Deployment Of Mobile Devices Research Articles

Dynamic activation and enhanced image contour features for object detection

Object detection technology is a popular research direction which is widely used in areas such as autonomous driving and medical diagnosis. At this stage mobile devices often have limited storage resources to deploy large object detection networks and need to meet real-time requirements. This paper proposes a lightweight and efficient object detection model based on YOLOv4, first using the lightweight network GhostNet to extract image features and reduce the number of parameters and computation of the backbone structure; then combining AFmodule and Meta-ACON activation function to enhance the feature extraction capability of the backbone network, which strengthen the mode’s ability to capture image spatial feature information; this paper also designs the RL-PAFPN feature fusion structure is with the Reslayer module to further improve the model’s ability to extract and fuse image features. By comparing other mainstream object detection models, the YOLOv4-Ghost-AMR network in this paper has less computation and fewer parameters, and the accuracy of the model reaches 86.83%, which is suitable for deployment in mobile devices with limited storage. The model proposed in this paper can be applied to medical, traffic and fault detection fields, which changes the traditional manual detection method and saves manpower and time costs, achieving high precision real-time object detection.

Progressive Kernel Pruning Based on the Information Mapping Sparse Index for CNN Compression

Network pruning can effectively reduce a model’s capacity and computational load, thereby making model deployment in mobile devices less difficult than that without pruning. To improve the pruning rate of the model while maintaining the kernel’s feature extraction ability, this paper designs a progressive kernel pruning method for CNN model compression based on the proposed information mapping sparsity index. This method first prunes the kernels in the filter and then prunes the kernels in the convolution layer when the model reaches a certain compression ratio. The whole process is called progressive kernel pruning (PKP). For the kernel pruning process, this paper defines the information mapping sparse index (IMSI), which is used to measure the mapping ability of the convolution kernel related to the amount of information transferred by the convolution operation. When pruning the kernels of filters and layers, according to the IMSI, the kernels with the strongest mapping abilities are retained to transfer as much information as possible with the least number of kernels. Progressive kernel pruning can make use of the characteristic that the model is easy to optimize when kernel pruning in the filter, and it avoids having the model easily fall into local optima when kernel pruning in the layer directly. The experimental results on the CIFAR-10/100 and ImageNet datasets show that compared to the existing CNN model compression methods, the IMSI-based progressive kernel pruning method exhibits better compression performance in processing the model compression tasks that are currently popular. In particular, pruning VGG-16 on CIFAR-10 with our model achieves a compression ratio of 80.8x and an acceleration ratio of 14.8x, which are 5.8x and 4.2x higher than the best results at present, respectively, and the classification accuracy decreases by only 0.59% relative to that of the baseline.

A Physical Layer for Low Power Optical Wireless Communications

Energy consumption is one of the critical issues in optical wireless communications transmitter design and a limiting factor to miniaturization and deployment in mobile devices. In order to reduce energy requirements, we assess a physical layer based on high-bandwidth on-off keying modulation. The use of on-off keying allows for highly efficient transmitter frontend designs that avoid operation of amplifier stages in a resistive mode, which has the potential of reducing their energy usage by an order of magnitude. Link-level simulations show that this physical layer can deal with typical frontend limitations and can operate in challenging non-line-of-sight channels. For these reasons, we believe that the solution evaluated here can deliver a significant contribution to optical wireless communications technology in a wide range of use cases.

Manifold learning for user profiling and identity verification using motion sensors

Mobile devices are becoming ubiquitous and being increasingly used for data-sensitive activities such as communication, personal media storage, and banking. The protection of such data commonly relies on passwords and biometric traits such as fingerprints. These methods perform the user authentication sporadically and often require action from the user, which may make them susceptible to spoofing attacks. This scenario can be mitigated if we bring to bear motion-sensing based methods for authentication, which operate continuously and without requiring user action, hence are harder to attack. Such methods could be used allied with traditional authentication methods or on their own. This paper explores this idea in a novel user-agnostic approach for identity verification based on motion traits acquired by mobile sensors. The proposed approach does not require user-specific training before deployment in mobile devices nor does it require any extra sensor in the device. This solution is capable of learning a user profiling manifold from a small user subset and extend it to unknown users. We validated the proposal on two public datasets. The reported experiments demonstrate remarkable results under a cross-dataset protocol and an open-set setup. Moreover, we performed several analyses aiming at answering critical questions of a biometric method and the presented solution.

Comparison of On-Site Versus Remote Mobile Device Support in the Framingham Heart Study Using the Health eHeart Study for Digital Follow-up: Randomized Pilot Study Set Within an Observational Study Design.

BackgroundNew electronic cohort (e-Cohort) study designs provide resource-effective methods for collecting participant data. It is unclear if implementing an e-Cohort study without direct, in-person participant contact can achieve successful participation rates.ObjectiveThe objective of this study was to compare 2 distinct enrollment methods for setting up mobile health (mHealth) devices and to assess the ongoing adherence to device use in an e-Cohort pilot study.MethodsWe coenrolled participants from the Framingham Heart Study (FHS) into the FHS–Health eHeart (HeH) pilot study, a digital cohort with infrastructure for collecting mHealth data. FHS participants who had an email address and smartphone were randomized to our FHS-HeH pilot study into 1 of 2 study arms: remote versus on-site support. We oversampled older adults (age ≥65 years), with a target of enrolling 20% of our sample as older adults. In the remote arm, participants received an email containing a link to enrollment website and, upon enrollment, were sent 4 smartphone-connectable sensor devices. Participants in the on-site arm were invited to visit an in-person FHS facility and were provided in-person support for enrollment and connecting the devices. Device data were tracked for at least 5 months.ResultsCompared with the individuals who declined, individuals who consented to our pilot study (on-site, n=101; remote, n=93) were more likely to be women, highly educated, and younger. In the on-site arm, the connection and initial use of devices was ≥20% higher than the remote arm (mean percent difference was 25% [95% CI 17-35] for activity monitor, 22% [95% CI 12-32] for blood pressure cuff, 20% [95% CI 10-30] for scale, and 43% [95% CI 30-55] for electrocardiogram), with device connection rates in the on-site arm of 99%, 95%, 95%, and 84%. Once connected, continued device use over the 5-month study period was similar between the study arms.ConclusionsOur pilot study demonstrated that the deployment of mobile devices among middle-aged and older adults in the context of an on-site clinic visit was associated with higher initial rates of device use as compared with offering only remote support. Once connected, the device use was similar in both groups.

Mobile Self-Monitoring ECG Devices to Diagnose Arrhythmia that Coincide with Palpitations: A Scoping Review.

The use and deployment of mobile devices across society is phenomenal with an increasing number of individuals using mobile devices to track their everyday health. However, there is a paucity of academic material examining this recent trend. Specifically, little is known about the use and deployment of mobile heart monitoring devices for measuring palpitations and arrhythmia. In this scoping literature review, we identify the contemporary evidence that reports the use of mobile heart monitoring to assess palpitations and arrhythmia across populations. The review was conducted between February and March 2018. Five electronic databases were searched: Association for Computing Machinery (ACM), CINHAL, Google Scholar, PubMed, and Scopus. A total of 981 records were identified and, following the inclusion and exclusion criteria, nine papers formed the final stage of the review. The results identified a total of six primary themes: purpose, environment, population, wearable devices, assessment, and study design. A further 24 secondary themes were identified across the primary themes. These included detection, cost effectiveness, recruitment, type of setting, type of assessment, and commercial or purpose-built mobile device. This scoping review highlights that further work is required to understand the impact of mobile heart monitoring devices on how arrhythmias and palpitations are assessed and measured across all populations and ages of society. A positive trend revealed by this review demonstrates how mobile heart monitoring devices can support primary care providers to deliver high levels of care at a low cost to the service provider. This has several benefits: alleviation of patient anxiety, lowering the risk of morbidity and mortality, while progressively influencing national and international care pathway guidelines. Limitations of this work include the paucity of knowledge and insight from primary care providers and lack of qualitative material. We argue that future studies consider qualitative and mixed methods approaches to complement quantitative methodologies and to ensure all actors’ experiences are recorded.

Constant envelope FrFT OFDM: Spectral and energy efficiency analysis

Constant envelope with a fractional Fourier transformorthogonal frequency division multiplexing (CE-FrFT-OFDM) is a special case of a constant envelope OFDM (CE-OFDM), both being energy efficient wireless communication techniques with a 0 dB peak to average power ratio (PAPR). However, with the proper selection of fractional order, the first technique has a high bit error rate (BER) performance in the frequency-time selective channels. This paper performs further analysis of CE-FrFT-OFDM by examining its spectral efficiency (SE) and energy efficiency (EE) and compare to the famous OFDM and FrFT-OFDM techniques. Analytical and comprehensive simulations conducted show that, the CE-FrFT-OFDM has five times the EE of OFDM and FrFT-OFDM systems with a slightly less SE. Increasing CE-FrFT-OFDM's transmission power by increasing its amplitude to 1.7 increases its SE to match that of the OFDM and FrFT-OFDM systems while slightly reducing its EE by 20% to be four times that of OFDM and FrFTOFDM systems. OFDM and FrFT-OFDM's amplitude fluctuations cause rapid changing output back-off (OBO) power requirements and further reduce power amplifier (PA) efficiency while CE-FrFTOFDM stable operational linear range makes it a better candidate and outperforms the other techniques when their OBO exceeds 1.7. Higher EE and low BER in time-frequency selective channel are attracting features for CE-FrFT-OFDM deployment in mobile devices.

Octennial Review (2010-2018) of Literature on M-Learning for Promoting Distributed-Based Medical Education in Sub-Saharan Africa

Medical education in Africa is in desperate need of reforms, evident in widespread diseases, and an inability to mobilise and train the required medical workforce to deal with these health issues. However, the exponential rise in the use of mobile technologies due to the spread of the Internet and increased telecommunication networks offer an opportunity for the transformation of medical education and practice through the deployment of mobile devices as a medium for learning and conveying health care services to the remote and resource-constrained locations of Sub-Saharan Africa (SSA). This paper reviewed articles on the affordances of m-learning for distributed medical education in SSA published between 2010-2018. Results from 18 articles identified in the review revealed a slow-paced ascendancy of practice and research in the field; it further exposed competing priorities, infrastructural deficit, and chronic workforce shortages as the bane of m-learning implementation in the subregion. This paper makes recommendations that will enhance the growth of mobile-based distance medical education and practice in SSA.

Mobile Devices to Enhance Teaching and Learning in the Classroom: Some More Second Thoughts, Using Activity Theory

The focus of this interdisciplinary research is to comprehend the impacts of computing lecturers' deployment of mobile devices in the classroom for teaching and learning. Along this line of thought, the use of activity theory was paramount towards understanding the activity system which three lecturers work within. Their stances were investigated with emphasis on their lengthy years of experiences relating to teaching and learning especially using technology in addition to additional constituents of the activity system of teaching computing to higher education students within a further education college.A qualitative approach was used and the results delineate the existential nature of different ambiguities that posits at the continuum of between and within various components of the activity system. These inconsistencies include the deficiency in reflecting, teamwork, peer communication, the pressure to reduce the existing gap between theory and practice, issues with classroom sizes and the habitus of the classrooms in relation to technology enhanced learning (TEL). Numerous recommendations are put forward to alter the current state of interplay in teaching computing to higher education learners in addition to strategic deployment of mobile devices in the classroom towards fostering the growth of a technology-enhanced classroom. Keywords: Computing lecturers, mobile devices, mobile learning, m-learning, technology-enhanced classroom, activity system, activity theory, higher education, further education DOI : 10.7176/JEP/10-9-15 Publication date :March 31 st 2019

Abstract MP24: Comparison of on-site versus Remote Support for a Mobile-Device Pilot Study: A Collaboration Between the Framingham Heart Study and Health eHeart Study (FHS-HeH)

Background: New “e-Cohort” study designs provide resource-effective methods for collecting participant data. It is unclear if implementing an e-cohort without direct, in-person participant contact can achieve successful participation rates. The FHS-HeH randomized pilot study compared two distinct implementation strategies for co-enrolling participants from the Framingham Heart Study (FHS) into the Health eHeart Study, a digital cohort with infrastructure for collecting mHealth data. Methods: FHS participants who had an email address and smartphone were randomized to one of two approaches: remote vs. on-site support. In the remote arm, participants received an email containing an enrollment URL, and, upon enrollment, were sent four Bluetooth sensor devices. Participants in the on-site arm were invited to visit FHS and were provided in-person support for enrollment and connecting the devices. Results: Compared to participants that declined, individuals that accepted an invitation to participate in our pilot study (n=101 remote , n=101 on-site ) were more often women, highly educated, and younger (Figure 1). All on-site participants completed the consent, compared to 93% of the remote arm. Of participants who consented to participate, connection and initial use of devices was also higher in the on-site arm (100% connected the activity monitor, 94% the blood pressure cuff and scale, and 84% the electrocardiogram) compared to the remote arm (74%, 75%, 80%, and 42%). Roughly 75-78% of those that initially connected in both arms were still using the devices by the 3 rd month and 58-60% were still participating by the 6 th month. Conclusions: Our pilot study demonstrated that deployment of mobile devices among middle-aged and older adults in the context of an on-site clinic visit was associated with higher initial rates of device use as compared to offering only remote support. Once connected, drop-off rates were similar in both groups.

Mobile Imagery eXchange (MIX) toolkit: data sharing for the unconnected

This paper proposes a healthcare solution that enables the sharing of medical videos in areas without satellite, broadband or mobile internet connectivity. Rural areas often encounter issues such as shortage of electricity, poor telecommunication services and lack of health facilities which have led to a deficiency of medical care in remote areas. The deployment of mobile devices for healthcare services is vital to alleviating these concerns. A majority of mobile device owners are located in developing nations, and the number of users is continually rising. These technologies effectively support remote health care due to their low-power requirements, multiple functionalities and custom applications. The Mobile Imagery eXchange (MIX) toolkit is a software application capable of converting echocardiogram videos into text for transmission through short message service (SMS), over a global system for mobile communications network. A smartphone or computer installed with the MIX toolkit can be utilized to deliver effective medical care within rural regions. To significantly shrink data size, video, image and file processing techniques are applied for analysis, segmentation, compression and conversion. Experiments show that data size reduction rates above 60 until 95 % are achievable when transforming imagery into text. Furthermore, in optimal conditions, the average SMS per image ranges from 9 to 23 text messages.

Understanding the Need of Mobile ICT Learning as an Elderly Learning Tool

With a rapid deployment of mobile devices, mobile learning gives rise to new possibilities for extending learning opportunities. Nevertheless, current research on mobile learning has mostly been aimed at enhancing learning of school or college students. In this light, the paper seeks to throw light on the potential of mobile learning for elderly. We describe in this paper a research study for examining needs that determine the adoption and usage of mobile devices by elderly population. The elderly are an often neglected group in product development and marketing, but they are the only growing age group in most developed societies. By using semi-structured interviews with a number of different stakeholders interested in elderly people, we identify a set of issues that need to be taken into account when designing strategy for the elderly learners. The results of our study indicate that elderly people are interested in using mobile devices and services, but these services need to deliver real value for them.

Effective Practices in Deploying Mobile Computing Devices for Field Operations in Process Industries

The deployment of mobile devices in process industries promises greater efficiencies in operations and more effective uses of limited plant resources, compared with current practices. Yet, the adoption and use of these devices has been limited. This paper reports effective practices, applications, and lessons learned from deploying mobile devices for field operations in the refining and petrochemicals industries. Six petrochemical production facilities participated in the study. We interviewed various stakeholders at these facilities on their culture, business drivers, field operations, current use of mobile devices, infrastructure and platforms in place, current applications, and potential needs. Four general areas were identified as critical to the success of deployment: 1) Organizations, Policies and Processes, 2) Applications, 3) Infrastructure, Hardware and Software, and 4) Training.