Labeling Privacy Protection SVM Using Privileged Information for COVID-19 Diagnosis

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.

Nanofiber Systems as Herbal Bioactive Compounds Carriers: Current Applications in Healthcare

Nanofibers have emerged as a potential novel platform due to their physicochemical properties for healthcare applications. Nanofibers’ advantages rely on their high specific surface-area-to-volume and highly porous mesh. Their peculiar assembly allows cell accommodation, nutrient infiltration, gas exchange, waste excretion, high drug release rate, and stable structure. This review provided comprehensive information on the design and development of natural-based polymer nanofibers with the incorporation of herbal medicines for the treatment of common diseases and their in vivo studies. Natural and synthetic polymers have been widely used for the fabrication of nanofibers capable of mimicking extracellular matrix structure. Among them, natural polymers are preferred because of their biocompatibility, biodegradability, and similarity with extracellular matrix proteins. Herbal bioactive compounds from natural extracts have raised special interest due to their prominent beneficial properties in healthcare. Nanofiber properties allow these systems to serve as bioactive compound carriers to generate functional matrices with antimicrobial, anti-inflammatory, antioxidant, antiseptic, anti-viral, and other properties which have been studied in vitro and in vivo, mostly to prove their wound healing capacity and anti-inflammation properties.

EEG Channel Selection Using Multiobjective Cuckoo Search for Person Identification as Protection System in Healthcare Applications

Recently, the electroencephalogram (EEG) signal presents an excellent potential for a new person identification technique. Several studies defined the EEG with unique features, universality, and natural robustness to be used as a new track to prevent spoofing attacks. The EEG signals are a visual recording of the brain’s electrical activities, measured by placing electrodes (channels) in various scalp positions. However, traditional EEG-based systems lead to high complexity with many channels, and some channels have critical information for the identification system while others do not. Several studies have proposed a single objective to address the EEG channel for person identification. Unfortunately, these studies only focused on increasing the accuracy rate without balancing the accuracy and the total number of selected EEG channels. The novelty of this paper is to propose a multiobjective binary version of the cuckoo search algorithm (MOBCS-KNN) to find optimal EEG channel selections for person identification. The proposed method (MOBCS-KNN) used a weighted sum technique to implement a multiobjective approach. In addition, a KNN classifier for EEG-based biometric person identification is used. It is worth mentioning that this is the initial investigation of using a multiobjective technique with EEG channel selection problem. A standard EEG motor imagery dataset is used to evaluate the performance of the MOBCS-KNN. The experiments show that the MOBCS-KNN obtained accuracy of 93.86 % using only 24 sensors with AR 20 autoregressive coefficients. Another critical point is that the MOBCS-KNN finds channels not too close to each other to capture relevant information from all over the head. In conclusion, the MOBCS-KNN algorithm achieves the best results compared with metaheuristic algorithms. Finally, the recommended approach can draw future directions to be applied to different research areas.

An Easy-to-Use Protocol for Segmenting and 3-D Printing Craniofacial CT-Images Using Open-Source Software

Introduction: Stereolithography, also known as 3D printing (3DP), is a versatile and useful technology with many healthcare applications. While 3DP has gained tremendous popularity, it remains a daunting and perceptibly time-consuming process for the inexperienced user, with most turning to commercially printed products. Commercial vendors are expensive. We propose that 3DP is feasible for the inexperienced user with the appropriate knowledge and tools. Methods: A 3DP protocol was created for model design and printing using open-source software and a low-cost desktop printer. It was betatested by 3 inexperienced users. The fidelity of the protocol was then tested in direct comparison to industry models made for 3 patients undergoing mandibular distraction osteogenesis, using standard cephalometric measurements. Results: All inexperienced testers were able to successfully create a 3D model using the easy-to-follow protocol without the use of any other resources. The models were created in a mean time of 170 minutes. All cephalometric measurements on the open-source printed models were equal to within 0.5 to 1.0 mm of the respective industry models. Conclusions: As the 3DP process is simplified and desktop printers and materials become more affordable, we anticipate that its implementation will become more commonplace. We describe a step-by-step, protocol using open-source software and affordable materials to create 3D models.

Improved Handover Authentication in Fifth-Generation Communication Networks Using Fuzzy Evolutionary Optimisation with Nanocore Elements in Mobile Healthcare Applications

Authentication is a suitable form of restricting the network from different types of attacks, especially in case of fifth-generation telecommunication networks, especially in healthcare applications. The handover and authentication mechanism are one such type that enables mitigation of attacks in health-related services. In this paper, we model an evolutionary model that uses a fuzzy evolutionary model in maintaining the handover and key management to improve the performance of authentication in nanocore technology-based 5G networks. The model is designed in such a way that it minimizes the delays and complexity while authenticating the networks in 5G networks. The attacks are mitigated using an evolutionary model when it is trained with the relevant attack datasets, and the model is validated to mitigate the attacks. The simulation is conducted to test the efficacy of the model, and the results of simulation show that the proposed method is effective in improving the handling and authentication and mitigation against various types of attacks in mobile health applications.

IoT Security Issues, Challenges, Threats, and Solutions in Healthcare Applications

A majority of the applications now go wireless involving IoT as a technology to communicate to their respective destination. IoT is considered as a future of internet. The internet of things integration and efficient communication of the patient health monitoring parameters is the need of the hour in this pandemic. This chapter discusses the three-layer architecture involving hardware communication protocols supporting a layer of healthcare services and applications. Also, the data-guarantee, security and integrity issues, threats risks, and solutions involving deployment of efficient privacy, control, integration methods to confront various prominent and erroneous data manipulation techniques, malicious, and a series of cyber-attacks are proposed. The deployment of various efficient privacy and security protocols in IoT networks is of extreme need to ensure the confidentiality, access-control, authentication, and integrity of the health data transferred and to guarantee the availability of the services to the user at any point of time.