Hasil untuk "artificial intelligence"

Erico Tjoa, Cuntai Guan

Recently, artificial intelligence and machine learning in general have demonstrated remarkable performances in many tasks, from image processing to natural language processing, especially with the advent of deep learning (DL). Along with research progress, they have encroached upon many different fields and disciplines. Some of them require high level of accountability and thus transparency, for example, the medical sector. Explanations for machine decisions and predictions are thus needed to justify their reliability. This requires greater interpretability, which often means we need to understand the mechanism underlying the algorithms. Unfortunately, the blackbox nature of the DL is still unresolved, and many machine decisions are still poorly understood. We provide a review on interpretabilities suggested by different research works and categorize them. The different categories show different dimensions in interpretability research, from approaches that provide “obviously” interpretable information to the studies of complex patterns. By applying the same categorization to interpretability in medical research, it is hoped that: 1) clinicians and practitioners can subsequently approach these methods with caution; 2) insight into interpretability will be born with more considerations for medical practices; and 3) initiatives to push forward data-based, mathematically grounded, and technically grounded medical education are encouraged.

Christopher J. Kelly, A. Karthikesalingam, Mustafa Suleyman et al.

BackgroundArtificial intelligence (AI) research in healthcare is accelerating rapidly, with potential applications being demonstrated across various domains of medicine. However, there are currently limited examples of such techniques being successfully deployed into clinical practice. This article explores the main challenges and limitations of AI in healthcare, and considers the steps required to translate these potentially transformative technologies from research to clinical practice.Main bodyKey challenges for the translation of AI systems in healthcare include those intrinsic to the science of machine learning, logistical difficulties in implementation, and consideration of the barriers to adoption as well as of the necessary sociocultural or pathway changes. Robust peer-reviewed clinical evaluation as part of randomised controlled trials should be viewed as the gold standard for evidence generation, but conducting these in practice may not always be appropriate or feasible. Performance metrics should aim to capture real clinical applicability and be understandable to intended users. Regulation that balances the pace of innovation with the potential for harm, alongside thoughtful post-market surveillance, is required to ensure that patients are not exposed to dangerous interventions nor deprived of access to beneficial innovations. Mechanisms to enable direct comparisons of AI systems must be developed, including the use of independent, local and representative test sets. Developers of AI algorithms must be vigilant to potential dangers, including dataset shift, accidental fitting of confounders, unintended discriminatory bias, the challenges of generalisation to new populations, and the unintended negative consequences of new algorithms on health outcomes.ConclusionThe safe and timely translation of AI research into clinically validated and appropriately regulated systems that can benefit everyone is challenging. Robust clinical evaluation, using metrics that are intuitive to clinicians and ideally go beyond measures of technical accuracy to include quality of care and patient outcomes, is essential. Further work is required (1) to identify themes of algorithmic bias and unfairness while developing mitigations to address these, (2) to reduce brittleness and improve generalisability, and (3) to develop methods for improved interpretability of machine learning predictions. If these goals can be achieved, the benefits for patients are likely to be transformational.

D. Gunning, M. Stefik, Jaesik Choi et al.

Explainability is essential for users to effectively understand, trust, and manage powerful artificial intelligence applications. Explainability is essential for users to effectively understand, trust, and manage powerful artificial intelligence applications.

Yue Pan, Limao Zhang

Abstract With the extensive adoption of artificial intelligence (AI), construction engineering and management (CEM) is experiencing a rapid digital transformation. Since AI-based solutions in CEM has become the current research focus, it needs to be comprehensively understood. In this regard, this paper presents a systematic review under both scientometric and qualitative analysis to present the current state of AI adoption in the context of CEM and discuss its future research trends. To begin with, a scientometric review is performed to explore the characteristics of keywords, journals, and clusters based on 4,473 journal articles published in 1997–2020. It is found that there has been an explosion of relevant papers especially in the past 10 years along with the change in keyword popularity from expert systems to building information modeling (BIM), digital twins, and others. Then, a brief understanding of CEM is provided, which can be benefited from the emerging trend of AI in terms of automation, risk mitigation, high efficiency, digitalization, and computer vision. Special concerns have been put on six hot research topics that amply the advantage of AI in CEM, including (1) knowledge representation and reasoning, (2) information fusion, (3) computer vision, (4) natural language processing, (5) intelligence optimization, and (6) process mining. The goal of these topics is to model, predict, and optimize issues in a data-driven manner throughout the whole lifecycle of the actual complex project. To further narrow the gap between AI and CEM, six key directions of future researches, such as smart robotics, cloud virtual and augmented reality (cloud VR/AR), Artificial Intelligence of Things (AIoT), digital twins, 4D printing, and blockchains, are highlighted to constantly facilitate the automation and intelligence in CEM.

Yogesh Kumar, Apeksha Koul, Ruchika Singla et al.

Artificial intelligence can assist providers in a variety of patient care and intelligent health systems. Artificial intelligence techniques ranging from machine learning to deep learning are prevalent in healthcare for disease diagnosis, drug discovery, and patient risk identification. Numerous medical data sources are required to perfectly diagnose diseases using artificial intelligence techniques, such as ultrasound, magnetic resonance imaging, mammography, genomics, computed tomography scan, etc. Furthermore, artificial intelligence primarily enhanced the infirmary experience and sped up preparing patients to continue their rehabilitation at home. This article covers the comprehensive survey based on artificial intelligence techniques to diagnose numerous diseases such as Alzheimer, cancer, diabetes, chronic heart disease, tuberculosis, stroke and cerebrovascular, hypertension, skin, and liver disease. We conducted an extensive survey including the used medical imaging dataset and their feature extraction and classification process for predictions. Preferred reporting items for systematic reviews and Meta-Analysis guidelines are used to select the articles published up to October 2020 on the Web of Science, Scopus, Google Scholar, PubMed, Excerpta Medical Database, and Psychology Information for early prediction of distinct kinds of diseases using artificial intelligence-based techniques. Based on the study of different articles on disease diagnosis, the results are also compared using various quality parameters such as prediction rate, accuracy, sensitivity, specificity, the area under curve precision, recall, and F1-score.

D. Vrontis, M. Christofi, V. Pereira et al.

Abstract Although academic production in intelligent automation (e.g. artificial intelligence, robotics) has grown rapidly, we still lack a comprehensive understanding of the impacts of the utilization of these technologies in human resource management (HRM) at an organizational (firms) and individual (employees) level. This study therefore aims to systematize the academic inputs on intelligent automation so far and to clarify what are its main contributions to and challenges for HRM. In a systematic search of 13,136 potentially relevant studies published in the top HRM, international business (IB), general management (GM) and information management (IM) journals, we found 45 articles studying artificial intelligence, robotics and other advanced technologies within HRM settings. Results show that intelligent automation technologies constitute a new approach to managing employees and enhancing firm performance, thus offering several opportunities for HRM but also considerable challenges at a technological and ethical level. The impact of these technologies has been identified to concentrate on HRM strategies, namely, job replacement, human-robot/AI collaboration, decision-making and learning opportunities, and HRM activities, namely, recruiting, training and job performance. This study discusses these shifts in detail, along with the main contributions to theory and practice and directions for future research.

Sofiat Abioye, Lukumon O. Oyedele, L. Àkànbí et al.

The growth of the construction industry is severely limited by the myriad complex challenges it faces such as cost and time overruns, health and safety, productivity and labour shortages. Also, construction industry is one the least digitized industries in the world, which has made it difficult for it to tackle the problems it currently faces. An advanced digital technology, Artificial Intelligence (AI), is currently revolutionising industries such as manufacturing, retail

Reza Toorajipour, Vahid Sohrabpour, Ali Nazarpour et al.

Abstract This paper seeks to identify the contributions of artificial intelligence (AI) to supply chain management (SCM) through a systematic review of the existing literature. To address the current scientific gap of AI in SCM, this study aimed to determine the current and potential AI techniques that can enhance both the study and practice of SCM. Gaps in the literature that need to be addressed through scientific research were also identified. More specifically, the following four aspects were covered: (1) the most prevalent AI techniques in SCM; (2) the potential AI techniques for employment in SCM; (3) the current AI-improved SCM subfields; and (4) the subfields that have high potential to be enhanced by AI. A specific set of inclusion and exclusion criteria are used to identify and examine papers from four SCM fields: logistics, marketing, supply chain and production. This paper provides insights through systematic analysis and synthesis.

Ida Merete Enholm, Emmanouil Papagiannidis, P. Mikalef et al.

Artificial Intelligence (AI) are a wide-ranging set of technologies that promise several advantages for organizations in terms off added business value. Over the past few years, organizations are increasingly turning to AI in order to gain business value following a deluge of data and a strong increase in computational capacity. Nevertheless, organizations are still struggling to adopt and leverage AI in their operations. The lack of a coherent understanding of how AI technologies create business value, and what type of business value is expected, therefore necessitates a holistic understanding. This study provides a systematic literature review that attempts to explain how organizations can leverage AI technologies in their operations and elucidate the value-generating mechanisms. Our analysis synthesizes the current literature and highlights: (1) the key enablers and inhibitors of AI adoption and use; (2) the typologies of AI use in the organizational setting; and (3) the first- and second-order effects of AI. The paper concludes with an identification of the gaps in the literature and develops a research agenda that identifies areas that need to be addressed by future studies.

Gwo-jen Hwang, Shu-Yun Chien

Artem Shmatko, N. Ghaffari Laleh, M. Gerstung et al.

L. Kaack, P. Donti, Emma Strubell et al.

M. A. Ayanwale, I. Sanusi, O. P. Adelana et al.

: This study aimed to investigate teachers’ attitudes towards using artificial intelligence (AI) applications to address learning difficulties (LDs) in Aseer Region, Kingdom of Saudi Arabia. A descriptive analytical approach was used to collect data from 147 teachers of Special Education in Aseer region. The questionnaire consisted of three axes: measuring teachers’ awareness of AI capabilities, advantages, and applications for solving LDs; assessing teachers’ emotional and behavioral attitudes towards employing AI applications for solving LDs; and identifying obstacles and difficulties from teachers’ point of view. Results showed that teachers had a medium to high level of awareness of AI capabilities for solving LDs and a high level of emotional and behavioral trends towards employing these applications. However, there were also great agreement about the existence of difficulties and obstacles to employing these applications. The study recommends preparing workshops dealing with the advantages and capabilities of AI applications for addressing LDs, as well as procedural research to identify and avoid difficulties in designing or dealing with these kinds of applications.

M. Ashok, Rohit Madan, Anton Joha et al.

The use of Artificial Intelligence (AI) in Digital technologies (DT) is proliferating a profound socio-technical transformation. Governments and AI scholarship have endorsed key AI principles but lack direction at the implementation level. Through a systematic literature review of 59 papers, this paper contributes to the critical debate on the ethical use of AI in DTs beyond high-level AI principles. To our knowledge, this is the first paper that identifies 14 digital ethics implications for the use of AI in seven DT archetypes using a novel ontological framework (physical, cognitive, information, and governance). The paper presents key findings of the review and a conceptual model with twelve propositions highlighting the impact of digital ethics implications on societal impact, as moderated by DT archetypes and mediated by organisational impact. The implications of intelligibility, accountability, fairness, and autonomy (under the cognitive domain), and privacy (under the information domain) are the most widely discussed in our sample. Furthermore, ethical implications related to the governance domain are shown to be generally applicable for most DT archetypes. Implications under the physical domain are less prominent when it comes to AI diffusion with one exception (safety). The key findings and resulting conceptual model have academic and professional implications.

Fabio Urbina, Filippa Lentzos, Cédric Invernizzi et al.

J. Lipkova, Richard J. Chen, Bowen Chen et al.

In oncology, the patient state is characterized by a whole spectrum of modalities, ranging from radiology, histology, and genomics to electronic health records. Current artificial intelligence (AI) models operate mainly in the realm of a single modality, neglecting the broader clinical context, which inevitably diminishes their potential. Integration of different data modalities provides opportunities to increase robustness and accuracy of diagnostic and prognostic models, bringing AI closer to clinical practice. AI models are also capable of discovering novel patterns within and across modalities suitable for explaining differences in patient outcomes or treatment resistance. The insights gleaned from such models can guide exploration studies and contribute to the discovery of novel biomarkers and therapeutic targets. To support these advances, here we present a synopsis of AI methods and strategies for multimodal data fusion and association discovery. We outline approaches for AI interpretability and directions for AI-driven exploration through multimodal data interconnections. We examine challenges in clinical adoption and discuss emerging solutions.

Xiujing He, Xiaowei Liu, Fengli Zuo et al.

With biotechnological advancements, innovative omics technologies are constantly emerging that have enabled researchers to access multi-layer information from the genome, epigenome, transcriptome, proteome, metabolome, and more. A wealth of omics technologies, including bulk and single-cell omics approaches, have empowered to characterize different molecular layers at unprecedented scale and resolution, providing a holistic view of tumor behavior. Multi-omics analysis allows systematic interrogation of various molecular information at each biological layer while posing tricky challenges regarding how to extract valuable insights from the exponentially increasing amount of multi-omics data. Therefore, efficient algorithms are needed to reduce the dimensionality of the data while simultaneously dissecting the mysteries behind the complex biological processes of cancer. Artificial intelligence has demonstrated the ability to analyze complementary multi-modal data streams within the oncology realm. The coincident development of multi-omics technologies and artificial intelligence algorithms has fuelled the development of cancer precision medicine. Here, we present state-of-the-art omics technologies and outline a roadmap of multi-omics integration analysis using an artificial intelligence strategy. The advances made using artificial intelligence-based multi-omics approaches are described, especially concerning early cancer screening, diagnosis, response assessment, and prognosis prediction. Finally, we discuss the challenges faced in multi-omics analysis, with tentative future trends in this field. With the increasing application of artificial intelligence in multi-omics analysis, we anticipate a shifting paradigm in precision medicine becoming driven by artificial intelligence-based multi-omics technology.

Yujie You, Xin Lai, Ying Pan et al.

Artificial intelligence is an advanced method to identify novel anticancer targets and discover novel drugs from biology networks because the networks can effectively preserve and quantify the interaction between components of cell systems underlying human diseases such as cancer. Here, we review and discuss how to employ artificial intelligence approaches to identify novel anticancer targets and discover drugs. First, we describe the scope of artificial intelligence biology analysis for novel anticancer target investigations. Second, we review and discuss the basic principles and theory of commonly used network-based and machine learning-based artificial intelligence algorithms. Finally, we showcase the applications of artificial intelligence approaches in cancer target identification and drug discovery. Taken together, the artificial intelligence models have provided us with a quantitative framework to study the relationship between network characteristics and cancer, thereby leading to the identification of potential anticancer targets and the discovery of novel drug candidates.

Zhibo Zhang, H. A. Hamadi, E. Damiani et al.

This survey presents a comprehensive review of current literature on Explainable Artificial Intelligence (XAI) methods for cyber security applications. Due to the rapid development of Internet-connected systems and Artificial Intelligence in recent years, Artificial Intelligence including Machine Learning (ML) and Deep Learning (DL) has been widely utilized in the fields of cyber security including intrusion detection, malware detection, and spam filtering. However, although Artificial Intelligence-based approaches for the detection and defense of cyber attacks and threats are more advanced and efficient compared to the conventional signature-based and rule-based cyber security strategies, most ML-based techniques and DL-based techniques are deployed in the “black-box” manner, meaning that security experts and customers are unable to explain how such procedures reach particular conclusions. The deficiencies of transparencies and interpretability of existing Artificial Intelligence techniques would decrease human users’ confidence in the models utilized for the defense against cyber attacks, especially in current situations where cyber attacks become increasingly diverse and complicated. Therefore, it is essential to apply XAI in the establishment of cyber security models to create more explainable models while maintaining high accuracy and allowing human users to comprehend, trust, and manage the next generation of cyber defense mechanisms. Although there are papers reviewing Artificial Intelligence applications in cyber security areas and the vast literature on applying XAI in many fields including healthcare, financial services, and criminal justice, the surprising fact is that there are currently no survey research articles that concentrate on XAI applications in cyber security. Therefore, the motivation behind the survey is to bridge the research gap by presenting a detailed and up-to-date survey of XAI approaches applicable to issues in the cyber security field. Our work is the first to propose a clear roadmap for navigating the XAI literature in the context of applications in cyber security.

M. M. Civaner, Y. Uncu, Filiz Bulut et al.

Background As the information age wanes, enabling the prevalence of the artificial intelligence age; expectations, responsibilities, and job definitions need to be redefined for those who provide services in healthcare. This study examined the perceptions of future physicians on the possible influences of artificial intelligence on medicine, and to determine the needs that might be helpful for curriculum restructuring. Methods A cross-sectional multi-centre study was conducted among medical students country-wide, where 3018 medical students participated. The instrument of the study was an online survey that was designed and distributed via a web-based service. Results Most of the medical students perceived artificial intelligence as an assistive technology that could facilitate physicians’ access to information (85.8%) and patients to healthcare (76.7%), and reduce errors (70.5%). However, half of the participants were worried about the possible reduction in the services of physicians, which could lead to unemployment (44.9%). Furthermore, it was agreed that using artificial intelligence in medicine could devalue the medical profession (58.6%), damage trust (45.5%), and negatively affect patient-physician relationships (42.7%). Moreover, nearly half of the participants affirmed that they could protect their professional confidentiality when using artificial intelligence applications (44.7%); whereas, 16.1% argued that artificial intelligence in medicine might cause violations of professional confidentiality. Of all the participants, only 6.0% stated that they were competent enough to inform patients about the features and risks of artificial intelligence. They further expressed that their educational gaps regarding their need for “knowledge and skills related to artificial intelligence applications” (96.2%), “applications for reducing medical errors” (95.8%), and “training to prevent and solve ethical problems that might arise as a result of using artificial intelligence applications” (93.8%). Conclusions The participants expressed a need for an update on the medical curriculum, according to necessities in transforming healthcare driven by artificial intelligence. The update should revolve around equipping future physicians with the knowledge and skills to effectively use artificial intelligence applications and ensure that professional values and rights are protected.