Abstract
Edge/fog computing works at the local area network level or devices connected to the sensor or the gateway close to the sensor. These nodes are located in different degrees of proximity to the user, while the data processing and storage are distributed among multiple nodes. In healthcare applications in the Internet of things, when data is transmitted through insecure channels, its privacy and security are the main issues. In recent years, learning from label proportion methods, represented by inverse calibration (InvCal) method, have tried to predict the class label based on class label proportions in certain groups. For privacy protection, the class label of the sample is often sensitive and invisible. As a compromise, only the proportion of class labels in certain groups can be used in these methods. However, due to their weak labeling scheme, their classification performance is often unsatisfactory. In this article, a labeling privacy protection support vector machine using privileged information, called LPP-SVM-PI, is proposed to promote the accuracy of the classifier in infectious disease diagnosis. Based on the framework of the InvCal method, besides using the proportion information of the class label, the idea of learning using privileged information is also introduced to capture the additional information of groups. The slack variables in LPP-SVM-PI are represented as correcting function and projected into the correcting space so that the hidden information of training samples in groups is captured by relaxing the constraints of the classification model. The solution of LPP-SVM-PI can be transformed into a classic quadratic programming problem. The experimental dataset is collected from the Coronavirus disease 2019 (COVID-19) transcription polymerase chain reaction at Hospital Israelita Albert Einstein in Brazil. In the experiment, LPP-SVM-PI is efficiently applied for COVID-19 diagnosis.
- [1] . 2019. Enabling workload engineering in edge, fog, and cloud computing through open-stack-based middleware. ACM Trans. Internet Technol. 19, 2 (2019), 28, 1–22. Google Scholar
Digital Library
- [2] . 2019. Cloud, fog, or mist in IoT? That is the question. ACM Trans. Internet Technol. 19, 2 (2019), 1533–5399. Google Scholar
Digital Library
- [3] . 2020. Cloud-based enabling mechanisms for container deployment and migration at the network edge. ACM Trans. Internet Technol. 20, 3 (2020), 1–28. Google Scholar
Digital Library
- [4] . 2017. Smart health care: an edge-side computing perspective. IEEE Consum. Electron. Mag. 7, 1 (2017), 29–37.Google Scholar
Cross Ref
- [5] . 2018. A fog-based healthcare framework for Chikungunya. IEEE Internet Things J. 5, 2 (2018), 794–801.Google Scholar
Cross Ref
- [6] . 2017. Fog computing in healthcare-a review and discussion. IEEE Access 5 (2017), 9206–9222.Google Scholar
Cross Ref
- [7] . 2019. A fog-based application for human activity recognition using personal smart devices. ACM Trans. Internet Technol. 19, 2 (2019), 20, 1–20. Google Scholar
Digital Library
- [8] . 2019. Edge computing for smart health: Context-aware approaches, opportunities, and challenges. IEEE Netw. 33, 3 (2019), 196–203.Google Scholar
Cross Ref
- [9] 2019. A neutrosophic theory-based security approach for fog and mobile-edge computing. Comput. Netw. 157, 5 (2019), 122–132.Google Scholar
Cross Ref
- [10] . 2017. An intelligent and secure system for predicting and preventing zika virus outbreak using fog computing. Enterprise Info. Syst. 11, 9 (2017), 1436–1456. Google Scholar
Digital Library
- [11] . 2020. A home hospitalization system based on the Internet of things, Fog computing and cloud computing. Info. Med. Unlocked 20 (2020), 100368.Google Scholar
Cross Ref
- [12] . 2020. A survey on deep transfer learning to edge computing for mitigating the COVID-19 pandemic. J. Syst. Architect. 108, 9 (2020), 101830.Google Scholar
Cross Ref
- [13] . 2018. Fog-cloud based cyber-physical system for distinguishing, detecting and preventing mosquito borne diseases. Future Gen. Comput. Syst. 88, 11 (2018), 764–775.Google Scholar
Cross Ref
- [14] . 2021. A drone-based networked system and methods for combating coronavirus disease (COVID-19) pandemic. Future Gen. Comput. Syst. 115, 2 (2021) 1–19.Google Scholar
Cross Ref
- [15] . 2018. Fog assisted-IoT enabled patient health monitoring in smart homes. IEEE Internet Things J. 5, 3 (2018), 1789–1796.Google Scholar
Cross Ref
- [16] . 2018. A study on medical Internet of Things and big data in personalized healthcare system. Health Info. Sci. Syst. 6, 14 (2018), 1–20.Google Scholar
- [17] . 2017. Survey of main challenges (security and privacy) in wireless body area networks for healthcare applications. Egypt. Info. J. 18, 2 (2017), 113–122.Google Scholar
Cross Ref
- [18] . 2020. A new transfer learning-based method for label proportions problem. Info. Sci. 541, 12 (2020), 391–408.Google Scholar
Cross Ref
- [19] . 2013. Learning Bayesian network classifiers from label proportions. Pattern Recogn. 46, 12 (2013), 3425–3440. Google Scholar
Digital Library
- [20] . 2015. Support vector machine with manifold regularization and partially labeling privacy protection. Info. Sci. 294, 10 (2015), 390–407. Google Scholar
Digital Library
- [21] . 2014. Learning a generative classifier from label proportions. Neurocomputing 139, 9 (2014), 47–55. Google Scholar
Digital Library
- [22] . 2005. Learning about individuals from group statistics. Proceedings of the 21st Conference on Uncertainty in Artificial Intelligence. AUAI Press, Corvallis, July 2005, 332–339. Google Scholar
Digital Library
- [23] 2009. Estimating labels from label proportions. J. Mach. Learn. Res. 10, 82 (2009), 2349–2374. Google Scholar
Digital Library
- [24] . 2013. ∝SVM for learning with label proportions. In Proceedings of the 30th International Conference on Machine Learning. 504–512. Google Scholar
Digital Library
- [25] . 2018. Adaboost-LLP: A boosting method for learning with label proportions. IEEE Trans. Neural Netw. Learn. Syst. 29, 8 (2018), 3548–3559.Google Scholar
Cross Ref
- [26] , and Zhiquan Qi. 2019. Learning from label proportions with pinball loss. International J. Mach. Learn. Cybernet. 10 (2019), 187–205.Google Scholar
Cross Ref
- [27] . 2010. SVM classifier estimation from group probabilities. In Proceedings of the 27th International Conference on Machine Learning (ICML’10). 911–918. Google Scholar
Digital Library
- [28] . 2009. A new learning paradigm: Learning using privileged information. Neural Netw. 22, 5 (2009), 544–557. Google Scholar
Digital Library
- [29] . 2014. A new one-class SVM based on hidden information. Knowl.-Based Syst. 60, 4 (2014), 35–43. Google Scholar
Digital Library
- [30] . 2016. Learning with label proportions via NPSVM. IEEE Trans. Cybernet. 47, 10 (2017), 3293–3305.Google Scholar
Cross Ref
- [31] . 2015. Learning using privileged information: Similarity control and knowledge transfer. J. Mach. Learn. Res. 16 (2015), 2023–2049. Google Scholar
Digital Library
- [32] . 2020. Prediction of epidemic trends in COVID-19 with logistic model and machine learning technics. Chaos, Solitons Fractals 139 (2020), 110058.Google Scholar
Cross Ref
- [33] 2020. Comparison of deep learning approaches to predict COVID-19 infection. Chaos, Solitons Fractals 140 (2020), 110120.Google Scholar
Cross Ref
- [34] . 2020. Extreme vector machine for fast training on large data. Int. J. Mach. Learn. Cybernet. 11, 1 (2020), 33–53.Google Scholar
Cross Ref
Index Terms
Labeling Privacy Protection SVM Using Privileged Information for COVID-19 Diagnosis
Recommendations
Semi-supervised multi-label classification using incomplete label information
Highlights- An inductive semi-supervised method called Smile is proposed for multi-label classification using incomplete label information.
AbstractClassifying multi-label instances using incompletely labeled instances is one of the fundamental tasks in multi-label learning. Most existing methods regard this task as supervised weak-label learning problem and assume sufficient ...
Privileged label enhancement with multi-label learning
IJCAI'20: Proceedings of the Twenty-Ninth International Joint Conference on Artificial IntelligenceLabel distribution learning has attracted more and more attention in view of its more generalized ability to express the label ambiguity. However, it is much more expensive to obtain the label distribution information of the data rather than the logical ...
Transductive Multilabel Learning via Label Set Propagation
The problem of multilabel classification has attracted great interest in the last decade, where each instance can be assigned with a set of multiple class labels simultaneously. It has a wide variety of real-world applications, e.g., automatic image ...






Comments