What and How long: Prediction of Mobile App Engagement

User engagement is crucial to the long-term success of a mobile app. Several metrics, such as dwell time, have been used for measuring user engagement. However, how to effectively predict user engagement in the context of mobile apps is still an open research question. For example, do the mobile usage contexts (e.g., time of day) in which users access mobile apps impact their dwell time? Answers to such questions could help mobile operating system and publishers to optimize advertising and service placement. In this article, we first conduct an empirical study for assessing how user characteristics, temporal features, and the short/long-term contexts contribute to gains in predicting users’ app dwell time on the population level. The comprehensive analysis is conducted on large app usage logs collected through a mobile advertising company. The dataset covers more than 12K anonymous users and 1.3 million log events. Based on the analysis, we further investigate a novel mobile app engagement prediction problem—can we predict simultaneously what app the user will use next and how long he/she will stay on that app? We propose several strategies for this joint prediction problem and demonstrate that our model can improve the performance significantly when compared with the state-of-the-art baselines. Our work can help mobile system developers in designing a better and more engagement-aware mobile app user experience.

Review on IoT Mobile App based on Rural Development in Terms of Agriculture

As India is still a developing country, it has a lot of rural areas wherein the living conditions and standards are below world standards and may even be on the underdeveloped scale of living standards. In order to achieve development in these regions the first and foremost step to initiate is to improve the agriculture standards and methodologies and bring in new technology to improve the methods used in agriculture which is the major source of income to these people. This project is a four staged project which intends on improving the agriculture standards of India. The first stage of the project is an automated humidity and moisture control for the soil, this will help the farmers in automating certain aspects and hence eliminate certain human errors and improve yield. The second stage of the project is an agriculture auction portal wherein the farmers can directly auction their products to the wholesaler without the need of a middle man/broker. The third stage of the project is an android app which conducts various surveys and suggests a new farmer the type of farming/seeds to be planted / soil information and other such relevant data in respect to agriculture which would help increase the yield for a new farmer. The last part of the project is a seed cum financial bank which helps the farmers by providing financial as well as seed aid in times of financial crisis.

EHealth and Its Role in Supporting Audiological Rehabilitation: Patient Perspectives on Barriers and Facilitators of Using a Personal Hearing Support System With Mobile Application as Part of the EVOTION Study

BackgroundHearing loss is a major public health challenge. Audiology services need to utilise a range of rehabilitative services and maximise innovative practice afforded by technology to actively promote personalized, participatory, preventative and predictive care if they are to cope with the social and economic burden placed on the population by the rapidly rising prevalence of hearing loss. Digital interventions and teleaudiology could be a key part of providing high quality, cost-effective, patient-centred management. There is currently very limited evidence that assesses the hearing impaired patient perspective on the acceptance and usability of this type of technology.AimThis study aims to identify patient perceptions of the use of a hearing support system including a mobile smartphone app when used with Bluetooth-connected hearing aids across the everyday life of users, as part of the EVOTION project.MethodsWe applied a questionnaire to 564 participants in three countries across Europe and analysed the following topics: connectivity, hearing aid controls, instructional videos, audiological tests and auditory training.Key FindingsOlder users were just as satisfied as younger users when operating this type of technology. Technical problems such as Bluetooth connectivity need to be minimised as this issue is highly critical for user satisfaction, engagement and uptake. A system that promotes user-controllability of hearing aids that is more accessible and easier to use is highly valued. Participants are happy to utilise monitoring tests and auditory training on a mobile phone out of the clinic but in order to have value the test battery needs to be relevant and tailored to each user, easy to understand and use. Such functions can elicit a negative as well as positive experience for each user.ConclusionOlder and younger adults can utilise an eHealth mobile app to complement their rehabilitation and health care. If the technology works well, is tailored to the individual and in-depth personalised guidance and support is provided, it could assist maximisation of hearing aid uptake, promotion of self-management and improving outcomes.

New Internet of Medical Things for Home-Based Treatment of Anorectal Disorders

Home-based healthcare provides a viable and cost-effective method of delivery for resource- and labour-intensive therapies, such as rehabilitation therapies, including anorectal biofeedback. However, existing systems for home anorectal biofeedback are not able to monitor patient compliance or assess the quality of exercises performed, and as a result have yet to see wide spread clinical adoption. In this paper, we propose a new Internet of Medical Things (IoMT) system to provide home-based biofeedback therapy, facilitating remote monitoring by the physician. We discuss our user-centric design process and the proposed architecture, including a new sensing probe, mobile app, and cloud-based web application. A case study involving biofeedback training exercises was performed. Data from the IoMT was compared against the clinical standard, high-definition anorectal manometry. We demonstrated the feasibility of our proposed IoMT in providing anorectal pressure profiles equivalent to clinical manometry and its application for home-based anorectal biofeedback therapy.

The feasibility of Telemedicine in Implementation of Therapeutic Hypothermia for Management of Neonatal Hypoxic-Ischemic Encephalopathy in Resource-Limited Areas.

Background: Telemedicine is widely used in neonatal services in developed countries. Lack of expertise and/or facilities, however, limited its use in developing countries and around areas of military conflicts. To our knowledge, no reports are demonstrating the feasibility of administering therapeutic hypothermia (TH) through telemedicine to neonates with hypoxic-ischemic encephalopathy (HIE) in resource-limited areas.Methodology: This is a retrospective study, evaluating 22 patients who received TH, guided by telemedicine, through a mobile app (Telegram®). We assessed the feasibility of utilizing Telemedicine in guiding the application of TH to infants affected with HIE in the North-West of Syria between July 2020 and July 2021.Results: Out of 5,545 newborn infants delivered during the study period, 22 patients were eligible for TH guided by Telemedicine. Patients were referred for consultation at a median (IQR) of 137 (35-165) minutes of life. A median (IQR) of 12 (3-18) minutes elapsed between the call for a consultation and the consultant response, and a median (IQR) of 30 (0-42) minutes elapsed between seeking the consultation and the initiation of cooling therapy. Eighteen patients completed cooling for 72 hours. The patients' temperatures were within the target range (33-34°C) most of the time (84.1%).Conclusion: Telemedicine is a feasible method to guide the implementation TH for HIE in resource-limited areas. The short-term success rate is relatively high; however, further studies with a larger population are needed to confirm these findings.

An IoT System Using Deep Learning to Classify Camera Trap Images on the Edge

Camera traps deployed in remote locations provide an effective method for ecologists to monitor and study wildlife in a non-invasive way. However, current camera traps suffer from two problems. First, the images are manually classified and counted, which is expensive. Second, due to manual coding, the results are often stale by the time they get to the ecologists. Using the Internet of Things (IoT) combined with deep learning represents a good solution for both these problems, as the images can be classified automatically, and the results immediately made available to ecologists. This paper proposes an IoT architecture that uses deep learning on edge devices to convey animal classification results to a mobile app using the LoRaWAN low-power, wide-area network. The primary goal of the proposed approach is to reduce the cost of the wildlife monitoring process for ecologists, and to provide real-time animal sightings data from the camera traps in the field. Camera trap image data consisting of 66,400 images were used to train the InceptionV3, MobileNetV2, ResNet18, EfficientNetB1, DenseNet121, and Xception neural network models. While performance of the trained models was statistically different (Kruskal–Wallis: Accuracy H(5) = 22.34, p < 0.05; F1-score H(5) = 13.82, p = 0.0168), there was only a 3% difference in the F1-score between the worst (MobileNet V2) and the best model (Xception). Moreover, the models made similar errors (Adjusted Rand Index (ARI) > 0.88 and Adjusted Mutual Information (AMU) > 0.82). Subsequently, the best model, Xception (Accuracy = 96.1%; F1-score = 0.87; F1-Score = 0.97 with oversampling), was optimized and deployed on the Raspberry Pi, Google Coral, and Nvidia Jetson edge devices using both TenorFlow Lite and TensorRT frameworks. Optimizing the models to run on edge devices reduced the average macro F1-Score to 0.7, and adversely affected the minority classes, reducing their F1-score to as low as 0.18. Upon stress testing, by processing 1000 images consecutively, Jetson Nano, running a TensorRT model, outperformed others with a latency of 0.276 s/image (s.d. = 0.002) while consuming an average current of 1665.21 mA. Raspberry Pi consumed the least average current (838.99 mA) with a ten times worse latency of 2.83 s/image (s.d. = 0.036). Nano was the only reasonable option as an edge device because it could capture most animals whose maximum speeds were below 80 km/h, including goats, lions, ostriches, etc. While the proposed architecture is viable, unbalanced data remain a challenge and the results can potentially be improved by using object detection to reduce imbalances and by exploring semi-supervised learning.

Dynamic Testing Techniques of Non-Functional Requirements in Mobile Apps: A Systematic Mapping Study

Context: The mobile app market is continually growing offering solutions to almost all aspects of people’s lives, e.g., healthcare, business, entertainment, as well as the stakeholders’ demand for apps that are more secure, portable, easy to use, among other non-functional requirements (NFRs). Therefore, manufacturers should guarantee that their mobile apps achieve high-quality levels. A good strategy is to include software testing and quality assurance activities during the whole life cycle of such solutions. Problem: Systematically warranting NFRs is not an easy task for any software product. Software engineers must take important decisions before adopting testing techniques and automation tools to support such endeavors. Proposal: To provide to the software engineers with a broad overview of existing dynamic techniques and automation tools for testing mobile apps regarding NFRs. Methods: We planned and conducted a Systematic Mapping Study (SMS) following well-established guidelines for executing secondary studies in software engineering. Results: We found 56 primary studies and characterized their contributions based on testing strategies, testing approaches, explored mobile platforms, and the proposed tools. Conclusions: The characterization allowed us to identify and discuss important trends and opportunities that can benefit both academics and practitioners.

Characterizing Daily-Life Social Interactions in Adolescents and Young Adults with Neurodevelopmental Disorders: A Comparison Between Individuals with Autism Spectrum Disorders and 22q11.2 Deletion Syndrome

Social impairments are common features of 22q11.2 deletion syndrome (22q11DS) and autism spectrum disorders (ASD). The Ecological Momentary Assessment (EMA) allowed access to daily-life information in order to explore the phenomenology of social interactions. 32 individuals with 22q11DS, 26 individuals with ASD and 44 typically developing peers (TD) aged 12–30 were assessed during 6 days 8 times a day using a mobile app. Participants with 22q11DS and ASD did not spend more time alone but showed distinct implication in the social sphere than TD. Distinct profiles emerged between the two conditions regarding the subjective experience of aloneness and the subjective experience of social interactions. This study highlights distinct social functioning profiles in daily-life in 22q11DS and ASD that points towards different therapeutic targets.

Effect of Gamified Mobile Applications and the Role of Player Types on the Achievement of Students

The purpose of this study was to examine a gamified mobile application’s effect on students’ achievement, and whether the player types of the students predicted their achievement scores. A “pretest-posttest control group design” research was conducted with 65 undergraduate students taking a compulsory online course. In the study, a gamified mobile app was developed by the researchers and then applied within an online History I course. The results of the study showed no significant difference between the achievement scores of the Experimental Group and Control Group students. However, multiple linear regression analysis results showed that the Experimental Group’s students’ achievement scores were significantly predicted by the player types they used and their mobile app performance. It is argued, therefore, that this result underlines the importance of player type in designing effective mobile gamification apps for the purpose of learning. Suggestions for further studies are also provided.