REAL-Time Smartphone Activity Classification Using Inertial Sensors-Recognition of Scrolling, Typing, and Watching Videos While Sitting or Walking.

By developing awareness of smartphone activities that the user is performing on their smartphone, such as scrolling feeds, typing and watching videos, we can develop application features that are beneficial to the users, such as personalization. It is currently not possible to access real-time smartphone activities directly, due to standard smartphone privileges and if internal movement sensors can detect them, there may be implications for access policies. Our research seeks to understand whether the sensor data from existing smartphone inertial measurement unit (IMU) sensors (triaxial accelerometers, gyroscopes and magnetometers) can be used to classify typical human smartphone activities. We designed and conducted a study with human participants which uses an Android app to collect motion data during scrolling, typing and watching videos, while walking or seated and the baseline of smartphone non-use, while sitting and walking. We then trained a machine learning (ML) model to perform real-time activity recognition of those eight states. We investigated various algorithms and parameters for the best accuracy. Our optimal solution achieved an accuracy of 78.6% with the Extremely Randomized Trees algorithm, data sampled at 50 Hz and 5-s windows. We conclude by discussing the viability of using IMU sensors to recognize common smartphone activities.

Exploring older peoples' attitudes and preferences around the use of their healthcare information.

AIMS: Routinely collected health data can provide rich information for research and epidemiological monitoring of different diseases, but using the data presents many challenges. This study aims to explore the attitudes and preferences of people aged 55 and over regarding the use of their de-identified health data, and their concerns and comfort in different scenarios. METHODS: An anonymous online survey was conducted with people aged 55 and over currently engaged with health services in a New Zealand health district during June-October 2022. The survey could be completed online or by telephone and was available in eight languages. RESULTS: Seventy-nine percent of respondents knew that their health information was currently being used in the ways described in the scenarios, and between 80-87% felt comfortable or very comfortable with their data being used as described in the scenarios. In contrast, 4% (n=9) felt "uncomfortable" or "very uncomfortable" across all of the scenarios. Participants expressed concerns about data accuracy, privacy and confidentiality, security, transparency of use, consent, feedback and the risk of data being sold to commercial companies. Some participants identified situations where permission should be required to link data, including being used by people other than health professionals, containing sensitive health issues, or being used for commercial purposes. CONCLUSION: This study finds general support from patients for the use of their routinely collected data for secondary purposes as long as its use will benefit the population from which the data are taken. It also highlights the necessity of including the perspectives of different cultures in the collection, storage, use and analysis of health information, particularly concerning Maori cultural considerations.

Identifying potential patients with diabetes-related dementia: a descriptive approach using routinely collected data.

AIMS: Diabetes-related dementia (DRD) is a new dementia subtype associated with type 2 diabetes mellitus, first described in 2013. This study investigated data from a local New Zealand memory service to identify patients that met the criteria for DRD. METHODS: Using routinely collected data from 2013-2021, we selected a sample of people with dementia, diabetes, and no CT evidence of Alzheimer's disease (AD), vascular dementia, or frontotemporal dementia. We compared their socio-demographic, clinical, and cognitive characteristics with a sample of patients with diabetes and Alzheimer's disease. RESULTS: Forty (16%) of 249 patients with diabetes and dementia had "normal" CT scans (DRD subgroup), and 38 (15%) had AD (AD subgroup). Compared to NZ Europeans, disproportionally more Maori and Pacific Islanders (70.2%) were in the DRD subgroup. In the Pacific subgroup (n=31), the DRD subgroup had higher memory subscores than the AD subgroup (p=0.047), and the Kaplan-Meier plot suggested poorer survival (p=0.13). Maori patients with diabetes and dementia were more likely to meet all four criteria for DRD. CONCLUSION: We have replicated the findings of the 2013 DRD research and have demonstrated a higher risk for the DRD subtype of dementia among the Maori and Pacific Islander patients in our sample.

Shilling Attacks Detection in Recommender Systems Based on Target Item Analysis.

Recommender systems are highly vulnerable to shilling attacks, both by individuals and groups. Attackers who introduce biased ratings in order to affect recommendations, have been shown to negatively affect collaborative filtering (CF) algorithms. Previous research focuses only on the differences between genuine profiles and attack profiles, ignoring the group characteristics in attack profiles. In this paper, we study the use of statistical metrics to detect rating patterns of attackers and group characteristics in attack profiles. Another question is that most existing detecting methods are model specific. Two metrics, Rating Deviation from Mean Agreement (RDMA) and Degree of Similarity with Top Neighbors (DegSim), are used for analyzing rating patterns between malicious profiles and genuine profiles in attack models. Building upon this, we also propose and evaluate a detection structure called RD-TIA for detecting shilling attacks in recommender systems using a statistical approach. In order to detect more complicated attack models, we propose a novel metric called DegSim' based on DegSim. The experimental results show that our detection model based on target item analysis is an effective approach for detecting shilling attacks.