algorithmic development requiring large linked clinicoimaging datasets.

Ship Infrared Automatic Target Recognition Based on Bipartite Graph Recommendation: A Model-Matching Method

Deep learning technology has greatly propelled the development of intelligent and information-driven research on ship infrared automatic target recognition (SIATR). In future scenarios, there will be various recognition models with different mechanisms to choose from. However, in complex and dynamic environments, ship infrared (IR) data exhibit rich feature space distribution, resulting in performance variations among SIATR models, thus preventing the existence of a universally superior model for all recognition scenarios. In light of this, this study proposes a model-matching method for SIATR tasks based on bipartite graph theory. This method establishes evaluation criteria based on recognition accuracy and feature learning credibility, uncovering the underlying connections between IR attributes of ships and candidate models. The objective is to selectively recommend the optimal candidate model for a given sample, enhancing the overall recognition performance and applicability of the model. We separately conducted tests for the optimization of accuracy and credibility on high-fidelity simulation data, achieving Accuracy and EDMS (our credibility metric) of 95.86% and 0.7781. Our method improves by 1.06% and 0.0274 for each metric compared to the best candidate models (six in total). Subsequently, we created a recommendation system that balances two tasks, resulting in improvements of 0.43% (accuracy) and 0.0071 (EDMS). Additionally, considering the relationship between model resources and performance, we achieved a 28.35% reduction in memory usage while realizing enhancements of 0.33% (accuracy) and 0.0045 (EDMS).

Mass Medias Impact on Students Mental Health

Contemporary people live in a reality full of intelligent technology construction, and many practical activities are regulated by technology. The chat content generation pre-training program artificial intelligence developed by the Open Artificial Intelligence Research Center (OpenAI) based on large model data training has aroused wide concern because of its generation and learning ability. It is necessary to admit that the current domestic media publicity seems to focus more on the convenience that big data technology may bring to human society. But not much about its own limitations. In the few discussions on the negative effects of big data technology, more concerns are raised about the ethical risks that may be caused by the abuse of relevant technology, such as the threat of "data greed" to personal privacy, and the decision-making errors that may be caused by the superstition of business decision-makers and government heads about "digital dictatorship", etc. From the perspective of philosophy of information technology and philosophy of cognitive science, this paper reviews the gains and losses of big data technology itself in terms of philosophical thought premise and path strategy. Starting from the theory of "moral materialization", this paper analyzes the ethical value load and risk of artificial intelligence from the perspectives of moral subject status, value position presupposition, operation intervention and operation result effect. And from the moral materialization theory of "top-down" approach and "bottom-up" approach to the ethical governance of modern scientific and technological intelligent artifacts.

Oral Materialization and Ethical Governance of Science and Technology in Artificial Intelligence

Contemporary people live in a reality full of intelligent technology construction, and many practical activities are regulated by technology. The chat content generation pre-training program artificial intelligence developed by the Open Artificial Intelligence Research Center (OpenAI) based on large model data training has aroused wide concern because of its generation and learning ability. It is necessary to admit that the current domestic media publicity seems to focus more on the convenience that big data technology may bring to human society. But not much about its own limitations. In the few discussions on the negative effects of big data technology, more concerns are raised about the ethical risks that may be caused by the abuse of relevant technology, such as the threat of "data greed" to personal privacy, and the decision-making errors that may be caused by the superstition of business decision-makers and government heads about "digital dictatorship", etc. From the perspective of philosophy of information technology and philosophy of cognitive science, this paper reviews the gains and losses of big data technology itself in terms of philosophical thought premise and path strategy. Starting from the theory of "moral materialization", this paper analyzes the ethical value load and risk of artificial intelligence from the perspectives of moral subject status, value position presupposition, operation intervention and operation result effect. And from the moral materialization theory of "top-down" approach and "bottom-up" approach to the ethical governance of modern scientific and technological intelligent artifacts.

Use of Anterior Chamber Paracentesis for Diagnosis in Viral Anterior Uveitis

In ophthalmic practices in the Intelligent Research in Sight (IRIS) Registry, 1.6% of eyes with viral anterior uveitis underwent anterior chamber paracentesis. When performed, anterior chamber paracentesis was associated with a change in diagnosis in 42% of cases.

A Bibliographic Dataset of Health Artificial Intelligence Research.

Objective: The aim of this study is to construct a curated bibliographic dataset for a landscape analysis on Health Artificial Intelligence (HAI) research. Data Source: We integrated HAI-related bibliographic records, including publications, open research datasets, patents, research grants, and clinical trials from Medline and Dimensions. Methods: Searching: Relevant documents were identified using Medical Subject Headings (MeSH) and Field of Research (FoR) indexed by 2 bibliographic databases, Medline and Dimensions. Extracting: MeSH terms annotated from the aforementioned bibliographic databases served as the primary information for our processing. For document records lacking MeSH terms, we re-extracted them using the Medical Text Indexer (MTI). Mapping: In order to enhance interoperability, HAI multi-documents were organized using a mapping system incorporating MeSH, FoR, The International Classification of Diseases (ICD-10), and Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT). Integrating: All documents were curated based on a pre-defined ontology of health problems and AI technologies from the MeSH hierarchy. Results: We collected 96,332 HAI documents (publications: 75,820, open research datasets: 638, patents: 11,226, grants: 6,113, and clinical trials: 2,535) during 2009 to 2021. On average, 75.12% of the documents were tagged with at least one label related to either health problems or AI technologies (with 92.9% of publications tagged). Summary: This study presents a comprehensive pipeline for processing and curating HAI bibliographic documents following the FAIR (Findable, Accessible, Interoperable, Reusable) standard, offering a valuable multidimensional collection for the community. This dataset serves as a crucial resource for horizontally scanning the funding, research, clinical assessments, and innovations within the HAI field.

The Application Research of Artificial Intelligence in Human Resource Management

The Application Research of Artificial Intelligence in Human Resource Management

Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science.

Machine learning has been pervasively touching many fields of science. Chemistry and materials science are no exception. While machine learning has been making a great impact, it is still not reaching its full potential or maturity. In this perspective, we first outline current applications across a diversity of problems in chemistry. Then, we discuss how machine learning researchers view and approach problems in the field. Finally, we provide our considerations for maximizing impact when researching machine learning for chemistry.

Analysis of Research on Artificial Intelligence in Human Resources Management: A Bibliometric Analysis

This research aims to find contributors who have a major impact, observe the latest developments, and identify domains and supporting factors that can guide future research in the field artificial intelligence (AI) and human resource management integration. This research was conducted Within the framework of many activities and practices that are present in organisations. This study utilises a methodology that involves conducting bibliometric analysis and utilising the Biblioshiny app. The sample for analysis consists of 298 papers obtained from the Scopus database. The objective is to discover research that is still relevant to this theme. Three questions to be identified were drawn up that were performed on documents retrieved in the scopus database. It found that the main research focus in the field is still very little and despite the impact of artificial intelligence practices on human resources is enormous. Several studies have investigated stakeholder perspectives on the practice of applying artificial intelligence in the application of human resources. It is hoped that this research can provide guidelines and directions for the advancement of the use of AI in the field of HR for several organizations in the future.

Role of Imaging in Diagnosis and Management of COVID-19: Evidence-Based Approaches.

Imaging has been demonstrated to play a crucial role in both the diagnosis and management of COVID-19. Depending on resources, pre-test probability, and risk factors for severe disease progression, real-time polymerase chain reaction (RT-PCR) testing may be followed by chest radiography (CXR) or chest computed tomography (CT) to further aid in diagnosis or excluding COVID-19 disease. SARS-CoV-2 has been shown not only to pathologically impact the pulmonary system, but also the cardiovascular, gastrointestinal, and neurological systems to name a few. Imaging has again proven useful in further investigating and managing extrapulmonary disease, with the use of echocardiogram, CT angiography of the cardiovascular and cerebrovascular structures, MRI of the brain, as well as ultrasound of the abdomen and CT of the abdomen and pelvis proving particularly useful. Research in artificial intelligence and its application in the diagnosis of COVID-19 and disease severity prediction is underway, and point-of-care ultrasound is an emerging bedside technique that may allow for more efficient and timely diagnosis of COVID-19.

Applications of artificial intelligence and cognitive science in design

Abstract Artificial intelligence and cognitive science are two core research areas in design. Artificial intelligence shows the capability of analysing massive amounts of data which supports making predictions, uncovering patterns and generating insights in varying design activities, while cognitive science provides the advantage of revealing the inherent mental processes and mechanisms of humans in design. Both artificial intelligence and cognitive science in design research are focused on delivering more innovative and efficient design outcomes and processes. Therefore, this thematic collection on “Applications of Artificial Intelligence and Cognitive Science in Design” brings together state-of-the-art research in artificial intelligence and cognitive science to showcase the emerging trend of applying artificial intelligence techniques and neurophysiological and biometric measures in design research. Three promising future research directions: 1) human-in-the-loop AI for design, 2) multimodal measures for design, and 3) AI for design cognitive data analysis and interpretation, are suggested by analysing the research papers collected. A framework for integration of artificial intelligence and cognitive science in design, incorporating the three research directions, is proposed to inspire and guide design researchers in exploring human-centred design methods, strategies, solutions, tools and systems.

The Application of Artificial Intelligence in Providing Intelligent Services in Libraries

Since the 1950s, the research of artificial intelligence has been continuously deepened and increasingly widely used in various fields of society, which is considered to be an important basis for the future human development. Library is an important part of public education. Based on how libraries use artificial intelligence to provide intelligent services, it discusses the combination of library service and artificial intelligence from three aspects of intelligent collection resource organization, automation of library management, and precision of information service. Through the introduction of artificial intelligence technology, the library can achieve a comprehensive upgrading in improving the service level, enriching the service mode and service content, enhancing the service efficiency and optimizing the user experience, so as to better meet the changes of readers' reading needs in the era of digital intelligence.

ИССЛЕДОВАНИЕ СТРАТЕГИЙ ПРЕПОДАВАНИЯ КУРСОВ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В ВЫСШИХ УЧЕБНЫХ ЗАВЕДЕНИЯХ

Being one of the ten most fashionable buzzwords in the media, artificial intelligence has penetrated into all aspects of social production and life, especially in the development of smart homes, smart education, etc., which makes artificial intelligence more closely related to production and people’s lives, and the development of smart finance, smart transport, etc. It has also brought great convenience to people’s lives. Artificial intelligence has become an inevitable trend in promoting social development. A large number of companies have joined the field of research, development and production of artificial intelligence, so there is an acute demand for artificial intelligence specialists in the market. It was added that higher professional educational institutions should closely integrate with market demand, introduce innovative teaching methods for specialties in the field of artificial intelligence and develop high-quality talents of practical application with skill and high quality.

A Comparative Study of Principled rPPG-Based Pulse Rate Tracking Algorithms for Fitness Activities.

Performance improvements obtained by recent principled approaches for pulse rate(PR) estimation have typically been achieved by adding or modifying certain modules within a reconfigurable system. Yet, evaluations are usually performed only at the system level. To better understand each module's contribution and facilitate future research in explainable learning and artificial intelligence for physiological monitoring, this paper conducts a comparative study of video-based, principled PR tracking algorithms, with a particular focus on challenging fitness scenarios. A review of the progress achieved over the last decade and a half in this field is utilized to construct the major processing modules of a reconfigurable remote pulse rate sensing system. Experiments are conducted on two challenging datasets-an internal collection of 25 videos of two Asian males exercising on stationary-bike, elliptical, and treadmill machines and 34 videos from a public ECG fitness database of 14 men and 3 women exercising on elliptical and stationary-bike machines. The signal-to-noise ratio (SNR), Pearson's correlation coefficient, error count ratio, error rate, and root mean squared error are used for performance evaluation. The top-performing configuration produces respective values of -0.8dB, 0.86, 9%, 1.7%, and 3.3beats per minute(bpm) for the internal dataset and 1.3dB, 0.77, 28.6%, 6.0%, and 8.1bpm for the ECG Fitness dataset, achieving significant improvements over alternative configurations. Our results indicate a synergistic effect between pulse color mapping and adaptive motion filtering, as well as the importance of a robust frequency tracking algorithm for PR estimation in low SNR settings.

Artificial Intelligence-Enabled Business Model Innovation: Competencies and Roles of Top Management

Research in artificial intelligence and business model innovation is flourishing. Nevertheless, the current discussion lacks an overarching understanding of, and thus has not sufficiently addressed, the interface between artificial intelligence-enabled business model innovation and the critical role of top management. Although a paradigm shift affecting top management is already occurring, extant management literature is limited, especially in terms of primary research. Accordingly, this study explores how top management can encourage and facilitate artificial intelligence-enabled business model innovation. We utilized an inductive approach and conducted semistructured interviews with 47 practitioners to develop a grounded theory. The developed framework consists of five top management competencies and eight top management roles. Overall, our study contributes to research in business model innovation theory, revealing that top management requires a specific skill set to carry out their roles and fulfill expectations.

Intelligent Control Method Research for High Rise Building Vibration by Integrating Genetic Algorithm and LSTM

Intelligent Control Method Research for High Rise Building Vibration by Integrating Genetic Algorithm and LSTM

Research on optimization of teaching mental health monitoring and evaluation system based on intelligent algorithm

Abstract Recently, the application and optimization research of intelligent algorithms in the monitoring and evaluation system of teaching mental health has been focused on. Many countries cannot avoid that with the rapid development of the urban economy, the mental health of Chinese people is ignored without knowing it. This phenomenon is more obvious in today’s campuses, especially in colleges and universities. Although the campus is equipped with a psychological counseling office, most students choose to give up because they can’t face themselves in a bad mood. Traditional random checks and individual conversations have no good effect. The intelligent algorithm developed in the new era is inevitably applied to the detection and evaluation of teaching psychological health. However, the intelligent algorithm at this stage cannot meet the requirements of teaching mental health monitoring and evaluation, because the data collection and processing are not completed through the matching intelligent algorithm, but directly through the algorithm DC method. The data collection will cause certain errors, and the data processing and output will inevitably be biased. This research is a kind of optimized intelligent algorithm system that can be applied to the monitoring and evaluation of teaching mental health. First, the research introduces and compares several modern intelligent algorithms used in teaching mental health monitoring and evaluation, and then analyzes the main influencing factors of monitoring and evaluation. These factors are integrated into the intelligent algorithm monitoring and evaluation system as key intelligent algorithm research objects, Finally, the optimized monitoring and evaluation system is applied in practice to obtain the corresponding imperfect information performance, and the final optimized result is obtained through further improvement. The results show that in most cases, a certain intelligent algorithm can not fully adapt to the detection and evaluation system, but the combination of different kinds of intelligent algorithms through influencing factors can give play to its advantages, and the final results can also be consistent with the actual. The proposed intelligent algorithm can not only be used in the monitoring and evaluation of teaching mental health but also reflect more monitoring and evaluation of teaching quality. The essence of the intelligent algorithm is to obtain complete data that can reflect reality by exploring the value of various information data. In the future, more joint intelligent algorithms will be proposed, which can adapt to more situations and achieve complete applications in teaching, security, medicine, and other fields.

Application and Benefits of Building Information Modeling (BIM) in Intelligent Engineering Construction

Abstract Currently, in China, intelligent construction research predominantly targets engineering projects, with limited focus on the benefits of Building Information Modeling (BIM) technology. This paper advocates for integrating BIM with cutting-edge engineering construction techniques, adhering to four intelligent construction level assessment principles. We introduce a benefit evaluation model for innovative construction, combining the two-dimensional cloud model with the Analytic Network Process (ANP) hierarchy method. Our findings highlight the significant role of BIM in enhancing operation and maintenance efficiency and in the deepening of design, evidenced by average scores of 4.0868 and 4.0691, respectively. Early stages of innovative construction projects benefit from BIM’s effective material usage control, reducing initial material consumption below planned levels. Furthermore, our analysis reveals BIM’s capacity to simultaneously optimize quality cost provision and additive cost, with Project 1 showcasing optimization indexes of 7.91% and 73.38%, respectively. These results underscore BIM’s substantial impact on improving the economic benefits of intelligent construction.

Risk-Averse Decision Making Under Uncertainty

A large class of decision making under uncertainty problems can be described via Markov decision processes (MDPs) or partially observable MDPs (POMDPs), with application to artificial intelligence and operations research, among others. In this paper, we consider the problem of designing policies for MDPs and POMDPs with objectives and constraints in terms of dynamic coherent risk measures rather than the traditional total expectation, which we refer to as the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">constrained risk-averse problem</i> . Our contributions can be described as follows: For MDPs, under some mild assumptions, we propose an optimization-based method to synthesize Markovian policies. We then demonstrate that such policies can be found by solving difference convex programs (DCPs). We show that our formulation generalize linear programs for constrained MDPs with total discounted expected costs and constraints; For POMDPs, we show that, if the coherent risk measures can be defined as a Markov risk transition mapping, an infinite-dimensional optimization can be used to design Markovian belief-based policies. For POMDPs with stochastic finite-state controllers (FSCs), we show that the latter optimization simplifies to a (finite-dimensional) DCP. We incorporate these DCPs in a policy iteration algorithm to design risk-averse FSCs for POMDPs. We demonstrate the efficacy of the proposed method with numerical experiments involving conditional-value-at-risk (CVaR) and entropic-value-at-risk (EVaR) risk measures.

Understanding the Use and Abuse of Social Media: Generalized Fake News Detection With a Multichannel Deep Neural Network

Fake news has spread across social media platforms and with the ease of access, negative consequences have come with it on individuals and society. This issue has become a focus of interest among various research communities, including artificial intelligence (AI) researchers. Existing AI-based fake news detection techniques primarily make use of a 1-D convolutional neural network (1D-CNN) with unidirectional word embedding. We propose a multichannel deep convolutional neural network (CNN) with different kernel sizes and filters as an AI technique. Multiple embedding of the same dimension with different kernel sizes technically allows the news article to be processed at different resolutions of different n-grams at the same time. Different kernel sizes increase the learning ability of the proposed classification model. The proposed model determines how to integrate these interpretations (different n-grams) most suitably. Three real-world fake news datasets were used in experiments to validate the classification performance. The classification results showed that the proposed model has high accuracy in detecting fake news. Regardless of the dataset, the proposed model can be used for fake news detection in binary classification problems.