Abstract
Over the past few years, researchers and developers have managed to overcome several challenges in order to provide informative, interactive and effective healthcare solutions. In particular, the recent developments in Artificial Intelligence (AI) field, more specifically ML and DL techniques, have contributed significantly to making Clinical Decision Support Systems (CDSS) more effective in healthcare processes by improving diagnostics, therapy, and prognosis. On another side, the Internet of Medical Things (IoMT), which has evolved into a tool to next-generation bioanalysis., combines networked biomedical devices with software applications to efficiently support healthcare tasks. Practically speaking, persons are susceptible to suffer from one or more chronic or non-chronic diseases under several conditions. This is why AI and IoMT are believed to enable the early identification of potential threats to human health that require effective health actions. In this paper, we accomplish an SLR of AI-based CDSS and IoMT techniques for multi-disease forecasting by making analysis and discussions according to various aspects. The aim is to help researchers in this field of interest to open up future prospects, especially since the existing literature reviews on medical decision support systems mainly focus on the prediction of a single disease rather than multiple diseases.
Access provided by Autonomous University of Puebla. Download conference paper PDF
Similar content being viewed by others
Keywords
1 Introduction
Healthcare systems have been majorly revolutionized over the last years due to the tremendous progress in digital health technologies such as artificial intelligence (AI), robotics, IoMT, etc. This advancement has noticeably reduced the medical diagnostic and monitoring errors made by humans due to tiredness, work overload, and massive generated data [1], Consequently clinical outcomes can be improved, and data can be tracked over time through digital health. Artificial Intelligence (AI) and IoMT technologies are increasingly being used in the Healthcare sector, especially in advanced clinical decision support systems (CDSS) applications. It provides solutions that would assist in accelerating the decision-making processes within healthcare systems for precisely, earlier, and more reliably focused medical treatments [2]. IoMT has a significant impact on data collection with patient data monitoring, whereas AI is expected to analyze the increasing amounts of data and make decisions according to what it learns from the data. The most important factor in the treatment of any disease is to predict or recognize early diseases. According to [2], in the United States, it is predicted that there will be 1.9 million new cancer diagnoses and 609,360 cancer deaths in 2023. Through early identification of a patient’s risk of cancer, along with other clinically relevant information, predictive models with AI using routinely performed blood tests have the potential to help physicians diagnose and deliver effective treatment to cancer patients earlier [3]. DL and ML are the areas that can be used to support the prediction of data-driven diagnosis systems. Researchers have introduced several ML and DL models to tackle the problem of huge and various data in promoting intelligent disease diagnosis to diagnose various diseases. Such models may predict the early diagnosis of the disease and provide solutions. Early diagnosis and efficient treatment are the best solutions to minimize the mortality rates caused by any disease. Consequently, the majority of medical experts become attracted to the new predictive models for disease prediction built around machine learning algorithms and deep learning. [4]. With the occurrence and emergence of telemedicine and intelligent health care came a major problem of restricted data access and limited data access. Therefore the IoMT is attracting the interest of the healthcare research community, where its potential to generate disruptive healthcare innovations may play a key role in reducing the pressure within health systems. Besides, combining IoMT with AI may deliver tailored health services that participate directly in enhancing the patient’s life quality [5]. Our principal research aim is to address The following questions using SLR guidelines.
-
1.
How effective is Artificial Intelligence in medical decision support systems ?
-
2.
Which diseases were treated using Machine Learning and Deep Learning ?
-
3.
How did the researchers implement the IoMT to predict disease?
-
4.
What motivates using artificial intelligence in medical decision-supporting systems ?
This paper presents an SLR of approaches and techniques for AI-based medical decision support systems. The main contributions of this SLR include Multiple diseases predictions using machine learning, deep learning, and IoMT. The rest of the paper is structured as follows: Sect. 1 presents a Background about the used technologies, Sect. 2 presents Material and Methods. The Sect. 3 is for Results and Interpretation, and we conclude the paper with general discussion and perspectives.
2 Background
2.1 Machine Learning
According to Arthur Samuel [6], ML is the area of study that enables computers to learn autonomously, without requiring explicit programming. It is used for training machines to handle data more efficiently [6]. ML implements complex algorithms to recognize patterns in large amounts of data and predict outcomes independently of specific codes. We can classify ML into three classes: unsupervised, supervised, semi-supervised, and reinforcement learning. Supervised learning is where ML algorithms are trained on labeled data. Semi-supervised learning techniques have the ability to train machine learning models using both labeled and unlabeled data. Meanwhile, unsupervised learning algorithms aim to identify natural connections and patterns within unlabelled data. Reinforcement learning, on the other hand, is a general concept for ML approaches that include both prediction and decision-making. Such ML technology has an iterative approach to learning and can adapt based on initial feedback [7]. The Table 1 presents the ML algorithms used in this systematic review:
2.2 Deep Learning
A DL architecture is an artificial neural network (ANN) having two or more hidden layers to achieve higher prediction accuracy [10]. Deep learning applications in health care cover various problems, such as cancer detection, disease monitoring, and individual treatment advice. Deep learning works through learning models in data structures with neural networks of multiple convolution nodes of artificial neurons [11].
2.3 Internet of Medical Things (IoMT)
The term IoMT is used to describe the interconnection of medical devices. Devices that communicate effectively with one another and integrate into larger-scale healthcare systems to improve patient health [12]. IoMT devices allow for healthcare monitoring without the need for human intervention through the integration of automation, interfacing sensors. IoMT technology enables patients to remotely connect with clinicians, granting them access to medical care from a distance and transfer medical data over a secure network [13].
3 Material and Methods
3.1 Search Strategy
A systematic literature review defines the available technologies and approaches applied to evaluate the clinical efficacy of CDS systems in disease detection and prediction. The references used in the review study were found through searches of papers in Google Scholar, IEEE Xplore Digital Library, Springer, and Elsevier, including a combination of ML keywords (Artificial Intelligence, Disease Prediction, machine learning, IoMT, Deep learning, and medical decision support systems). The articles used in this research consist of papers from 2018.
3.2 Identify the Research Questions
The Table 2 the motivations of our research:
3.3 Study Selection and Data Used in the Articles
Researchers demonstrated the effectiveness of the new technologies; they applied innovative systems built on machine learning and deep learning, in addition to IoMT. They used different algorithms to demonstrate the benefit of artificial intelligence along with their methodologies. To apply the different algorithms, they have used various data gathered from The Cleveland heart disease dataset 2016 which is publicly available from the University of California, Slides of human cancer tissue from the NCT biobank and the UMM pathology, (the Genomic Data Commons Data Portal (TCGA Pan-Cancer Clinical Data Resource), (Shandong Provincial Hospital dataset), (the Radiological Society of North America (RSNA)), Some researchers have encountered a few data sets, joined them, and built new one to work on (the Cleveland, Hungary, Switzerland, VA Long Beach, and Starlog heart disease dataset).
4 Results and Interpretation:
We divided this section into 2 parts, First, we presents researches applying Machine Learning algorithms to diagnose diseases with IoMT. The second part includes and discusses studies using deep learning and IoMT to predict diseases.
4.1 Machine Learning and IoMT-Based Diagnostic Applications
ML is increasingly used across various fields, including diagnosing diseases in healthcare. Many researchers have offered decision support systems for diagnosis based on machine learning [15]. In [14] researchers proposed a smart medical decision support system for the detection of heart disease, through several models such as LR, KNN, ANN, to classify individuals with cardiac diseases and individuals in a normal state. The proposal in [14] reached a 91.10% classification accuracy [14]. Other researchers used effective collection, pre-processing of data and data transformation methods to generate precise information for the training model for heart disease prediction. They used KNN for the missing data and Relief and LASSO for features extraction. The accuracy achieved is 99.05% [16]. Another study about heart disease prediction discussed in [17], researchers implemented the model prediction with 5 Active learning methods (MMC, Random, Adaptive, QUIRE, and AUDI). The experiments consist of using hyper-parameter optimization by the grid search technique. [17]. Morshedul Bari Ant, at [18], focused on Alzheimer’s disease. He applied ML algorithms to detect dementia. This system was created with the OASIS (Open Access series of imaging studies) dataset which trained by SVM, logistic regression, decision tree, and random forest models [18]. The study in [19] suggested ML approaches used with blood test data to forecast the likelihood of COVID-19-related death. A robust combination of five features predicts mortality with 96% accuracy. [19]. The main goal of the research in [20] was to explore the potential applications of big data analytics and machine learning-based techniques in diabetes. The proposed work achieves an accuracy of 83% [20]. Chronic Kidney Disease prediction was covered in the study [21], The researchers used the CKD dataset extracted from the UCI repository. Their major aim was the feature optimization. The developed model implemented 6 ML algorithms for training: ANN, C5.0, LR, LSVM, KNN, and random tree. The model’s most significant accuracy in SMOTE with all features was 98.86% [21]. Shahadat Uddin compared the performances of the K-nearest neighbor (KNN) algorithm and its variants (Classic one, Adaptive, Locally adaptive, k-means clustering, Fuzzy, Mutual, Ensemble, Hassanat, and Generalised mean distance) for forecasting eight diseases [22]. A further interesting disease to explore in [36] about skin cancer, Researchers presented a machine learning (ML) classification-based automated image-based system for the recognition, extraction, processing, and categorization of the skin. The proposed method extracts the most valuable features from the skin images with an accuracy of 87% [36]. In [23], The researchers proposed ML and IoMT-based model to provide clinical decision support to reduce doctors’ workload and decrease the death rate within the COVID-19 pandemic. The research described in [24] provided an ML model for a dataset of fundamental medical health that predicts what foods should be offered to particular patients according to their medical condition. The medical dataset consisted of 30 patient records with 13 features associated with various illnesses and 1000 items obtained from hospitals and the Internet. Andrei Velichk in [3] proposed a model for determining the presence of COVID-19 based on typical blood results. It applied 13 classifiers for examination and used the HGB approach for feature selection. The researchers used advanced Arduino computing and the IoMT cloud service [3]. The Table 3 summarizes researchers’ studies of medical decision-making systems with machine learning and IoMT:
4.2 Deep Learning and IoMT-Based Diagnostic Applications
The study in [25] presented a DL architecture to detect tumor and non tumor tissue in histological images of CRC. the model achieved a nine-class accuracy of 94% [25]. An end-to-end deep learning system (DLS) was proposed by the researchers In [26] to predict Survival for patients with various forms of cancer [26]. Researchers have proposed a global architecture of pathological type identification of lung cancer during the early stage by CT images. From the experimental outcomes, VGG16-T with boost has an accuracy rate of 86.58% [27]. In [28] the research presented A Novel Method to detect COVID-19 through AI in Chest X-ray Images. The researchers proposed two approaches: The first one for COVID-19 classification and evaluation. The second one, for the feature extraction [28]. Other researchers proposed a new automated DL method for multiclass brain tumor classification [29]. In [30] researchers proposed a decision support system through physicians’ knowledge that applied a fuzzy inference system (FIS). The reason for proposing such a system was that during the COVID-19 period, the datasets were not available. Therefore the solution was to benifit from the researchers’ knowledge. Marwa EL-Geneedy in [31] developed a learning-based pipeline to recognize Alzheimer’s multi-class disease with brain MRI images. The suggested approach provided both a local and a global categorization (i.e., normal vs. Mild Cognitive Impairment (MCI) vs. AD). The model reached 99.68% accuracy [31]. In [32], authors benefited from the advance of IoMT, and they proposed an IoMT-based fog calculation model to diagnose patients who suffered from type 2 diabetes [32]. Another study [33], consisted of a clinical decision support system with cloud-based IoMT for CKD prediction with DNN. The System gathers patient data through IoMT devices, and stored them in the cloud with their associated medical records from the UCI repository. The DNN classifier achieves a maximum classifier accuracy of 98.25% [33]. To extract precise characteristics from an MRI image, the researchers in [34] established a neural network model with a VGG16 feature extractor, with an accuracy of 90.40% for dataset 1 and 71.1% for dataset 2 [34]. The work [35] presented a new light-weight “Reduced-FireNet” deep learning based model for histopathology image self-classification [35].
Researchers [37] proposed a new approach to predict heart disease. They applied a pre-trained Deep Neural Network to extract feature, Principal Component Analysis (PCA) to reduce dimensionality, and Logistic Regression (LR) for prediction. The model suggested achieved an accuracy of 91.79% [37]. Roseline in [38] and other authors proposed an IoMT diagnosis system to identify breast cancer. The system consists of classifying the tissue into malignant and benign classes. The proposed model achieved a classification accuracy of 98.5% with CNN and 99.2% with ANN [38]. Oher research interest was about analyzing medical images using Deep Learning in real-time. The proposed system contains two parts: the first one aims to define the regions of interest (RoIs) where capillaries might exist, and the second part is to predict if the RoIs contain capillaries or not using CNN [39]. The study described in [40] focused on applying deep learning techniques to detect COVID-19. The proposed work used CNN architectures like VGG16, DeseNet121, MobileNet, NASNet, Xception, and EfficientNet [40]. The Table 4 summarizes researchers’ studies of medical decision-making systems with Deep learning and IoMT: [h]
5 Discussion
This systematic review is interested in the recent proposed approaches of IoT and AI that are used in healthcare, while addressing their benefits and weaknesses. This review demonstrates that there is a significant increase in the number of the proposed works in this research area. The adoption of AI in medical field can speed up the process of tumor diagnosis without the need to the histological examination that can take a lot of time. This is due to the progress in CPU computing power, the efficiency of recent ML and DL algorithms and the accessibility of huge amounts of data (big data) collected from electronic health monitors and medical health records. The presented work in this paper covered the involvement of machine and DL models along with IoMT in the diagnosis of cancer, diabetes, chronic diseases, heart, Alzheimer, and COVID. The machine learning models used include random forest classifier, logistic regression, decision tree, K-nearest neighbor (KNN), and support vector machines (SVM). Moreover, the deep learning models used include convolutional neural networks (CNN) have often been used for disease diagnosis and pre-trained models: VGG16, GoogleNet, Alexnet, Squeezenet, Resnet50. Despite the significant advantages of AI and IoT-based techniques in diagnosing diseases, many challenges remain to be overcome such as:
-
1.
The small size of the pre-processed datasets that can be used to evaluate the proposed approaches efficiency.
-
2.
The lack of efficient feature selection techniques to clean medical data while generating high precision in disease prediction.
-
3.
The problems of data security during the collection phase.
-
4.
The absence of models validation phase by medical experts.
6 Conclusion and Future Perspectives
AI is a broad field of approaches that combines data mining and analytics, machine learning and deep learning, data collection, and pattern recognition that is regularly evolving and growing to fit the criteria needed of the Healthcare sector and its Patients. This article explores the potential impact of technologies such as IoMT and AI in healthcare and the clinical support system through a systematic literature review of 27 published papers. To clarify the performance of AI and IoMT in clinical support systems, This current study was divided into three sections covering applications for machine learning- and deep learning-based diagnostics, and IoMT-based applications. The main conclusions build across this paper state that the approaches of AI and IoMT in the clinical support system for disease detection, prediction, and patient monitoring are an avoidable path to migrate toward precision medicine. However, problems like lack of data, ethical and data security, and non-practical accuracy represent the major research challenges that need to be addressed. Therefore, in future work, we aim to elaborate and introduce technical and research solutions for aiding intelligent medical support systems to provide secure and robust models. Due to the continuous progress in artificial intelligence and IoMT fields, there are many opportunities for extending the research presented in this work. Although our SLR has highlighted the potential of AI and IoMT technologies to predict and prevent the onset of various diseases, it still needs improvement to be suitable for the medical field. In our future works, we will focus on the potential of innovative deep learning and machine learning methods. Furthermore, to improve the predictive performance of these models, researchers need to integrate other data sources such as genetic and environmental factors. To determine the most effective fusion among data sources and modeling approaches for various illness types, additional investigation is also needed. Real-time illness forecasting systems which can be implemented to support medical decision making is another research area in our further studies.
References
Merabet, A., Ferradji, M.A.: Smart virtual environment to support collaborative medical diagnosis. In: 2022 4th International Conference on Pattern Analysis and Intelligent Systems (PAIS), pp. 1–6. IEEE, October 2022
Afrash, M.R., Erfanniya, L., Amraei, M., Mehrabi, N., Jelvay, S., Shanbehzadeh, M.: Machine learning-based clinical decision support system for automatic diagnosis of COVID-19 based on the routine blood test. J. Biostat. Epidemiol. 8(1), 77–89 (2022)
Velichko, A., Huyut, M.T., Belyaev, M., Izotov, Y., Korzun, D.: Machine learning sensors for diagnosis of COVID-19 disease using routine blood values for internet of things application. Sensors 22(20), 7886 (2022)
Ibrahim, I., Abdulazeez, A.: The role of machine learning algorithms for diagnosing diseases. J. Appl. Sci. Technol. Trends 2(01), 10–19 (2021)
Kashani, M.H., Madanipour, M., Nikravan, M., Asghari, P., Mahdipour, E.: A systematic review of IoT in healthcare: applications, techniques, and trends. J. Netw. Comput. Appl. 192, 103164 (2021)
Mahesh, B.: Machine learning algorithms-a review. Int. J. Sci. Res. (IJSR). [Internet] 9, 381–386 (2020)
Feng, Y., Wang, Y., Zeng, C., Mao, H.: Artificial intelligence and machine learning in chronic airway diseases: focus on asthma and chronic obstructive pulmonary disease. Int. J. Med. Sci. 18(13), 2871 (2021)
Tiwari, D., Bhati, B.S., Al-Turjman, F., Nagpal, B.: Pandemic coronavirus disease (COVID-19): world effects analysis and prediction using machine-learning techniques. Expert. Syst. 39(3), e12714 (2022)
Nusinovici, S., et al.:Logistic regression was as good as machine learning for predicting major chronic diseases. J. Clin. Epidemiol. 122, 56–69 (2020)
Shamshirband, S., Fathi, M., Dehzangi, A., Chronopoulos, A.T., Alinejad-Rokny, H.: A review on deep learning approaches in healthcare systems: taxonomies, challenges, and open issues. J. Biomed. Inform. 113, 103627 (2021)
Suganyadevi, S., Seethalakshmi, V., Balasamy, K.: A review on deep learning in medical image analysis. Int. J. Multimedia Inf. Retrieval 11(1), 19–38 (2022)
Gatouillat, A., Badr, Y., Massot, B., Sejdić, E.: Internet of medical things: a review of recent contributions dealing with cyber-physical systems in medicine. IEEE Internet Things J. 5(5), 3810–3822 (2018)
Manickam, P., Mariappan, S.A., Murugesan, S.M., Hansda, S., Kaushik, A., Shinde, R., Thipperudraswamy, S.P.: Artificial intelligence (AI) and internet of medical things (IoMT) assisted biomedical systems for intelligent healthcare. Biosensors 12(8), 562 (2022)
Haq, A.U., Li, J.P., Memon, M.H., Nazir, S., Sun, R.: A hybrid intelligent system framework for the prediction of heart disease using machine learning algorithms. Mob. Inf. Syst. (2018)
Ahsan, M.M., Luna, S.A., Siddique, Z.: Machine-learning-based disease diagnosis: a comprehensive review. In: Healthcare, vol. 10, no. 3, p. 541. MDPI, March 2022
Ghosh, P., et al.:Efficient prediction of cardiovascular disease using machine learning algorithms with relief and LASSO feature selection techniques. IEEE Access 9, 19304–19326 (2021)
El-Hasnony, I.M., Elzeki, O.M., Alshehri, A., Salem, H.: Multi-label active learning-based machine learning model for heart disease prediction. Sensors 22(3), 1184 (2022)
Bari Antor, M., et al.: A comparative analysis of machine learning algorithms to predict Alzheimer’s disease. J. Healthc. Eng. (2021)
Karthikeyan, A., Garg, A., Vinod, P.K., Priyakumar, U.D.: Machine learning based clinical decision support system for early COVID-19 mortality prediction. Front. Publ. Health 9, 626697 (2021)
Krishnamoorthi, R., et al.: A novel diabetes healthcare disease prediction framework using machine learning techniques. J. Healthc. Eng. (2022)
Chittora, P., et al.: Prediction of chronic kidney disease-a machine learning perspective. IEEE Access 9, 17312–17334 (2021)
Uddin, S., Haque, I., Lu, H., Moni, M.A., Gide, E.: Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction. Sci. Rep. 12(1), 1–11 (2022)
Abdulkareem, K.H., et al.: Realizing an effective COVID-19 diagnosis system based on machine learning and IOT in smart hospital environment. IEEE Internet Things J. 8(21), 15919–15928 (2021)
Iwendi, C., Khan, S., Anajemba, J.H., Bashir, A.K., Noor, F.: Realizing an efficient IoMT-assisted patient diet recommendation system through machine learning model. IEEE Access 8, 28462–28474 (2020)
Kather, J.N., et al.: Predicting survival from colorectal cancer histology slides using deep learning: a retrospective multicenter study. PLoS Med. 16(1), e1002730 (2019)
Wulczyn, E., et al.: Deep learning-based survival prediction for multiple cancer types using histopathology images. PloS ONE 15(6), e0233678 (2020)
Pang, S., et al.: VGG16-T: a novel deep convolutional neural network with boosting to identify pathological type of lung cancer in early stage by CT images. Int. J. Comput. Intell. Syst. 13(1), 771 (2020)
Almalki, Y.E., et al.: A novel method for COVID-19 diagnosis using artificial intelligence in chest X-ray images. In: Healthcare, vol. 9, no. 5, p. 522. Multidisciplinary Digital Publishing Institute, May 2021
Sharif, M.I., Khan, M.A., Alhussein, M., Aurangzeb, K., Raza, M.: A decision support system for multimodal brain tumor classification using deep learning. Complex Intell. Syst. 8(4), 3007–3020 (2022)
Govindan, K., Mina, H., Alavi, B.: A decision support system for demand management in healthcare supply chains considering the epidemic outbreaks: a case study of coronavirus disease 2019 (COVID-19). Transport. Res. Part E Logist. Transport. Rev. 138, 101967 (2020)
Marwa, E.G., Moustafa, H.E.D., Khalifa, F., Khater, H., AbdElhalim, E.: An MRI-based deep learning approach for accurate detection of Alzheimer’s disease. Alex. Eng. J. 63, 211–221 (2023)
Abdel-Basset, M., Manogaran, G., Gamal, A., Chang, V.: A novel intelligent medical decision support model based on soft computing and IoT. IEEE Internet Things J. 7(5), 4160–4170 (2019)
Lakshmanaprabu, S.K., Mohanty, S.N., Krishnamoorthy, S., Uthayakumar, J., Shankar, K.: Online clinical decision support system using optimal deep neural networks. Appl. Soft Comput. 81, 105487 (2019)
Sharma, S., Guleria, K., Tiwari, S., Kumar, S.: A deep learning based convolutional neural network model with VGG16 feature extractor for the detection of Alzheimer disease using MRI scans. Meas. Sens. 24, 100506 (2022)
Datta Gupta, K., Sharma, D.K., Ahmed, S., Gupta, H., Gupta, D., Hsu, C.H.: A novel lightweight deep learning-based histopathological image classification model for IoMT. Neural Process. Lett. 1–24 (2021)
Yu, Z., Wang, K., Wan, Z., Xie, S., Lv, Z.: Popular deep learning algorithms for disease prediction: a review. Cluster Comput. 1–21 (2022)
Hassan, D., Hussein, H.I., Hassan, M.M.: Heart disease prediction based on pre-trained deep neural networks combined with principal component analysis. Biomed. Sig. Process. Control 79, 104019 (2023)
Ogundokun, R.O., Misra, S., Douglas, M., Damaševičius, R., Maskeliūnas, R.: Medical internet-of-things based breast cancer diagnosis using hyperparameter-optimized neural networks. Future Internet 14(5), 153 (2022)
Abdou, M.A.H., Ferreira, P., Jul, E., Truong, T.T.: Capillaryx: a software design pattern for analyzing medical images in real-time using deep learning. arXiv preprint arXiv:2204.08462 (2022)
Kogilavani, S.V., et al.: COVID-19 detection based on lung CT scan using deep learning techniques. Comput. Math. Methods Med. (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Merabet, A., Saighi, A., Laboudi, Z., Ferradji, M.A. (2024). Multiple Diseases Forecast Through AI and IoMT Techniques: Systematic Literature Review. In: Bennour, A., Bouridane, A., Chaari, L. (eds) Intelligent Systems and Pattern Recognition. ISPR 2023. Communications in Computer and Information Science, vol 1940. Springer, Cham. https://doi.org/10.1007/978-3-031-46335-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-46335-8_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46334-1
Online ISBN: 978-3-031-46335-8
eBook Packages: Computer ScienceComputer Science (R0)