Security and Privacy Analysis of Youth-Oriented Connected Devices.

Under the Internet of Things paradigm, the emergence and use of a wide variety of connected devices and personalized telematics services have proliferated recently. As a result, along with the penetration of these devices in our daily lives, the users' security and privacy have been compromised due to some weaknesses in connected devices and underlying applications. This article focuses on analyzing the security and privacy of such devices to promote safe Internet use, especially by young people. First, the connected devices most used by the target group are classified, and an exhaustive analysis of the vulnerabilities that concern the user is performed. As a result, a set of differentiated security and privacy issues existing in the devices is identified. The study reveals that many of these vulnerabilities are related to the fact that device manufacturers often prioritize functionalities and services, leaving security aspects in the background. These companies even exploit the data linked to the use of these devices for various purposes, ignoring users' privacy rights. This research aims to raise awareness of severe vulnerabilities in devices and to encourage users to use them correctly. Our results help other researchers address these issues with a more global perspective.

AFOROS: A Low-Cost Wi-Fi-Based Monitoring System for Estimating Occupancy of Public Spaces.

Estimating the number of people present in a given venue in real-time is extremely useful from a security, management, and resource optimization perspective. This article presents the architecture of a system based on the use of Wi-Fi sensor devices that allows estimating, almost in real-time, the number of people attending an event that is taking place in a venue. The estimate is based on the analysis of the "probe request" messages periodically transmitted by smartphones to determine the existence of Wi-Fi access points in the vicinity. The method considers the MAC address randomization mechanisms introduced in recent years in smartphones, which prevents the estimation of the number of devices by simply counting different MAC addresses. To solve this difficulty, our Wi-Fi sensors analyze other fields present in the header of the IEEE 802.11 frames, the information elements, to extract a unique fingerprint from each smartphone. The designed system was tested in a set of real scenarios, obtaining an estimate of attendance at different public events with an accuracy close to 95%.

An IoT-Focused Intrusion Detection System Approach Based on Preprocessing Characterization for Cybersecurity Datasets.

Security in IoT networks is currently mandatory, due to the high amount of data that has to be handled. These systems are vulnerable to several cybersecurity attacks, which are increasing in number and sophistication. Due to this reason, new intrusion detection techniques have to be developed, being as accurate as possible for these scenarios. Intrusion detection systems based on machine learning algorithms have already shown a high performance in terms of accuracy. This research proposes the study and evaluation of several preprocessing techniques based on traffic categorization for a machine learning neural network algorithm. This research uses for its evaluation two benchmark datasets, namely UGR16 and the UNSW-NB15, and one of the most used datasets, KDD99. The preprocessing techniques were evaluated in accordance with scalar and normalization functions. All of these preprocessing models were applied through different sets of characteristics based on a categorization composed by four groups of features: basic connection features, content characteristics, statistical characteristics and finally, a group which is composed by traffic-based features and connection direction-based traffic characteristics. The objective of this research is to evaluate this categorization by using various data preprocessing techniques to obtain the most accurate model. Our proposal shows that, by applying the categorization of network traffic and several preprocessing techniques, the accuracy can be enhanced by up to 45%. The preprocessing of a specific group of characteristics allows for greater accuracy, allowing the machine learning algorithm to correctly classify these parameters related to possible attacks.

P-Ergonomics Platform: Toward Precise, Pervasive, and Personalized Ergonomics using Wearable Sensors and Edge Computing.

Preventive healthcare has attracted much attention recently. Improving people's lifestyles and promoting a healthy diet and wellbeing are important, but the importance of work-related diseases should not be undermined. Musculoskeletal disorders (MSDs) are among the most common work-related health problems. Ergonomists already assess MSD risk factors and suggest changes in workplaces. However, existing methods are mainly based on visual observations, which have a relatively low reliability and cover only part of the workday. These suggestions concern the overall workplace and the organization of work, but rarely includes individuals' work techniques. In this work, we propose a precise and pervasive ergonomic platform for continuous risk assessment. The system collects data from wearable sensors, which are synchronized and processed by a mobile computing layer, from which exposure statistics and risk assessments may be drawn, and finally, are stored at the server layer for further analyses at both individual and group levels. The platform also enables continuous feedback to the worker to support behavioral changes. The deployed cloud platform in Amazon Web Services instances showed sufficient system flexibility to affordably fulfill requirements of small to medium enterprises, while it is expandable for larger corporations. The system usability scale of 76.6 indicates an acceptable grade of usability.

Adaptive software architecture based on confident HCI for the deployment of sensitive services in Smart Homes.

Smart spaces foster the development of natural and appropriate forms of human-computer interaction by taking advantage of home customization. The interaction potential of the Smart Home, which is a special type of smart space, is of particular interest in fields in which the acceptance of new technologies is limited and restrictive. The integration of smart home design patterns with sensitive solutions can increase user acceptance. In this paper, we present the main challenges that have been identified in the literature for the successful deployment of sensitive services (e.g., telemedicine and assistive services) in smart spaces and a software architecture that models the functionalities of a Smart Home platform that are required to maintain and support such sensitive services. This architecture emphasizes user interaction as a key concept to facilitate the acceptance of sensitive services by end-users and utilizes activity theory to support its innovative design. The application of activity theory to the architecture eases the handling of novel concepts, such as understanding of the system by patients at home or the affordability of assistive services. Finally, we provide a proof-of-concept implementation of the architecture and compare the results with other architectures from the literature.

Characterization of User-Centered Security in Telehealth Services.

Emerging information and communication technologies are expected to foster new, efficient and accessible services for citizens, while guaranteeing the core principles of equality and privacy. Telehealth services are a clear example of a service in which technology can help enhance efficiency. The security of telehealth services is essential due to their critical nature. However, although ample efforts have been made to characterize security requirements for healthcare facilities, users are often worried because they are not aware of or do not understand the guarantees provided by the technology they are making use of. This paper describes the concept of User-Centered Security and characterizes it in the form of requirements. These requirements have been formalized in the form of a security architecture that should be utilized for each telehealth service during its design stage. Thus, such sensitive services will adequately manage patient fears regarding their correct operation. Finally, these requirements and the related security architecture have been validated by means of a test-case that is based on a real home telehealth service in order to ensure their consistency, completeness, realism and verifiability.

Outpatient Readmission in Rheumatology: A Machine Learning Predictive Model of Patient's Return to the Clinic.

Our objective is to develop and validate a predictive model based on the random forest algorithm to estimate the readmission risk to an outpatient rheumatology clinic after discharge. We included patients from the Hospital Clínico San Carlos rheumatology outpatient clinic, from 1 April 2007 to 30 November 2016, and followed-up until 30 November 2017. Only readmissions between 2 and 12 months after the discharge were analyzed. Discharge episodes were chronologically split into training, validation, and test datasets. Clinical and demographic variables (diagnoses, treatments, quality of life (QoL), and comorbidities) were used as predictors. Models were developed in the training dataset, using a grid search approach, and performance was compared using the area under the receiver operating characteristic curve (AUC-ROC). A total of 18,662 discharge episodes were analyzed, out of which 2528 (13.5%) were followed by outpatient readmissions. Overall, 38,059 models were developed. AUC-ROC, sensitivity, and specificity of the reduced final model were 0.653, 0.385, and 0.794, respectively. The most important variables were related to follow-up duration, being prescribed with disease-modifying anti-rheumatic drugs and corticosteroids, being diagnosed with chronic polyarthritis, occupation, and QoL. We have developed a predictive model for outpatient readmission in a rheumatology setting. Identification of patients with higher risk can optimize the allocation of healthcare resources.

A Different Approach for Digital Pathology: Lexicon-semantic Analysis of Histopathological Reports for the Assessment of their Quality.

An analysis of the costs related to the processes involved in a pathological analysis of a biopsy justifies the traditional view of digital pathology. However, this traditional conception has left aside another important aspect of this process, the writing of pathological reports. The efficiency and effectiveness of this subprocess has been raised in recent years as a challenge in the field of digital pathology. This work explores in this aspect offering a system of lexical-semantic analysis to determine the usefulness of pathological reports. It is a tool that assists the pathologist in the drafting of a useful report and establishes the bases for the management of the veracity of information in the automatic generation of pathological reports.