SDAA: Secure Data Aggregation and Authentication Using Multiple Sinks in Cluster-Based Underwater Vehicular Wireless Sensor Network.

Security is one of the major concerns while designing robust protocols for underwater sensor networks (UWSNs). The underwater sensor node (USN) is an example of medium access control (MAC) that should control underwater UWSN, and underwater vehicles (UV) combined. Therefore, our proposed method, in this research, investigates UWSN combined with UV optimized as an underwater vehicular wireless network (UVWSN) that can completely detect malicious node attacks (MNA) from the network. Thus, MNA that engages the USN channel and launches MNA is resolved by our proposed protocol through SDAA (secure data aggregation and authentication) protocol deployed in UVWSN. SDAA protocol plays a significant role in secure data communication, as the cluster-based network design (CBND) network organization creates a concise, stable, and energy-efficient network. This paper introduces SDAA optimized network known as UVWSN. In this proposed SDAA protocol, the cluster head (CH) is authenticated through the gateway (GW) and the base station (BS) to guarantee that a legitimate USN oversees all clusters deployed in the UVWSN are securely established for providing trustworthiness/privacy. Furthermore, the communicated data in the UVWSN network guarantee that data transmission is secure due to the optimized SDAA models in the network. Thus, the USNs deployed in the UVWSN are securely confirmed to maintain secure data communication in CBND for energy efficiency. The proposed method is implemented and validated on the UVWSN for measuring reliability, delay, and energy efficiency in the network. The proposed method is utilized for monitoring scenarios for inspecting vehicles or ship structures in the ocean. Based on the testing results, the proposed SDAA protocol methods improve energy efficiency and reduce network delay compared to other standard secure MAC methods.

Application of Machine Learning Algorithms to Predict Uncontrolled Diabetes Using the All of Us Research Program Data.

There is a paucity of predictive models for uncontrolled diabetes mellitus. The present study applied different machine learning algorithms on multiple patient characteristics to predict uncontrolled diabetes. Patients with diabetes above the age of 18 from the All of Us Research Program were included. Random forest, extreme gradient boost, logistic regression, and weighted ensemble model algorithms were employed. Patients who had a record of uncontrolled diabetes based on the international classification of diseases code were identified as cases. A set of features including basic demographic, biomarkers and hematological indices were included in the model. The random forest model demonstrated high performance in predicting uncontrolled diabetes, yielding an accuracy of 0.80 (95% CI: 0.79-0.81) as compared to the extreme gradient boost 0.74 (95% CI: 0.73-0.75), the logistic regression 0.64 (95% CI: 0.63-0.65) and the weighted ensemble model 0.77 (95% CI: 0.76-0.79). The maximum area under the receiver characteristics curve value was 0.77 (random forest model), while the minimum value was 0.7 (logistic regression model). Potassium levels, body weight, aspartate aminotransferase, height, and heart rate were important predictors of uncontrolled diabetes. The random forest model demonstrated a high performance in predicting uncontrolled diabetes. Serum electrolytes and physical measurements were important features in predicting uncontrolled diabetes. Machine learning techniques may be used to predict uncontrolled diabetes by incorporating these clinical characteristics.

Enhancing attention and memory of individuals at clinical high risk for psychosis with mHealth technology.

BACKGROUND: Cognitive impairment has adverse impact on the social and role functions of those at clinical high risk for psychosis and it has become an important target for intervention. Mobile health applications are user-friendly, real-time, personalized and portable in administering cognitive training and have promising application prospects in the field of mental health. METHODS: Eighty CHR subjects were randomized into an intervention group and a control group. CHR subjects of the intervention group performed attention and memory training via a Specific Memory Attention Resource and Training (SMART) application in their smart phones for 10 min per day, five days per week for three months. Both groups were followed up for three months. At baseline and follow-up phases, cognitive function was measured using the MATRICS Consensus Cognitive Battery (MCCB). In the follow-up, the intervention group completed the Mobile Application Rating Scale (MARS) to provide feedback to improve SMART. RESULTS: There is a significant group by time interaction effect in the Attention/Vigilance domain, which is significantly better in the intervention group than in the control group at 3- month follow-up. The improvement in Attention/Vigilance in the intervention group is significantly related to the amount of cognitive training time. Global Assessment of Function (GAF) reduction rate at baseline could predict the improvement of Attention/Vigilance. MARS results indicate that CHR subjects were receptive of SMART. CONCLUSION: Mobile technology can be applied to improve cognitive function of CHR individuals, especially in the Attention/Vigilance domain.

Mobile health applications for mental illnesses: An Asian context.

Advances in digital technologies have created unprecedented opportunities to assess and improve health behavior and health outcomes. Evidence indicates that a majority of the world's population, including traditionally underserved populations and low- and middle-income countries, has access to mobile technologies (phones, tablets, mobile devices). Given the widespread access to mobile technology worldwide, health behavior-change tools delivered on mobile platforms enable broader reach and scalability of evidence-based assessment and interventions, especially for addressing the growing burden of mental health disorders globally. The purpose of this article was to present a qualitative review of mobile mental health applications in an Asian context. We searched on-line databases and included 22 articles in this review. We have identified mobile health applications that address eight categories of mental illnesses. These applications were developed in only six countries and regions in Asia. Future studies from more diverse countries for diverse cultures should be conducted to examine the advantages and disadvantages of mobile health technology.

Mobile health in China: current status and future development.

Mobile health applications offer unique opportunities for monitoring patient progress, providing education materials to patients and family members, receiving personalized prompts and support, collecting ecologically valid data, and using self-management interventions when and where they are needed. Mobile health application services to mental illness have evidenced success in Western countries. However, they are still in the initial stage of development in China. The purpose of this paper is to identify needs for mobile health in China, present major mobile health products and technology in China, introduce mobile and digital psychiatric services, and discuss ethical issues and challenges in mobile health development in a country with the largest population in the world.