With the wide deployment of the face recognition systems in applications from deduplication to mobile device unlocking, security against the face spoofing attacks requires increased attention; such ...attacks can be easily launched via printed photos, video replays, and 3D masks of a face. We address the problem of face spoof detection against the print (photo) and replay (photo or video) attacks based on the analysis of image distortion (e.g., surface reflection, moiré pattern, color distortion, and shape deformation) in spoof face images (or video frames). The application domain of interest is smartphone unlock, given that the growing number of smartphones have the face unlock and mobile payment capabilities. We build an unconstrained smartphone spoof attack database (MSU USSA) containing more than 1000 subjects. Both the print and replay attacks are captured using the front and rear cameras of a Nexus 5 smartphone. We analyze the image distortion of the print and replay attacks using different: 1) intensity channels (R, G, B, and grayscale); 2) image regions (entire image, detected face, and facial component between nose and chin); and 3) feature descriptors. We develop an efficient face spoof detection system on an Android smartphone. Experimental results on the public-domain Idiap Replay-Attack, CASIA FASD, and MSU-MFSD databases, and the MSU USSA database show that the proposed approach is effective in face spoof detection for both the cross-database and intra-database testing scenarios. User studies of our Android face spoof detection system involving 20 participants show that the proposed approach works very well in real application scenarios.
Smartphone apps are a promising tool for delivering accessible and appealing physical activity interventions. Given the large growth of research in this field, there are now enough studies using the ..."gold standard" of experimental design-the randomized controlled trial design-and employing objective measurements of physical activity, to support a meta-analysis of these scientifically rigorous studies.
This systematic review and meta-analysis aimed to determine the effectiveness of smartphone apps for increasing objectively measured physical activity in adults.
A total of 7 electronic databases (EMBASE, EmCare, MEDLINE, Scopus, Sport Discus, The Cochrane Library, and Web of Science) were searched from 2007 to January 2018. Following the Population, Intervention, Comparator, Outcome and Study Design format, studies were eligible if they were randomized controlled trials involving adults, used a smartphone app as the primary or sole component of the physical activity intervention, used a no- or minimal-intervention control condition, and measured objective physical activity either in the form of moderate-to-vigorous physical activity minutes or steps. Study quality was assessed using a 25-item tool based on the Consolidated Standards of Reporting Trials checklist. A meta-analysis of study effects was conducted using a random effects model approach. Sensitivity analyses were conducted to examine whether intervention effectiveness differed on the basis of intervention length, target behavior (physical activity alone vs physical activity in combination with other health behaviors), or target population (general adult population vs specific health populations).
Following removal of duplicates, a total of 6170 studies were identified from the original database searches. Of these, 9 studies, involving a total of 1740 participants, met eligibility criteria. Of these, 6 studies could be included in a meta-analysis of the effects of physical activity apps on steps per day. In comparison with the control conditions, smartphone apps produced a nonsignificant (P=.19) increase in participants' average steps per day, with a mean difference of 476.75 steps per day (95% CI -229.57 to 1183.07) between groups. Sensitivity analyses suggested that physical activity programs with a duration of less than 3 months were more effective than apps evaluated across more than 3 months (P=.01), and that physical activity apps that targeted physical activity in isolation were more effective than apps that targeted physical activity in combination with diet (P=.04). Physical activity app effectiveness did not appear to differ on the basis of target population.
This meta-analysis provides modest evidence supporting the effectiveness of smartphone apps to increase physical activity. To date, apps have been most effective in the short term (eg, up to 3 months). Future research is needed to understand the time course of intervention effects and to investigate strategies to sustain intervention effects over time.
Background: Objective methods to improve the measurement of selfreported dietary intake, in particular the timing of eating occasions (EO), are needed. The aim of this study is to describe the timing ...of EO using self-report (SR) with a smartphone app, actigraphic-based wrist motion (WM), and a continuous glucose monitor (CGM). Methods: Participants (n = 30; 58 ± 11y; 56.7% female; BMI: 33.8 ± 4.1 kg/m2) were enrolled in a behavioral weight loss intervention. Data were collected at baseline. All participants self-reported EO into a smartphone app wore an ActiGraph GT9X on the dominant wrist and CGM (Abbott Libre Pro) for up to 10 days. A validated, actigraphic-based classifier was used to detect EO. A simulation of the glucose-insulin model was used to detect EO timing using CGM data. We described EO timing for the 3 methods (SR, CGM, WM) in terms of first, midpoint, and last EO. We explored the overlap of identifying the timing of EO with applied tolerance periods of ±0, 5, 10, 30, 60, 120 min to all SR mealtimes in comparison to CGM and WM. Data are reported as clock times and median interquartile range. Results: The median first EO for SR, CGM and WM was 08:24 07:00-09:59, 06:55 04:23-10:03, and 10:27 08:24-12:54, respectively. The eating midpoint for SR, CGM and WM was 13:34 11:48-15:39, 14:06 11:54-16:19, 14:28 12:54-16:41, respectively. The median last EO for SR, CGM, WM was 20:20 16:50-21:42, 21:43 20:35-22:16, 20:09 16:38-21:54, respectively. Tolerance periods of ±0, 5,10 min resulted in <50% detection of SR EO by both WM and CGM. The overlap between SR and CGM was between 50%-80% of EO detected with tolerance periods of ±30, 60, 120 min. The over-lap between SR and WM was between 36%-60% EO detected with ±30, 60, 120 min tolerance periods. Conclusions: Determining the timing of EO may be improved with objective measures that include WM and a CGM.
A new generation of mobile sensing approaches offers significant advantages over traditional platforms in terms of test speed, control, low cost, ease-of-operation, and data management, and requires ...minimal equipment and user involvement. The marriage of novel sensing technologies with cellphones enables the development of powerful lab-on-smartphone platforms for many important applications including medical diagnosis, environmental monitoring, and food safety analysis. This paper reviews the recent advancements and developments in the field of smartphone-based food diagnostic technologies, with an emphasis on custom modules to enhance smartphone sensing capabilities. These devices typically comprise multiple components such as detectors, sample processors, disposable chips, batteries and software, which are integrated with a commercial smartphone. One of the most important aspects of developing these systems is the integration of these components onto a compact and lightweight platform that requires minimal power. To date, researchers have demonstrated several promising approaches employing various sensing techniques and device configurations. We aim to provide a systematic classification according to the detection strategy, providing a critical discussion of strengths and weaknesses. We have also extended the analysis to the food scanning devices that are increasingly populating the Internet of Things (IoT) market, demonstrating how this field is indeed promising, as the research outputs are quickly capitalized on new start-up companies.
Problematic smartphone use (PSU) has been increasing hastily in recent decades, and it has become inseparable during the COVID-19 pandemic, especially among the students who are at risk of ...problematic smartphone use. Therefore, the present study aimed to investigate the prevalence and associated factors of PSU during the COVID-19 pandemic among the Bangladeshi students.
A total of 601 Bangladeshi students were recruited through an online-based cross-sectional survey that was conducted between October 7 and November 2, 2020. The survey collected information related to socio-demographics, behavioral health, internet use behaviors, depression, anxiety, and PSU. Independent samples
-test and one-way ANOVA were performed to present the relationship between the studied variables and PSU. Multiple linear regression analysis was also used for investigating the explanatory power of the predictive models for PSU.
Surprisingly, about 86.9% of the students scored to be problematic smartphone users (≥21 out of a total 36 based on the Smartphone Application-Based Addiction Scale). In addition, medical students, engaging in a relationship, performing less physical activity, longer duration of internet use, some sorts of internet use purpose (eg, messaging, watching videos, using social media), depression, and anxiety were significantly associated with higher scores of PSU. After adjusting all the studied variables, the final model explained a 31.3% variance predicting PSU.
The present study is one of the first approaches to assess the prevalence of PSU among the Bangladeshi students during the COVID-19 pandemic, whereas the addiction level was superfluous (and this may be due to more online engagement related to the pandemic). Thus, the study recommended strategies or policies related to the students' risk-reducing and healthy use of smartphones.
Smartphones allow people to connect with others from almost anywhere at any time. However, there is growing concern that smartphones may actually sometimes detract, rather than complement, social ...interactions. The term “phubbing” represents the act of snubbing someone in a social setting by concentrating on one’s phone instead of talking to the person directly. The current study was designed to examine some of the psychological antecedents and consequences of phubbing behavior. We examined the contributing roles of Internet addiction, fear of missing out, self-control, and smartphone addiction, and how the frequency of phubbing behavior and of being phubbed may both lead to the perception that phubbing is normative. The results revealed that Internet addiction, fear of missing out, and self-control predicted smartphone addiction, which in turn predicted the extent to which people phub. This path also predicted the extent to which people feel that phubbing is normative, both via (a) the extent to which people are phubbed themselves, and (b) independently. Further, gender moderated the relationship between the extent to which people are phubbed and their perception that phubbing is normative. The present findings suggest that phubbing is an important factor in modern communication that warrants further investigation.
•Internet addiction, FoMOs, and self-control predict smartphone addiction.•Smartphone addiction predicts phubbing behavior and phubbee experiences.•Phubbing and phubbee experiences predict the perceived normativity of phubbing.•Gender moderates the relationship between phubbee experiences and perceived norms.
The article discusses the new approach of digital phenotyping, an approach to measuring behavior from smartphone sensors, keyboard interaction, and various features of voice and speech. Some of the ...benefits and advantages offered by digital phenotyping are highlighted.
Determining the current position in a forest is essential for many applications and is often carried out using smartphones. Modern smartphones now support various GNSS constellations and ...multi-frequency analyses, which are expected to provide more accurate positioning. This study compares the static autonomous GNSS positioning accuracy under forest conditions of four multi-frequency multi-constellation smartphones as well as six single-frequency smartphones and a geodetic receiver. Measurements were carried out at 15 different study sites under forest canopies, with 24 measurements lasting approximately 10 min each taken for the 11 GNSS receivers. The results indicate that, on average, multi-frequency smartphones can achieve a higher positioning accuracy. However, the accuracy varies greatly between smartphones, even between identical or quasi-identical tested smartphones. Therefore, no accuracy should be generalised depending on the number of usable frequencies or constellations, but each smartphone should be considered separately. The dual-frequency Xiaomi Mi 10 clearly stands out compared with the other smartphone with a DRMS of 4.56 m and has a 34% lower absolute error than the best single-frequency phone.
Although impressive progress has been made toward developing empirically‐supported psychological treatments, the reality remains that a significant proportion of people with mental health problems do ...not receive these treatments. Finding ways to reduce this treatment gap is crucial. Since app‐supported smartphone interventions are touted as a possible solution, access to up‐to‐date guidance around the evidence base and clinical utility of these interventions is needed. We conducted a meta‐analysis of 66 randomized controlled trials of app‐supported smartphone interventions for mental health problems. Smartphone interventions significantly outperformed control conditions in improving depressive (g=0.28, n=54) and generalized anxiety (g=0.30, n=39) symptoms, stress levels (g=0.35, n=27), quality of life (g=0.35, n=43), general psychiatric distress (g=0.40, n=12), social anxiety symptoms (g=0.58, n=6), and positive affect (g=0.44, n=6), with most effects being robust even after adjusting for various possible biasing factors (type of control condition, risk of bias rating). Smartphone interventions conferred no significant benefit over control conditions on panic symptoms (g=–0.05, n=3), post‐traumatic stress symptoms (g=0.18, n=4), and negative affect (g=–0.08, n=5). Studies that delivered a cognitive behavior therapy (CBT)‐based app and offered professional guidance and reminders to engage produced larger effects on multiple outcomes. Smartphone interventions did not differ significantly from active interventions (face‐to‐face, computerized treatment), although the number of studies was low (n≤13). The efficacy of app‐supported smartphone interventions for common mental health problems was thus confirmed. Although mental health apps are not intended to replace professional clinical services, the present findings highlight the potential of apps to serve as a cost‐effective, easily accessible, and low intensity intervention for those who cannot receive standard psychological treatment.
PDF
