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

2022 ◽  
Vol 22 (3) ◽  
pp. 1-21
Author(s):  
Tongguang Ni ◽  
Jiaqun Zhu ◽  
Jia Qu ◽  
Jing Xue
Keyword(s):  
Privacy Protection ◽  
Local Area Network ◽  
Fog Computing ◽  
Disease Diagnosis ◽  
Classification Model ◽  
Support Vector ◽  
Area Network ◽  
Privileged Information ◽  
Class Label ◽  
Healthcare Applications

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.

Indoor Positioning in WLAN Environment Based on Support Vector Regression and Space Partitioning

2011 ◽  
Vol 204-210 ◽  
pp. 1599-1602 ◽  
Author(s):  
Zhi An Deng ◽  
Yu Bin Xu ◽  
Di Wu
Keyword(s):  
Support Vector Regression ◽  
Wireless Local Area Network ◽  
Local Area Network ◽  
Physical Space ◽  
Mapping Function ◽  
Local Area ◽  
Indoor Positioning ◽  
Support Vector ◽  
Area Network ◽  
Space Partitioning

Indoor positioning system in wireless local area network (WLAN) has been a subject of intensive research due to its cost effectiveness and reasonable positioning accuracy. A new WLAN indoor positioning algorithm based on support vector regression (SVR) and space partitioning is proposed. The whole positioning environment is partitioned into several subspaces by combining k-means clustering method and binary support vector classifiers (SVC). Then the mapping function between received signal strength (RSS) and the physical space is established by SVR machine for each subspace. Subspace with much smaller physical range means more compact input feature space and leads to the enhancement of generalization capability for each SVR machine. The proposed algorithm and other well-known positioning algorithms are carried and compared in a real WLAN environment. Experimental results show that the proposed algorithm achieves 14.6 percent (0.31m) improvement than the single SVR algorithm in the sense of mean positioning error.

scholarly journals The Evolution of Vector Machine Support in the Field of Intrusion Detection Systems

2021 ◽  
Author(s):  
Ouafae Elaeraj ◽  
Cherkaoui Leghris
Keyword(s):  
Intrusion Detection ◽  
Local Area Network ◽  
Detection Efficiency ◽  
Training Data ◽  
Intrusion Detection Systems ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Good Prediction ◽  
Area Network ◽  
Detection Systems

With the increase in Internet and local area network usage, malicious attacks and intrusions into computer systems are growing. The design and implementation of intrusion detection systems became extremely important to help maintain good network security. Support vector machines (SVM), a classic pattern recognition tool, has been widely used in intrusion detection. They make it possible to process very large data with great efficiency and are easy to use, and exhibit good prediction behavior. This paper presents a new SVM model enriched with a Gaussian kernel function based on the features of the training data for intrusion detection. The new model is tested with the CICIDS2017 dataset. The test proves better results in terms of detection efficiency and false alarm rate, which can give better coverage and make the detection more effective.

IoT with Cloud Based End to End Secured Disease Diagnosis Model using Light Weight Cryptography and Gradient Boosting Tree

2020 ◽  
Vol 13 ◽  
Author(s):  
K. Shankar
Keyword(s):  
Internet Of Things ◽  
Disease Diagnosis ◽  
Classification Model ◽  
Gradient Boosting ◽  
The Internet ◽  
Pima Indians ◽  
Healthcare Applications ◽  
Diagnosis Model ◽  
Consistent Performance ◽  
The Internet Of Things

Background: With the evolution of the Internet of Things (IoT) technology and connected devices employed in the medicinal domain, the different characteristics of the online healthcare applications become advantageous. Aim: The objective of this paper is to present an IoT and cloud-based secured disease diagnosis model. At present, various e-healthcare applications with the use of the Internet of Things (IoT) offers diverse dimensions and services online. Method: In this paper, an efficient IoT and cloud-based secured classification model are proposed for disease diagnosis. It is used to avail efficient and secured services to the people globally over online healthcare applications. The presented model includes an effective gradient boosting tree (GBT) based data classification and lightweight cryptographic technique named rectangle. The presented GBT–R model offers a better diagnosis in a secure way. Results: It is validated using the Pima Indians diabetes data, and extensive simulation takes place to verify the consistent performance of the employed GBT-R model. Conclusion: The experimental outcome strongly suggested that the presented model shows maximum performance with an accuracy of 94.92.

scholarly journals Emphasis Learning, Features Repetition in Width Instead of Length to Improve Classification Performance: Case Study—Alzheimer’s Disease Diagnosis

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 941
Author(s):  
Hamid Akramifard ◽  
MohammadAli Balafar ◽  
SeyedNaser Razavi ◽  
Abd Rahman Ramli
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Principal Component ◽  
Classification Problem ◽  
Disease Diagnosis ◽  
Classification Model ◽  
Support Vector ◽  
Svm Classifier ◽  
Small Subset ◽  
Alzheimer’S Disease Diagnosis

In the past decade, many studies have been conducted to advance computer-aided systems for Alzheimer’s disease (AD) diagnosis. Most of them have recently developed systems concentrated on extracting and combining features from MRI, PET, and CSF. For the most part, they have obtained very high performance. However, improving the performance of a classification problem is complicated, specifically when the model’s accuracy or other performance measurements are higher than 90%. In this study, a novel methodology is proposed to address this problem, specifically in Alzheimer’s disease diagnosis classification. This methodology is the first of its kind in the literature, based on the notion of replication on the feature space instead of the traditional sample space. Briefly, the main steps of the proposed method include extracting, embedding, and exploring the best subset of features. For feature extraction, we adopt VBM-SPM; for embedding features, a concatenation strategy is used on the features to ultimately create one feature vector for each subject. Principal component analysis is applied to extract new features, forming a low-dimensional compact space. A novel process is applied by replicating selected components, assessing the classification model, and repeating the replication until performance divergence or convergence. The proposed method aims to explore most significant features and highest-preforming model at the same time, to classify normal subjects from AD and mild cognitive impairment (MCI) patients. In each epoch, a small subset of candidate features is assessed by support vector machine (SVM) classifier. This repeating procedure is continued until the highest performance is achieved. Experimental results reveal the highest performance reported in the literature for this specific classification problem. We obtained a model with accuracies of 98.81%, 81.61%, and 81.40% for AD vs. normal control (NC), MCI vs. NC, and AD vs. MCI classification, respectively.

scholarly journals Developing the Next Generation of Augmented Reality Games for Pediatric Healthcare: An Open-Source Collaborative Framework Based on ARCore for Implementing Teaching, Training and Monitoring Applications

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1865
Author(s):  
Aida Vidal-Balea ◽  
Óscar Blanco-Novoa ◽  
Paula Fraga-Lamas ◽  
Tiago M. Fernández-Caramés
Keyword(s):  
Augmented Reality ◽  
Open Source ◽  
Web Application ◽  
Local Area Network ◽  
Local Area ◽  
Area Network ◽  
Healthcare Applications ◽  
Detection Technology ◽  
Real Time Visualization ◽  
Pediatric Healthcare

Augmented Reality (AR) provides an alternative to the traditional forms of interaction between humans and machines, and facilitates the access to certain technologies to groups of people with special needs like children. For instance, in pediatric healthcare, it is important to help children to feel comfortable during medical procedures and tests that may be performed on them. To tackle such an issue with the help of AR-based solutions, this article presents the design, implementation and evaluation of a novel open-source collaborative framework that enables to develop teaching, training, and monitoring pediatric healthcare applications. Specifically, such a framework allows for building collaborative applications and shared experiences for AR devices, providing functionalities for connecting with other AR devices and enabling real-time visualization and simultaneous interaction with virtual objects. Since all the communications involved in AR interactions are handled by AR devices, the proposed collaborative framework is able to operate autonomously through a Local Area Network (LAN), thus requiring no cloud or external servers. In order to demonstrate the potential of the proposed framework, a practical use case application is presented. Such an application has been designed to motivate pediatric patients and to encourage them to increase their physical activity through AR games. The presented games do not require any previous configuration, as they use ARCore automatic surface detection technology. Moreover, the AR mobile gaming framework allows multiple players to engage in the same AR experience, so children can interact and collaborate among them sharing the same AR content. In addition, the proposed AR system provides a remote web application that is able to collect and to visualize data on patient use, aiming to provide healthcare professionals with qualified data about the mobility and mood of their patients through an intuitive and user-friendly web tool. Finally, to determine the performance of the proposed AR system, this article presents its evaluation in terms of latency and processing time. The results show that both times are low enough to provide a good user experience.

scholarly journals Artificial Intelligence Analysis of EEG Amplitude in Intensive Heart Care

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Junjun Chen ◽  
Hong Pu ◽  
Dianrong Wang
Keyword(s):  
Optimization Algorithm ◽  
Morphological Characteristics ◽  
Disease Diagnosis ◽  
Classification Model ◽  
Cardiac Monitoring ◽  
Twin Support Vector Machine ◽  
Support Vector ◽  
Cardiac Care ◽  
Public Data ◽  
Bioelectric Signals

This article first studied the morphological characteristics of the EEG for intensive cardiac care; that is, based on the analysis of the mechanism of disease diagnosis and treatment, a signal processing and machine learning model was constructed. Then, the methods of signal preprocessing, signal feature extraction, new neural network model structure, training mechanism, optimization algorithm, and efficiency are studied, and experimental verification is carried out for public data sets and clinical big data. Then, the principle of intensive cardiac monitoring, the mechanism of disease diagnosis, the types of arrhythmia, and the characteristics of the typical signal are studied, and the rhythm performance, individual variability, and neurophysiological basis of electrical signals in intensive cardiac monitoring are researched. Finally, the automatic signal recognition technology is studied. In order to improve the training speed and generalization ability, a multiclassification model based on Least Squares Twin Support Vector Machine (LS-TWIN-SVM) is proposed. The computational complexity of the classification model algorithm is compared, and intelligence is adopted. The optimization algorithm selects the parameters of the classifier and uses the EEG signal to simulate the model. Support Vector Machines and their improved algorithms have achieved the ultimum in shallow neural networks and have achieved good results in the classification and recognition of bioelectric signals. The LS-TWIN-SVM algorithm proposed in this paper has achieved good results in the classification and recognition of bioelectric signals. It can perform bioinformatics processing on intensive cardiac care EEG signals, systematically biometric information, diagnose diseases, the real-time detection, auxiliary diagnosis, and rehabilitation of patients.

scholarly journals Comparative analysis of classification algorithms for chronic kidney disease diagnosis

2019 ◽  
Vol 8 (4) ◽  
Author(s):  
Zainuri Saringat ◽  
Aida Mustapha ◽  
R. D. Rohmat Saedudin ◽  
Noor Azah Samsudin
Keyword(s):  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Supervised Classification ◽  
Bone Fractures ◽  
Kidney Diseases ◽  
Disease Diagnosis ◽  
Classification Model ◽  
Support Vector ◽  
Classification Algorithms ◽  
Nearest Neighbour

Chronic Kidney Disease (CKD) is one of the leading cause of death contributed by other illnesses such as diabetes, hypertension, lupus, anemia or weak bones that lead to bone fractures. Early prediction of CKD is important in order to contain the disesase. However, instead of predicting the severity of CKD, the objective of this paper is to predict the diagnosis of CKD based on the symptoms or attributes observed in a particular case, whether the stage is acute or chronic. To achieve this, a classification model is proposed to label stage of severity for kidney diseases patients. The experiments then investigated the performance of the proposed classification model based on eight supervised classification algorithms, which are ZeroR, Rule Induction, Support Vector Machine, Naïve Bayes, Decision Tree, Decision Stump, k-Nearest Neighbour, and Classification via Regression. The performance of the all classifiers is evaluated based on accuracy, precision, and recall. The results showed that the regression classifier perform best in the kidney diagnostic procedure.

Strathnet—a local area network

1981 ◽  
Vol 1 (1) ◽  
pp. 21 ◽  
Author(s):  
David Hutchison ◽  
Doug Shepherd
Keyword(s):  
Local Area Network ◽  
Local Area ◽  
Area Network

A Local Area Network for Medical Research; Planning, Realization and Experience

1991 ◽  
Vol 30 (01) ◽  
pp. 53-64 ◽  
Author(s):  
R. Schosser ◽  
C. Weiss ◽  
K. Messmer
Keyword(s):  
Medical Research ◽  
Word Processing ◽  
Local Area Network ◽  
Local Area ◽  
Area Network ◽  
Test Installation ◽  
Cost Performance ◽  
The Public ◽  
On Line ◽  
The University

This report focusses on the planning and realization of an interdisciplinary local area network (LAN) for medical research at the University of Heidelberg. After a detailed requirements analysis, several networks were evaluated by means of a test installation, and a cost-performance analysis was carried out. At present, the LAN connects 45 (IBM-compatible) PCs, several heterogeneous mainframes (IBM, DEC and Siemens) and provides access to the public X.25 network and to wide-area networks for research (EARN, BITNET). The network supports application software that is frequently needed in medical research (word processing, statistics, graphics, literature databases and services, etc.). Compliance with existing “official” (e.g., IEEE 802.3) and “de facto” standards (e.g., PostScript) was considered to be extremely important for the selection of both hardware and software. Customized programs were developed to improve access control, user interface and on-line help. Wide acceptance of the LAN was achieved through extensive education and maintenance facilities, e.g., teaching courses, customized manuals and a hotline service. Since requirements of clinical routine differ substantially from medical research needs, two separate networks (with a gateway in between) are proposed as a solution to optimally satisfy the users’ demands.

Sign in / Sign up

Export Citation Format

Share Document