A Novel Framework for Generating Personalized Network Datasets for NIDS Based on Traffic Aggregation.

In this paper, we addressed the problem of dataset scarcity for the task of network intrusion detection. Our main contribution was to develop a framework that provides a complete process for generating network traffic datasets based on the aggregation of real network traces. In addition, we proposed a set of tools for attribute extraction and labeling of traffic sessions. A new dataset with botnet network traffic was generated by the framework to assess our proposed method with machine learning algorithms suitable for unbalanced data. The performance of the classifiers was evaluated in terms of macro-averages of F1-score (0.97) and the Matthews Correlation Coefficient (0.94), showing a good overall performance average.

Segmentation of the ECG Signal by Means of a Linear Regression Algorithm.

The monitoring and processing of electrocardiogram (ECG) beats have been actively studied in recent years: new lines of research have even been developed to analyze ECG signals using mobile devices. Considering these trends, we proposed a simple and low computing cost algorithm to process and analyze an ECG signal. Our approach is based on the use of linear regression to segment the signal, with the goal of detecting the R point of the ECG wave and later, to separate the signal in periods for detecting P, Q, S, and T peaks. After pre-processing of ECG signal to reduce the noise, the algorithm was able to efficiently detect fiducial points, information that is transcendental for diagnosis of heart conditions using machine learning classifiers. When tested on 260 ECG records, the detection approach performed with a Sensitivity of 97.5% for Q-point and 100% for the rest of ECG peaks. Finally, we validated the robustness of our algorithm by developing an ECG sensor to register and transmit the acquired signals to a mobile device in real time.

Mobile Personal Health Care System for Noninvasive, Pervasive, and Continuous Blood Pressure Monitoring: Development and Usability Study.

BACKGROUND: Smartphone-based blood pressure (BP) monitoring using photoplethysmography (PPG) technology has emerged as a promising approach to empower users with self-monitoring for effective diagnosis and control of hypertension. OBJECTIVE: This study aimed to develop a mobile personal health care system for noninvasive, pervasive, and continuous estimation of BP level and variability, which is user friendly for elderly people. METHODS: The proposed approach was integrated by a self-designed cuffless, calibration-free, wireless, and wearable PPG-only sensor and a native purposely designed smartphone app using multilayer perceptron machine learning techniques from raw signals. We performed a development and usability study with three older adults (mean age 61.3 years, SD 1.5 years; 66% women) to test the usability and accuracy of the smartphone-based BP monitor. RESULTS: The employed artificial neural network model had good average accuracy (>90%) and very strong correlation (>0.90) (P<.001) for predicting the reference BP values of our validation sample (n=150). Bland-Altman plots showed that most of the errors for BP prediction were less than 10 mmHg. However, according to the Association for the Advancement of Medical Instrumentation and British Hypertension Society standards, only diastolic blood pressure prediction met the clinically accepted accuracy thresholds. CONCLUSIONS: With further development and validation, the proposed system could provide a cost-effective strategy to improve the quality and coverage of health care, particularly in rural zones, areas lacking physicians, and areas with solitary elderly populations.

Mobile Personal Health Monitoring for Automated Classification of Electrocardiogram Signals in Elderly.

Mobile electrocardiogram (ECG) monitoring is an emerging area that has received increasing attention in recent years, but still real-life validation for elderly residing in low and middle-income countries is scarce. We developed a wearable ECG monitor that is integrated with a self-designed wireless sensor for ECG signal acquisition. It is used with a native purposely designed smartphone application, based on machine learning techniques, for automated classification of captured ECG beats from aged people. When tested on 100 older adults, the monitoring system discriminated normal and abnormal ECG signals with a high degree of accuracy (97%), sensitivity (100%), and specificity (96.6%). With further verification, the system could be useful for detecting cardiac abnormalities in the home environment and contribute to prevention, early diagnosis, and effective treatment of cardiovascular diseases, while keeping costs down and increasing access to healthcare services for older persons.

Mobile personal health system for ambulatory blood pressure monitoring.

The ARVmobile v1.0 is a multiplatform mobile personal health monitor (PHM) application for ambulatory blood pressure (ABP) monitoring that has the potential to aid in the acquisition and analysis of detailed profile of ABP and heart rate (HR), improve the early detection and intervention of hypertension, and detect potential abnormal BP and HR levels for timely medical feedback. The PHM system consisted of ABP sensor to detect BP and HR signals and smartphone as receiver to collect the transmitted digital data and process them to provide immediate personalized information to the user. Android and Blackberry platforms were developed to detect and alert of potential abnormal values, offer friendly graphical user interface for elderly people, and provide feedback to professional healthcare providers via e-mail. ABP data were obtained from twenty-one healthy individuals (>51 years) to test the utility of the PHM application. The ARVmobile v1.0 was able to reliably receive and process the ABP readings from the volunteers. The preliminary results demonstrate that the ARVmobile 1.0 application could be used to perform a detailed profile of ABP and HR in an ordinary daily life environment, bedsides of estimating potential diagnostic thresholds of abnormal BP variability measured as average real variability.

Machine learning approach to extract diagnostic and prognostic thresholds: application in prognosis of cardiovascular mortality.

Machine learning has become a powerful tool for analysing medical domains, assessing the importance of clinical parameters, and extracting medical knowledge for outcomes research. In this paper, we present a machine learning method for extracting diagnostic and prognostic thresholds, based on a symbolic classification algorithm called REMED. We evaluated the performance of our method by determining new prognostic thresholds for well-known and potential cardiovascular risk factors that are used to support medical decisions in the prognosis of fatal cardiovascular diseases. Our approach predicted 36% of cardiovascular deaths with 80% specificity and 75% general accuracy. The new method provides an innovative approach that might be useful to support decisions about medical diagnoses and prognoses.