Real-world Usage Research Articles

Feasibility Evaluation of Highwall Mining in Open-Pit Coal Mine Based on Method of Integrated Analytic Hierarchy Process–Fuzzy Comprehensive Evaluation–Variable Weight Theory

Highwall mining is a method that involves using a continuous highwall miner system (CHM) to extract coal from the remaining coal seams, which has proven to be an effective and safe method for extracting coal after open-pit mining. However, application cases globally have shown that the feasibility of highwall mining in open-pit coal mines is subject to geological conditions, mining techniques, and other factors. If application conditions are not suitable, equipment may be trapped under collapsed coal–rock masses and unable to be retrieved, resulting in severe safety issues for slope stability. To meet the real-world demand for extracting the remaining coal in open-pit coal mines in China, it is urgent to conduct a feasibility evaluation of highwall mining in these areas. This paper establishes a mathematical evaluation framework for assessing the feasibility of highwall mining by summarizing a large number of engineering application cases globally and analyzing various technical characteristics such as geological deposit conditions, mining techniques, and technical equipment. The analytic hierarchy process (AHP), fuzzy comprehensive evaluation (FCE) and variable weight theory (VWT) are utilized in conjunction to form this framework, which includes four secondary indicators: geological deposit factors, mining technique factors, safety impact factors, and economic evaluation factors, and 20 tertiary sub-indicators, along with their corresponding characteristic values. The feasibility sub-set is divided into four categories: infeasible, basically feasible, relatively feasible, and highly feasible, and the values of the sub-indicators strictly follow and represent these four levels of feasibility. Weight vectors for the sub-indicators are obtained through a judgment matrix established within the mathematical evaluation framework. The fuzzy relationship matrix of the sub-indicators is constructed using fuzzy mathematical membership functions, and the final feasibility evaluation is determined through two-level comprehensive evaluation. The accuracy of the model is verified using the characteristic parameters of open-pit coal mines under two different conditions (JZT coal mine in Inner Mongolia, China, and GC coal mine in Australia). The results demonstrate that the maximum evaluation membership degree for the JZT mine is 0.7113, belonging to the “highly feasible” level, while the GC mine is 0.3304, belonging to the “basically feasible” level, which aligns well with real-world usage, proving that the evaluation model can effectively reveal the performance and membership degree of each indicator in different application cases. By quantitatively characterizing the feasibility level of highwall mining technology under different application conditions, this evaluation model can provide scientific guidance for coal mining enterprises to introduce CHM for highwall mining operation in open-pit coal mines.

Real-World User Demographics of Three Web-Based Digital Mental Health Interventions Provided by the US Department of Veterans Affairs: Observational Study Using Web Analytics Data.

Unguided digital mental health interventions (UDMHIs) have the potential to provide low-cost and effective mental health care at scale. Controlled trials have demonstrated the efficacy of UDMHIs to address mental health symptoms and conditions. However, few previous publications have described the demographics of real-world users of UDMHIs that are freely available to the public. The US Department of Veterans Affairs has created and hosts several UDMHIs on its Veteran Training Portal website. These web-based, free-to-use, and publicly available UDMHIs include Path to Better Sleep, Anger and Irritability Management Skills, and Moving Forward, which focus on insomnia, problematic anger, and depression symptoms, respectively. This study aimed to examine the user demographics of these 3 UDMHIs in the year 2021. In addition, it aimed to compare the age and gender distribution of the users of those 3 UDMHIs with one another and with the age and gender distribution of the total US veteran population. Google Analytics was used to collect user data for each of the 3 UDMHIs. The age and gender distribution of the users of each UDMHI was compared with that of the other UDMHIs as well as with that of the overall US veteran population using chi-square tests. Information on the total number of users, the country they were in, and the devices they used to access the UDMHIs was also collected and reported. In 2021, the 3 UDMHIs together recorded 29,306 unique users. The estimated age range and gender were available for 24.12% (7068/29,306) of those users. Each UDMHI's age and gender distribution significantly differed from that of the other UDMHIs and from that of the overall US veteran population (P<.001 on all chi-square tests). Women and younger age groups were overrepresented among UDMHI users compared with the overall US veteran population. The majority of devices used to access the UDMHIs were desktop or laptop devices, although a substantial proportion of devices used were mobile devices (10,199/29,752, 34.28%). Most users (27,789/29,748, 93.41%) were located in the United States, with users from Canada, the United Kingdom, and Australia accounting for another 2.61% (775/29,748) of total users. Our use of Google Analytics data provided useful information about the users of 3 free and publicly available UDMHIs provided by the US Department of Veterans Affairs. Although our findings should be considered in light of the limitations of autonomously collected web analytics data, they still offer useful information for health care policy makers, administrators, and UDMHI developers.

MiniMed 780G™ advanced hybrid closed-loop system performance in Egyptian patients with type 1 diabetes across different age groups: evidence from real-world users

BackgroundAdvanced hybrid closed loop (AHCL) system provides both automated basal rate and correction boluses to keep glycemic values in a target range.ObjectivesTo evaluate the real-world performance of the MiniMed™ 780G system among different age groups of Egyptian patients with type 1diabetes.MethodsOne-hundred seven AHCL system users aged from 3 to 71 years were enrolled. Data uploaded by patients were aggregated and analyzed. The mean glucose management indicator (GMI), percentage of time spent within glycemic ranges (TIR), time below range (TBR) and time above range (TAR) were determined.ResultsSix months after initiating Auto Mode, patients spent a mean of 85.31 ± 22.04% of the time in Auto Mode (SmartGuard) and achieved a mean GMI of 6.95 ± 0.58% compared with 7.9 ± 2.1% before AHCL initiation (p < 0.001). TIR 70–180 mg/dL was increased post-AHCL initiation from 63.48 ± 10.14% to 81.54 ± 8.43% (p < 0.001) while TAR 180–250 mg/dL, TAR > 250 mg/dL, TBR < 70 mg/dL and TBR < 54 mg/dL were significantly decreased (p < 0.001). After initiating AHCL, TIR was greater in children and adults compared with adolescents (82.29 ± 7.22% and 83.86 ± 9.24% versus 78.4 ± 7.34%, respectively; p < 0.05). The total daily dose of insulin was increased in all age groups primarily due to increased system-initiated insulin delivery including auto correction boluses and basal insulin.ConclusionsMiniMed™ 780G system users across different age groups achieved international consensus-recommended glycemic control with no serious adverse effects even in challenging age group as children and adolescents.

Pilot Investigation of Blood Pressure Control Using a Mobile App (Cardi.Health): Retrospective Chart Review Study.

The high prevalence of hypertension necessitates effective, scalable interventions for blood pressure (BP) control. Self-monitoring has shown improved adherence to medication and better BP management. Mobile apps offer a promising approach with their increasing popularity and potential for large-scale implementation. Studies have demonstrated associations between mobile app interventions and lowered BP, yet real-world data on app effectiveness and engagement remain limited. In this study, we analyzed real-world user data from the Cardi.Health mobile app, which is aimed at helping its users monitor and control their BP. Our goal was to find out whether there is an association between the use of the mobile app and a decrease in BP. Additionally, the study explored how engagement with the app may influence this outcome. This was a retrospective chart review study. The initial study population comprised 4407 Cardi.Health users who began using the app between January 2022 and April 2022. After applying inclusion criteria, the final study cohort comprised 339 users with elevated BP at the baseline. The sample consisted of 108 (31.9%) men and 231 (68.1%) women (P=.04). This retrospective chart review study obtained permission from the Biomedical Research Alliance of New York Institutional Review Board (June 2022, registration ID 22-08-503-939). The study's main findings were that there is a possible relationship between use of the Cardi.Health mobile app and a decrease in systolic BP. Additionally, there was a significant association between active use of the app and systolic BP decrease (χ21=5.311; P=.02). Finally, active users had an almost 2 times greater chance of reducing systolic BP by 5 mm Hg or more over 4 weeks (odds ratio 1.932, 95% CI 1.074-3.528; P=.03). This study shows a possible relationship between Cardi.Health mobile app use and decreased BP. Additionally, engagement with the app may be related to better results-active use was associated with an almost 2-fold increase in the odds of reducing BP by 5 or more mm Hg.

THE PROCESS OF LOWER LIMB PROSTHESIS CREATION USING CAD DESIGN AND FINITE ELEMENT ANALYSIS

Research objective: The aim of this article is to illustrate how prostheses are made, the significance of strength analyses, and why they are produced in accordance with ISO standards. Methodology: Research methods employed include literature review and analysis of an original research. Main conclusions: CAD design and strength analyses are crucial aspects of creating prostheses as medical devices. Modern technology allows for tailoring the design to a specific case and the patient's needs, considering anatomy and specific functional requirements. Numerical analyses make it possible to identify the most vulnerable elements to potential damage and optimize these areas through geometry modifications, among other factors. Additionally, it is possible to simulate critical conditions in which the designed element may find itself. An essential part of the research is conducting strength analyses according to ISO standards, which precisely specify how they should be carried out and under what load. Successfully passing these stages ensures legal safety for the designer and the possibility of implementing the designed solutions throughout the European Union. Application of the study: Strength analyses allow for predicting the behavior of prostheses under load and real-world usage conditions, which is crucial for patient safety. The use of CAD design enables customization of medical devices to individual patient needs. Originality/Novelty of the study: The presented results provide insights into the prostheses design process. By outlining the creation process and conducting numerical analyses, the complexity of this issue becomes apparent. Designing prostheses requires collaboration among several scientific disciplines, including biomechanics, engineering, medicine, materials science, and computer science.

Security and Trust in Online Booking Systems: A Comparative Analysis Of Tour and Travel Websites

The Tour and Travel sector have undergone a transformative shift with the proliferation of online reservation platforms, redefining how individuals plan and secure their travel arrangements. This study critically examines the pivotal aspects of security and trust within the digital landscape of tour and travel websites, aiming to provide a comprehensive comparative analysis.In our increasingly digitised age, the security of sensitive financial and personal data is of utmost importance. Our investigation begins with a thorough analysis of the security precautions taken by a wide-ranging sample of tour and travel websites. The effectiveness of user authentication, data protection protections, and conformance with industry standards are some of the key areas under evaluation. This analysis reveals considerable discrepancies in how these security protocols are applied, potentially exposing weaknesses in particular systems. The foundation of the internet booking procedure is trust, as well. This study evaluates a variety of elements, such as user reviews, website design, pricing transparency, and timeliness of customer support, when evaluating trust-building strategies. The study draws attention to the varying approaches taken by various websites to build trust, which has a big impact on how confident customers are in the booking process. This research explores the practical repercussions of security breaches and trust deficiencies, combining real-world case studies and user input, in addition to security and trust evaluation. These results highlight how these elements have a significant influence on consumer behaviour and brand reputation. This comparison analysis highlights the critical requirement for uniform and strong security safeguards across all online booking systems, to sum up. At the same time, it highlights how crucial it is to create trust-enhancing strategies like open pricing and attentive customer care. This research is a useful resource for industry stakeholders, regulatory agencies, and consumers in an era where digital travel planning and booking predominates, enabling informed decision-making and supporting a safe and reliable online booking environment. Additionally, a key element affecting customer choices during the online booking process is trust. This study considers factors including user reviews, website design, pricing transparency, and customer service responsiveness to gauge trustworthiness. It becomes clear that different websites employ quite different trust-building techniques, which has an effect on users' faith in the reservation process.

The impact of therapeutic persuasiveness on engagement and outcomes in unguided interventions: A randomized pilot trial of a digital parent training program for child behavior problems

Understanding how to design engaging unguided digital health interventions is key in our ability to utilize digital tools to improve access to care. Therapeutic persuasiveness (TP) is a design concept that relates to how the digital intervention features as a whole should be designed to encourage users to make positive changes in their lives, while reducing the experienced effort required from them to engage in these activities. In our previous work, we examined the user traffic of publicly available programs, finding programs' TP quality to be a reliable, robust, and stable predictor of real-world usage; however, these findings have not been subject to experimental manipulation in a controlled trial. The current study examined the impact of TP quality in digital parent training programs (DPTs) aimed at treating child's behavior problems. We conducted a pilot randomized controlled trial comparing two interventions that utilize the same evidence-based content of established DPTs, but that differ in terms of the quality of TP (standard: DPT-STD; enhanced: DPT-TP). Altogether, parents from 88 families who have a child with behavior problems were enrolled in the study. Compared to DPT-STD (n = 43), participants allocated to DPT-TP (n = 45) used the program significantly more (ps < 0.001; Cohen's ds = 0.91–2.22). In terms of program completion, 68.9 % of DPT-TP participants completed it compared to 27.9 % of DPT-STD participants. Significant differences between the interventions were also found in reported improvements in child behavior problems favoring DPT-TP (ps < 0.05; Cohen's ds = 0.43–0.54). The results point to the importance of adequate product design and the utilization of conceptual frameworks in order to improve user engagement challenges.

Capsule endoscopy with artificial intelligence-assisted technology: Real-world usage of a validated AI model for capsule image review.

Background and study aims Capsule endoscopy is a time-consuming procedure with a significance error rate. Artificial intelligence (AI) can potentially reduce reading time significantly by reducing the number of images that need human review. An OMOM Artificial Intelligence-enabled small bowel capsule has been recently trained and validated for small bowel capsule endoscopy video review. This study aimed to assess its performance in a real-world setting in comparison with standard reading methods. Patients and methods In this single-center retrospective study, 40 patient studies performed using the OMOM capsule were analyzed first with standard reading methods and later using AI-assisted reading. Reading time, pathology identified, intestinal landmark identification and bowel preparation assessment (Brotz Score) were compared. Results Overall diagnosis correlated 100% between the two reading methods. In a per-lesion analysis, 1293 images of significant lesions were identified combining standard and AI-assisted reading methods. AI-assisted reading captured 1268 (98.1%, 95% CI 97.15-98.7) of these findings while standard reading mode captured 1114 (86.2%, 95% confidence interval 84.2-87.9), P < 0.001. Mean reading time went from 29.7 minutes with standard reading to 2.3 minutes with AI-assisted reading ( P < 0.001), for an average time saving of 27.4 minutes per study. Time of first cecal image showed a wide discrepancy between AI and standard reading of 99.2 minutes (r = 0.085, P = 0.68). Bowel cleansing evaluation agreed in 97.4% (r = 0.805 P < 0.001). Conclusions AI-assisted reading has shown significant time savings without reducing sensitivity in this study. Limitations remain in the evaluation of other indicators.

Robust Location Prediction over Sparse Spatiotemporal Trajectory Data: Flashback to the Right Moment!

As a fundamental problem in human mobility modeling, location prediction forecasts a user’s next location based on historical user mobility trajectories. Recurrent neural networks (RNNs) have been widely used to capture sequential patterns of user visited locations for solving location prediction problems. Due to the sparse nature of real-world user mobility trajectories, existing techniques strive to improve RNNs by incorporating spatiotemporal contexts into the recurrent hidden state passing process of RNNs using context-parameterized transition matrices or gates. However, such a scheme mismatches universal spatiotemporal mobility laws and thus cannot fully benefit from rich spatiotemporal contexts encoded in user mobility trajectories. Against this background, we propose Flashback++, a general RNN architecture designed for modeling sparse user mobility trajectories. It not only leverages rich spatiotemporal contexts to search past hidden states with high predictive power but also learns to optimally combine them via a hidden state re-weighting mechanism, which significantly improves the robustness of the models against different settings and datasets. Our extensive evaluation compares Flashback++ against a sizable collection of state-of-the-art techniques on two real-world location-based social networks datasets and one on-campus mobility dataset. Results show that Flashback++ not only consistently and significantly outperforms all baseline techniques by 20.56% to 44.36% but also achieves better robustness of location prediction performance against different model settings (different RNN architectures and numbers of hidden states to flash back), different levels of trajectory sparsity, and different train-testing splitting ratios than baselines, yielding an improvement of 31.05% to 94.60%.

FewShotBP

Deep learning-based methods demonstrate promising results in continuous non-invasive blood pressure measurement, whereas those models trained on large public datasets suffer from severe performance degradation in predicting from real-world user data collected in home settings. Transfer learning has been recently introduced to personalize the pre-trained model with unseen users' data to solve the problem. However, the existing methods based on network fine-tuning for model personalization require a large amount of labeled data, lacking practicality due to labeling using a cuff-based blood pressure monitor is extremely tedious and laborious for home users. In this paper, we propose a novel few-shot transfer learning approach named FewShotBP, which addresses the above-mentioned challenges by introducing a personalization adapter at the personalization stage (i.e., the transfer learning stage), and a multi-modal spectro-temporal neural network at the pre-train stage, to bridge the gap between data-hungry models and limited labeled data in realistic scenarios. To evaluate the approach's significance, we conducted experiments using both a publicly available dataset and a real-world user experiment. The results demonstrated that the proposed approach achieves similar accuracy of blood pressure prediction with 10× less data for personalization compared with the state-of-the-art method in the public dataset and achieves a mean absolute error of 6.68 mmHg (systolic blood pressure) and 3.91 mmHg (diastolic blood pressure) with only 10 personal data samples in the real-world user experiment.

Exploring YouTube's Recommendation System in the Context of COVID-19 Vaccines: Computational and Comparative Analysis of Video Trajectories.

Throughout the COVID-19 pandemic, there has been a concern that social media may contribute to vaccine hesitancy due to the wide availability of antivaccine content on social media platforms. YouTube has stated its commitment to removing content that contains misinformation on vaccination. Nevertheless, such claims are difficult to audit. There is a need for more empirical research to evaluate the actual prevalence of antivaccine sentiment on the internet. This study examines recommendations made by YouTube's algorithms in order to investigate whether the platform may facilitate the spread of antivaccine sentiment on the internet. We assess the prevalence of antivaccine sentiment in recommended videos and evaluate how real-world users' experiences are different from the personalized recommendations obtained by using synthetic data collection methods, which are often used to study YouTube's recommendation systems. We trace trajectories from a credible seed video posted by the World Health Organization to antivaccine videos, following only video links suggested by YouTube's recommendation system. First, we gamify the process by asking real-world participants to intentionally find an antivaccine video with as few clicks as possible. Having collected crowdsourced trajectory data from respondents from (1) the World Health Organization and United Nations system (nWHO/UN=33) and (2) Amazon Mechanical Turk (nAMT=80), we next compare the recommendations seen by these users to recommended videos that are obtained from (3) the YouTube application programming interface's RelatedToVideoID parameter (nRTV=40) and (4) from clean browsers without any identifying cookies (nCB=40), which serve as reference points. We develop machine learning methods to classify antivaccine content at scale, enabling us to automatically evaluate 27,074 video recommendations made by YouTube. We found no evidence that YouTube promotes antivaccine content; the average share of antivaccine videos remained well below 6% at all steps in users' recommendation trajectories. However, the watch histories of users significantly affect video recommendations, suggesting that data from the application programming interface or from a clean browser do not offer an accurate picture of the recommendations that real users are seeing. Real users saw slightly more provaccine content as they advanced through their recommendation trajectories, whereas synthetic users were drawn toward irrelevant recommendations as they advanced. Rather than antivaccine content, videos recommended by YouTube are likely to contain health-related content that is not specifically related to vaccination. These videos are usually longer and contain more popular content. Our findings suggest that the common perception that YouTube's recommendation system acts as a "rabbit hole" may be inaccurate and that YouTube may instead be following a "blockbuster" strategy that attempts to engage users by promoting other content that has been reliably successful across the platform.

Integrative Korean Medicine Treatment for Obesity and Overweight in Children and Adolescents: A Multicenter Retrospective Chart Review Study.

Integrative Korean medicine treatment (IKM), including herbal medicine (HM) and acupuncture, has been widely used for obesity and overweight in children and adolescents in South Korea. We investigated the real-world usage status and the potential effect of the IKM for obesity and overweight in children and adolescents. Multicenter medical charts were retrospectively reviewed of obese and overweight children and adolescents who visited Korean medicine institutions with the goal of weight control for the first time and received IKM, to analyze the usage status and effect of IKM. We defined IKM responders as those with an improved obesity grade on the body mass index (BMI) percentile and analyzed their characteristics. Medical charts of 209 patients (183 obese and 26 overweight) with a mean age of 11.45 years were examined. Patients visited the institution a mean of 5.95 times, and HM alone and HM plus acupuncture were frequently used IKM. HM was prescribed to 205 patients, 167 of whom received an HM prescription containing Ephedrae Herba. An HM of the decoction type was prescribed to 189 patients, and the average treatment duration was 76.54 days. After IKM, the percentile and z-score of BMI and weight significantly declined and height percentile and z-score were significantly enhanced, without serious adverse events. In the IKM responders, age, and the proportion of girls and overweight were significantly higher, and the percentile and z-score of height, weight, and BMI were significantly lower. This is the first study to examine the real-world usage of IKM for obesity and overweight in children and adolescents. A significant improvement in obesity-related outcome measures after IKM, illustrated the potential effect of IKM.

Flexible Resource Allocation for Relational Database-as-a-Service

Oversubscription is an essential cost management strategy for cloud database providers, and its importance is magnified by the emerging paradigm of serverless databases. In contrast to general purpose techniques used for oversubscription in hypervisors, operating systems and cluster managers, we develop techniques that leverage our understanding of how DBMSs use resources and how resource allocations impact database performance. Our techniques are designed to flexibly redistribute resources across database tenants at the node and cluster levels with low overhead. We have implemented our techniques in a commercial cloud database service: Azure SQL Database. Experiments using microbenchmarks, industry-standard benchmarks and real-world resource usage traces show that using our approach, it is possible to tightly control the impact on database performance even with a relatively high degree of oversubscription.

Toward Teachable Autotelic Agents

Autonomous discovery and direct instruction are two distinct sources of learning in children but education sciences demonstrate that mixed approaches such as assisted discovery or guided play result in improved skill acquisition. In the field of Artificial Intelligence, these extremes respectively map to autonomous agents learning from their own signals and interactive learning agents fully taught by their teachers. In between should stand teachable autotelic agents (TAA): agents that learn from both internal and teaching signals to benefit from the higher efficiency of assisted discovery. Designing such agents will enable real-world non-expert users to orient the learning trajectories of agents towards their expectations. More fundamentally, this may also be a key step to build agents with human-level intelligence. This paper presents a roadmap towards the design of teachable autonomous agents. Building on developmental psychology and education sciences, we start by identifying key features enabling assisted discovery processes in child-tutor interactions. This leads to the production of a checklist of features that future TAA will need to demonstrate. The checklist allows us to precisely pinpoint the various limitations of current reinforcement learning agents and to identify the promising first steps towards TAA. It also shows the way forward by highlighting key research directions towards the design or autonomous agents that can be taught by ordinary people via natural pedagogy.

Exploring the Application of Design Thinking Methodology in Cellular Communications Network Planning and Deployment

Cellular network planning and deployment represent a set of activities that operators have been performing since the advent of mobile wireless communication systems. Decisions along this route traditionally have been based on engineering or commercial criteria, focusing on providing the best service to users. Although operator companies gather information regarding perceived quality of service among their subscribers, mainly using surveys, engineers work with numerical data more than with people’s interests, feelings, perceptions, or hopes. In other sectors, Design Thinking has arisen as a methodology that allows designers to involve real-world users in implementing new products or services. Thus, we are introducing this methodology for cellular networking, exploring its application in a process that could be designed in a more human-centered way. With this aim, we analyzed the different steps that could be included in the network planning and deployment. From this analysis, we detected which actions have chances to be explored in a human-centered view and thus, can be improved with some Design Thinking tips. Finally, we developed an experience of limited potential, comparing the insights obtained by an empathic interview to those given by traditional surveys, to show what Design Thinking could provide.

Investigating Real-World Benztropine Usage Patterns in Movement Disorders: Claims Analysis and Health Care Provider Survey Results.

Investigating Real-World Benztropine Usage Patterns in Movement Disorders: Claims Analysis and Health Care Provider Survey Results.

A Comprehensive Review of Key Technologies for Enhancing the Reliability of Lithium-Ion Power Batteries

Fossil fuel usage has a great impact on the environment and global climate. Promoting new energy vehicles (NEVs) is essential for green and low-carbon transportation and supporting sustainable development. Lithium-ion power batteries (LIPBs) are crucial energy-storage components in NEVs, directly influencing their performance and safety. Therefore, exploring LIPB reliability technologies has become a vital research area. This paper aims to comprehensively summarize the progress in LIPB reliability research. First, we analyze existing reliability studies on LIPB components and common estimation methods. Second, we review the state-estimation methods used for accurate battery monitoring. Third, we summarize the commonly used optimization methods in fault diagnosis and lifetime prediction. Fourth, we conduct a bibliometric analysis. Finally, we identify potential challenges for future LIPB research. Through our literature review, we find that: (1) model-based and data-driven approaches are currently more commonly used in state-estimation methods; (2) neural networks and deep learning are the most prevalent methods in fault diagnosis and lifetime prediction; (3) bibliometric analysis indicates a high interest in LIPB reliability technology in China compared to other countries; (4) this research needs further development in overall system reliability, research on real-world usage scenarios, and advanced simulation and modeling techniques.

SonarGuard: Ultrasonic Face Liveness Detection on Mobile Devices

Liveness detection has been widely applied in face authentication systems to combat malicious attacks. However, existing methods purely depending on visual frames become vulnerable once visual perception is not reliable. The emerging face spoof and forge techniques urge the systems to exploit the defensive potential of non-visual modalities. To tackle this challenge, we introduce SonarGuard, a system combining ultrasonic and visual information to achieve robust liveness detection on mobile devices. More specifically, SonarGuard simultaneously extracts micro-doppler signatures from ultrasound reflections and motion trajectories from video frames both corresponding to the user’s lip movement. To further confirm the collected ultrasonic and visual information is not derived from malicious audio/video attacks, we consolidate the system via introducing a cross-modal matching mechanism, which demands the inherent consistency between these two modalities. Extensive experiments on a new dataset collected with existing mobile devices demonstrate that the proposed system could achieve average classification error rate of 0.91% under presentation attacks. This result indicates that SonarGuard can boost the security of face authenfication systems in real world usage without additional hardware modification.

High ablation-resistant silicone rubber composites via nanoscale phenolic resin dispersion

High ablation-resistant silicone rubber composites exhibit significant potential for solid rocket engine ablation coating applications. However, the low char yield of silicone rubber restricts its real-world usage. Herein, silicone rubber with nanoscale dispersed Novolac-type phenolic resin particles (novolac-silicone rubber, NSR) is synthesized. The introduction of dynamic urethane bonds is crucial for achieving nanoscale dispersion of the phenolic resin, as it leads to both improved mechanical strength and enhanced char yield. In addition, the NSR-based composite materials demonstrate linear and mass ablation rates of 0.1440 mm/s and 0.0466 g/s, respectively, representing reductions of 44.19 % and 17.81 % compared with their conventional silicone rubber counterparts. Moreover, unlike the traditional physical blending approach, the nanoscale dispersion in this work is achieved by introducing a dihydroxypropyl-terminated silicone oil-novolac phenolic resin block copolymer to the silicone rubber matrix. The enhanced structural compatibility is proven to be pivotal for the improved performance of NSR. This work provides new routes for the synergistic improvement of the ablation resistance and mechanical properties of silicone rubber composites.

You Are How You Use Apps: User Profiling Based on Spatiotemporal App Usage Behavior

Mobile apps have become an indispensable part of people’s daily lives. Users determine what apps to use and when and where to use them based on their tastes, interests, and personal demands, depending on their personality traits. This article aims to infer user profiles from their spatiotemporal mobile app usage behavior. Specifically, we first transform mobile app usage records into a heterogeneous graph. On the graph, nodes represent users, apps, locations, and time slots. Edges describe the co-occurrence of entities in usage records. We then develop a multi-relational heterogeneous graph attention network (MRel-HGAN), an end-to-end system for user profiling. MRel-HGAN first adopts a neighbor sampling strategy based on bootstrapping to sample heavily connected neighbors of a fixed size for each node. Next, we design a relational graph convolutional operation and a multi-relational attention operation. Through such modules, MRel-HGAN can generate node embedding by sufficiently leveraging the rich semantic information of the multi-relational structure in the mobile app usage graph. Experimental results on real-world mobile app usage datasets show the effectiveness and superiority of our MRel-HGAN in the user profiling task for attributes of gender and age.