Advent Of Mobile Devices Research Articles

An IoT solution that detects human physical activities to support health assessment based on sensors and supervised learning algorithms

At the moment, human physical activities can be detected by activity recognition systems to help with health status evaluation. One of the key issues in human activity recognition (HAR) systems is cost, speed, and accuracy. With the advancement of mobile devices and increasingly sophisticated microprocessors, along with the integration of various sensors including accelerometers, human activity recognition has become easier and faster. However, the accuracy of activity classification based on accelerometer data depends on many different factors, which can lead to potential deviations in results. Through various experiments, we have found that selecting optimal features is crucial for the performance of classification. In this paper, we propose a simple feature set that yields very promising results with an accuracy of up to 99%.

Applying the Health Belief Model to mobile device distracted driving

Introduction: The advancement of mobile devices has resulted in constant connectivity, but at the expense of traffic safety. The goal of this study was to apply the Health Belief Model to understand the barriers preventing drivers from driving without manipulating their devices, and what they perceived would motivate them to stop driving distracted. Methods: We conducted a nationwide survey of 2,013 U.S. licensed drivers. Participants indicated how much they agreed with or supported 63 statements and concepts pertaining to the Health Belief Model constructs of threats, barriers, benefits, and cues to action related to manipulating devices while driving. Heath Belief Model constructs were compared between distracted drivers, or those who regularly did (during most or all drives in the previous 30 days) one or more mobile device tasks, and non-distracted drivers. Logistic regression evaluated the relationship between Health Belief Model constructs and distracted driver designation. Results: Those who agreed more with threats (odds ratio [OR], 1.61; 95 % confidence interval [CI], 1.27, 2.04) and disagreed more with barriers to stopping (OR, 0.36; 95 % CI, 0.31, 0.41) were more likely to not drive distracted. We identified distracted drivers’ top barriers to avoiding cellphone distractions, as well as barrier categories that were significantly greater for distracted drivers than non-distracted drivers. Distracted drivers felt most strongly that intrapersonal, interpersonal, and policy cues would motivate behavior termination, and more support of technological countermeasures was associated with regularly driving distracted after controlling for support for policy and organizational countermeasures. Conclusions: Simultaneously increasing threat perceptions, targeting the top barriers identified, and implementing policy-, interpersonal-, and technological-based countermeasures may encourage device-free driving. Practical Applications: When designing interventions or programs, state highway safety offices should find new ways to increase threat perceptions and offer solutions to the barriers most cited by distracted drivers.

RF circuit techniques for transition to 5G advanced

Abstract Worldwide adoption of 5G mobile devices has been one of the main driving engines behind semiconductor industry. Since the initial release in 2020, 5G-enabled devices have surpassed the market penetration of 3G/4G smartphones. 5G brings higher data capacity, low latency, and new applications. These are possible due to lower feature nodes such as FinFET 3 nm/5 nm but also due to improvements of the 5G radio frequency (RF)front-end circuitry. This paper presents 5G RF front-end architectures with novel circuits and measurement details which will be part of future 5G advanced and 6G mobile devices and are easier to be controlled using digital circuitry. The paper presents an envelope-controlled power amplifier (PA) principle, along with a novel simplified calibration architecture designed for 5G/5G+ operating under 6 GHz, as well as for frequency range 2 millimeter-wave PAs. An earlier version of this paper was presented at the 2023 53rd European Microwave Conference and was published in the Proceedings [Balteanu F, Thoomu K, Pingale A, Venimadhavan S, Sarkar S, Choi Y, Modi H, Drogi S, Lee J and Agarwal B (2023) Enabling RF circuit techniques for 5G and beyond In 53rd European Microwave Conference (EuMC), Berlin, Germany, 22–25].

Spatial Urban Analysis of Attractions in Riyadh City Using Location-Based Social Network Data (LBSNs)

With the proliferation of technology and the advancement of mobile devices and the internet, the use of Location-Based Social Networks (LBSNs) has become popular in urban communities. That providing a rich source of data for analyzing social and urban behaviour in cities. Which allows for the tracking of urban interaction patterns and human activity to understand visitor behaviour in these places. This paper aims to identify spatial patterns and the distribution the attractions using LBSNs. Density estimation, spatial direction monitoring, and identification of spatial correlation of attractions within Riyadh city were conducted. Heat maps were utilized to reveal the relative density of attraction spots in Riyadh. On the other hand, the distribution trend was analysed using the SDE tool. Moreover, Moran's I index was employed to measure the spatial correlation of attractions within the city. The results of directional and density analysis of attractions indicate a tendency for attraction spots to concentrate in the city centre. Additionally, the results reflect variations between types of places across the studied categories, including parks, shopping centres, entertainment venues, and tourist attractions. The Moran index indicates spatial correlation for the attractions. Overall, LBSNs can be considered an additional and reliable source of big data for social media to monitor urban places and interactions within the city. Future integration of temporal analysis with spatial analysis can be pursued to identify spatiotemporal changes over time. Key words: GIS, Spatial Analysis, LBSNs, Google maps.

Human Activity Recognition Based On Video Summarization And Deep Convolutional Neural Network

Abstract In this technological era, human activity recognition (HAR) plays a significant role in several applications like surveillance, health services, Internet of Things, etc. Recent advancements in deep learning and video summarization have motivated us to integrate these techniques for HAR. This paper introduces a computationally efficient HAR technique based on a deep learning framework, which works well in realistic and multi-view environments. Deep convolutional neural networks (DCNNs) normally suffer from different constraints, including data size dependencies, computational complexity, overfitting, training challenges and vanishing gradients. Additionally, with the use of advanced mobile vision devices, the demand for computationally efficient HAR algorithms with the requirement of limited computational resources is high. To address these issues, we used integration of DCNN with video summarization using keyframes. The proposed technique offers a solution that enhances performance with efficient resource utilization. For this, first, we designed a lightweight and computationally efficient deep learning architecture based on the concept of identity skip connections (features reusability), which preserves the gradient loss attenuation and can handle the enormous complexity of activity classes. Subsequently, we employed an efficient keyframe extraction technique to minimize redundancy and succinctly encapsulate the entire video content in a lesser number of frames. To evaluate the efficacy of the proposed method, we performed the experimentation on several publicly available datasets. The performance of the proposed method is measured in terms of evaluation parameters Precision, Recall, F-Measure and Classification Accuracy. The experimental results demonstrated the superiority of the presented algorithm over other existing state-of-the-art methods.

IeMTLF: Interaction-enhanced Multi-Task Learning Framework for next location prediction

Location-Based Services (LBSs) provide spatial and semantic information of various locations, thanks to the advances in mobile devices and commercial map services. However, most existing studies on next location prediction neglect the semantic information and do not investigate the effects of different levels of semantic granularity. To address these issues, we propose an Interaction-enhanced Multi-Task Learning Framework (IeMTLF) that jointly predicts the next location and its semantic category and leverages higher-order feature interactions to enrich the semantic learning process. Moreover, we examine the effect of two different levels of semantic granularity, namely, specific and abstract, on prediction performance. We conducted extensive experiments on two real-world datasets and demonstrate that IeMTLF outperforms seven baselines on all evaluation metrics, with a maximum gain of more than 13% for Acc@5 compared to the state-of-the-art method. Our implementation code is available at https://github.com/mrc-wyh/IeMTLF.

The Riego Berry mobile application: A powerful tool to improve on-farm irrigation performance in berry crops

Berry crops have transformed the province of Huelva, in the Southwest Spain, transforming it into a prosperous area of Andalusia. Since the 1990 s, there has been a debate in this area about balancing agricultural production with environmental preservation, because 75% of berry production is in the vicinity of the Doñana National Park, a natural area of high ecological value designated as World Heritage by UNESCO. Therefore, it is necessary to improve the efficiency of water use in the area. The advancement of mobile devices has allowed their wide use by technicians and farmers to schedule their irrigations. For this reason, the Riego Berry App has been developed as a smartphone application that allows to make irrigation schedules in a fast and intuitive way. This tool is the result of a more than ten-year public-private partnership. In this work, a comprehensive study has been made to validate the App, using data from trials conducted on commercial farm. The average irrigation water applied (IWA) by farmers ranged from 4292 (raspberry) to 8752 m3/ha (blueberry), whereas Riego Berry’s average IWA ranged from 3053 (raspberry) to 6177 m3/ha (blueberry). Water savings of 41% for strawberry and 29% for raspberry and blueberry have resulted from the use of this tool on commercial farms. Despite irrigation differences, there were no significant differences in yields between the farmer’s and Riego Berry treatments. Farm application efficiency increased by 63% for strawberry, 42% for raspberry, and 37% for blueberry, while irrigation water productivity increased by 36% for blueberry and raspberry, and 56% for strawberry.

FAVER: Blind quality prediction of variable frame rate videos

Video quality assessment (VQA) remains an important and challenging problem that affects many applications at the widest scales. Recent advances in mobile devices and cloud computing techniques have made it possible to capture, process, and share high resolution, high frame rate (HFR) videos across the Internet nearly instantaneously. Being able to monitor and control the quality of these streamed videos can enable the delivery of more enjoyable content and perceptually optimized rate control. Accordingly, there is a pressing need to develop VQA models that can be deployed at enormous scales. While some recent effects have been applied to full-reference (FR) analysis of variable frame rate and HFR video quality, the development of no-reference (NR) VQA algorithms targeting frame rate variations has been little studied. Here, we propose a first-of-a-kind blind VQA model for evaluating HFR videos, which we dub the Framerate-Aware Video Evaluator w/o Reference (FAVER). FAVER uses extended models of spatial natural scene statistics that encompass space–time wavelet-decomposed video signals, and leverages the advantages of the deep neural network to provide motion perception, to conduct efficient frame rate sensitive quality prediction. Our extensive experiments on several HFR video quality datasets show that FAVER outperforms other blind VQA algorithms at a reasonable computational cost. To facilitate reproducible research and public evaluation, an implementation of FAVER is being made freely available online: https://github.com/uniqzheng/HFR-BVQA.

Exploring Embodied Cognition and Brain Dynamics under Multi-tasks Target Detection in Immerse Projector-based Augmented Reality (IPAR) Scenarios.

Embodied cognition explores the intricate interaction between the brain, body, and the surrounding environment. The advancement of mobile devices, such as immersive interactive computing and wireless electroencephalogram (EEG) devices, has presented new challenges and opportunities for studying embodied cognition. To address how mobile technology within immersive hybrid settings affects embodied cognition, we propose a target detection multitask incorporating mixed body movement interference and an environmental distraction light signal. We aim to investigate human embodied cognition in immersive projector-based augmented reality (IPAR) scenarios using wireless EEG technology. We recruited and engaged fifteen participants in four multitasking conditions: standing without distraction (SND), walking without distraction (WND), standing with distraction (SD), and walking with distraction (WD). We pre-processed the EEG data using Independent Component Analysis (ICA) to isolate brain sources and K-means clustering to categorize Independent Components (ICs). Following that, we conducted time-frequency and correlation analyses to identify neural dynamics changes associated with multitasking. Our findings reveal a decline in behavioral performance during multitasking activities. We also observed decreases in alpha and beta power in the frontal and motor cortex during standing target search tasks, decreases in theta power, and increases in alpha power in the occipital lobe during multitasking. We also noted perturbations in theta band power during distraction tasks. Notably, physical movement induced more significant fluctuations in the frontal and motor cortex than distractions from social environment light signals. Particularly in scenarios involving walking and multitasking, there was a noticeable reduction in beta suppression. Our study underscores the importance of brain-body collaboration in multitasking scenarios, where the simultaneous engagement of the body and brain in complex tasks highlights the dynamic nature of cognitive processes within the framework of embodied cognition. Furthermore, integrating immersive augmented reality technology into embodied cognition research enhances our understanding of the interplay between the body, environment, and cognitive functions, with profound implications for advancing human-computer interaction and elucidating cognitive dynamics in multitasking.

Biomechanical Analysis and Mobility Improvement of Auxiliary Mobile Equipment

As an advanced auxiliary mobile device, exoskeleton booster has attracted wide attention in the field of rehabilitation and life assistance. Through biomechanical analysis, this paper discusses the effect of exoskeleton booster on user mobility. Using biomechanical tools such as kinematics, dynamics and muscle mechanics, this paper deeply studies the influence of exoskeleton booster in different motion States, and verifies its biomechanical effect through simulation and experiment. Firstly, this paper analyzes the influence of exoskeleton booster on gait from the perspective of kinematics. The research shows that the exoskeleton booster can improve the walking efficiency of users by optimizing the step size and step frequency. The precise adjustment of joint motion by intelligent control system enables exoskeleton to better adapt to the gait characteristics of different users. Secondly, through dynamic analysis, this paper deeply studies the influence of exoskeleton on joint torque. The exoskeleton is designed to apply appropriate torque at key joints to help users complete the movement. The synergistic effect of this moment not only reduces the muscle burden of users, but also improves the stability of joints and reduces the risks in sports. In terms of improving mobility, exoskeleton technology can significantly improve the gait of patients in rehabilitation training, which is helpful to improve the balance ability of patients. The improvement effect of exoskeleton technology directly affects the quality of daily life of patients. This biomechanical effect provides strong support for the extensive application of exoskeleton technology in rehabilitation, sports assistance and daily life.

Optimizing the input feature sets and machine learning algorithms for reliable and accurate estimation of continuous, cuffless blood pressure

The advent of mobile devices, wearables and digital healthcare has unleashed a demand for accurate, reliable, and non-interventional ways to measure continuous blood pressure (BP). Many consumer products claim to measure BP with a cuffless device, but their lack of accuracy and reliability limit clinical adoption. Here, we demonstrate how multimodal feature datasets, comprising: (i) pulse arrival time (PAT); (ii) pulse wave morphology (PWM), and (iii) demographic data, can be combined with optimized Machine Learning (ML) algorithms to estimate Systolic BP (SBP), Diastolic BP (DBP) and Mean Arterial Pressure (MAP) within a 5 mmHg bias of the gold standard Intra-Arterial BP, well within the acceptable limits of the IEC/ANSI 80601-2-30 (2018) standard. Furthermore, DBP’s calculated using 126 datasets collected from 31 hemodynamically compromised patients had a standard deviation within 8 mmHg, while SBP’s and MAP’s exceeded these limits. Using ANOVA and Levene’s test for error means and standard deviations, we found significant differences in the various ML algorithms but found no significant differences amongst the multimodal feature datasets. Optimized ML algorithms and key multimodal features obtained from larger real-world data (RWD) sets could enable more reliable and accurate estimation of continuous BP in cuffless devices, accelerating wider clinical adoption.

Design of a Smart Cabin Lighting System Based on Internet of Things

With the rapid advancements in mobile devices and wireless network technologies, the Internet of Things (IoT) has become more powerful and popular than ever. The aim of IoT is to efficiently control various types of objects through wireless communications. This paper aims to design an IoT-based smart lighting system that reduces development costs and saves power consumption. Unlike public open spaces, the focus of this paper is on ship cabin spaces. As ship cabins have unique properties, such as requiring gas-based power generation and preferring a wireless environment, designing a smart cabin lighting system is crucial and has significant commercial value. The smart cabin lighting system is designed with four features. Firstly, it can automatically control the lighting devices around people using position-sensitive devices. Secondly, it enables setting on/off and adjusting the luminance for lighting devices through Touch Keypads. Thirdly, the system can be controlled using an app to turn on/off and adjust the luminance of lighting devices. Lastly, the lighting devices equipped with sensors collect specific data on cloud servers for analysis. The underlying communication protocol used to interconnect the smart lighting devices, sensors, and Touch Keypads is Zigbee. The smart cabin lighting system can be applied to marine lighting, thus improving the commercial value of enterprises related to marine lighting.

Effect of Electronic Health Records Training Program Via Using Advanced Mobile Devices on Career Success among Intern-Nurses

Effect of Electronic Health Records Training Program Via Using Advanced Mobile Devices on Career Success among Intern-Nurses

TeSP-TMF: A temporal-aware personalized POI recommendation approach based on potential preferences and grey relational analysis

The great advances in mobile devices make it critical to exploit multiple auxiliary information for efficient point-of-interest (POI) recommendations. However, most existing methods can neither effectively address the extreme data sparsity encountered in temporal-aware recommendation nor reasonably deal with implicit feedback. Furthermore, previous methods, including those relying on similarity measurement, cannot capture the intrinsic data correlations exhibited in the sparse data. To remedy these drawbacks, this paper proposes a temporal-aware personalized recommendation framework called Temporal Spatial Popularity and Temporal-aware Matrix Factorization (TeSP-TMF). In TeSP-TMF, we present the potential preferences model and temporal-aware matrix factorization model. Specifically, users’ potential preferences that incorporate temporal, spatial, and popularity information are investigated to learn a set of potential POIs for each user, which are filled into the original matrix for further matrix factorization, owing to the sparse nature of the rating matrix. On this basis, we develop a new approach using a combination of grey relational analysis and matrix factorization, which not only relieves data scarcity caused by dividing the matrix with time slots but also strategically mines inherent temporal relationships. Finally, we implement extensive experiments on two public datasets collected from Foursquare and Yelp. Experimental results demonstrate that our proposed method yields competitive quality compared to several state-of-the-art methods. Theoretically, our work contributes promising insights for mitigating data sparsity. In practice, our results can enhance personalized temporal-aware POI recommendation services for location-based social networks.

Smart Attendance System based on improved Facial Recognition

Nowadays, the fourth industrial revolution has achieved significant advancement in high technology, in which artificial intelligence has had vigorous development. In practice, facial recognition is one most essential tasks in the field of computer vision with various potential applications from security and attendance system to intelligent services. In this paper, we propose an efficient deep learning approach to facial recognition. The paper utilizes the architecture of improved FaceNet model based on MobileNetV2 backbone with SSD subsection. The improved architecture uses depth-wise separable convolution to reduce the model size and computational volume and achieve high accuracy and processing speed. To solve the problem of identifying a person entering and exiting an area and integrating on advanced mobile devices limits to (such as limited memory and on-device storage) highly mobile resources. Especially, our approach yields better results in practical application with more than 95% accuracy on a small dataset of the original face images. Obtained frame rate (25 FPS) is very favorable compared to the field of facial recognition using neural network. Besides, the deep learning based on solution could be applicable in many low-capacity hardware or optimize system’s resource. Finally, the smart automated attendance systems is successfully designed basing on the improved efficient facial recognition.

IS-DT: A New Feature Selection Method for Determining the Important Features in Programmatic Buying

Traditional data-driven feature selection techniques for extracting important attributes are often based on the assumption of maximizing the overall classification accuracy. However, the selected attributes are not always meaningful for practical problems. So, we need additional confirmation from the experts in the domain knowledge to determine whether these extracted features are meaningful knowledge. Moreover, due to advances in mobile devices and wireless environments, programmatic buying (PB) has become one of the critical consumer behaviors in e-commerce. However, it is extremely difficult for PB service providers to build customers’ loyalty, since PB customers require a high level of service quality and can quickly shift the purchases from one website to another. Previous studies developed various dimensions/models to measure the service quality of PB; nevertheless, they did not identify the key factors for increasing customers’ loyalty and satisfaction. Consequently, this study used an importance–satisfaction (IS) model as domain knowledge and proposed a new IS-DT feature selection method. This new IS-DT method combined the IS model and the decision tree (DT) algorithm to extract useful service quality factors for enhancing customer satisfaction and loyalty in PB. An actual case was also provided to illustrate the effectiveness of our proposed method. The results showed that for increasing customer satisfaction, the highest impact factors included “problem solving”, “punctuality”, “valence”, and “ease of use”; for building customer loyalty, the most important factors were “expertise”, “problem solving”, “information”, “single column”, “voice guidance”, “QR code”, “situation”, “tangibles”, “assurance”, “entertainment”, and “safety”. Our IS-DT method can effectively determine important service quality factors in programmatic buying.

Scalable Pore Engineering Strategy for Promoting Ion Transport and Rate Capability in Thick Li-Ion Battery Electrodes

Since the first commercialization of lithium-ion batteries (LIBs) in the early 1990s, previous research has been extensive on electrode material development. Due to its high volumetric energy and power densities and its low cost, the LIBs have aided in the widespread adoption of advanced mobile electronic devices, slowly spurred the market penetration of electric vehicles (EVs) globally and been incorporated in household energy storage systems to promote efficient use of renewable energy1,2. Unfortunately, after rapid improvements in LIB technology, the present progress in increasing energy density and reducing the costs of LIBs has been slow. To overcome the performance limitations on the material side, increasing the nickel (Ni) content of layered lithium nickel cobalt aluminum oxide (NCA) and lithium nickel cobalt manganese oxide (NCM) cathode materials and blending silicon with graphite anode materials have shown promise3,4,5. On the manufacturing side, there is a push to use thicker and denser electrodes and increase areal capacity loadings from 3-4 mAh/cm2 to 5-7 mAh/cm2 to reduce the mass and volume fraction of inactive materials and thus reduce costs and improve the energy density and specific energy of LIB cells beyond about 700 Wh/L and 250 Wh/kg, respectively6.-8 . Unfortunately, the characteristic Li+ ion diffusion time is proportional to the square of the average diffusion path through the electrode, which depends on both the electrode thickness and the tortuosity. As a result, the charging time and power performance characteristics in high-loading, dense electrodes may become undesirably poor. Herein, we report on several manufacturing pathways to create straight channel pores within electrodes to accelerate electrolyte wetting and facilitate rapid ion transport to overcome these rate limitations.

Designing and Implementing Electronic Health Records Software for Intern-Nurses by Using Advanced Mobile Devices

Designing and Implementing Electronic Health Records Software for Intern-Nurses by Using Advanced Mobile Devices

Facial Expression Recognition using Robust Algorithm based on Modern Machine Learning Technique

Recently facial expression recognition has turned out to be an interesting field in research because of more demand for security and the advancement of mobile devices. Due to many serious incidents like terrorists’ attack, there arises more concern to develop the security systems mainly in certain places like airports and border crossings where identification and verification are mandatory. On the other hand, these surveillance systems aid to identify the missing person, even though it is based on robust facial expression recognition algorithms and on the developed database for facial expression recognition. However, the human faces are complex and multidimensional which make the facial gesture extraction to be very challenging. Obviously, in high secured applications facial expression recognition (FER) systems are mandatory to avoid incidents. In this paper, the automatic facial expression recognition system is developed based on the machine learning algorithms for classification. This research reveals the identification of FER for the ease of communication. Hybridization of Adaptive Kernel function based Extreme Learning Machine with Chicken Swarm Optimization (HAKELM-CSO) algorithm is introduced for identifying the accurate facial expression among the large database. In this work, an approach is developed by applying the machine learning techniques for the automated classification on the image region. The major purpose of this research work is to overcome the flaws of traditional algorithms and to improve the process of facial expression recognition which could be used in various applications.

Big data from a popular app reveals that fishing creates superhighways for aquatic invaders.

Human activities are the leading cause of biological invasions that cause ecologic and economic damage around the world. Aquatic invasive species (AIS) are often spread by recreational anglers who visit two or more bodies of water within a short time frame. Movement data from anglers are, therefore, critical to predicting, preventing, and monitoring the spread of AIS. However, the lack of broad-scale movement data has restricted efforts to large and popular lakes or small geographic extents. Here, we show that recreational fishing apps are an abundant, convenient, and relatively comprehensive source of "big" movement data across the contiguous United States. Our analyses revealed a dense network of angler movements that was dramatically more interconnected and extensive than the network that is formed naturally by rivers and streams. Short-distanced movements by anglers combined to form invasion superhighways that spanned the contiguous United States. We also identified possible invasion fronts and invaded hub lakes that may be superspreaders for two relatively common aquatic invaders. Our results provide unique insight into the national network through which AIS may be spread, increase opportunities for interjurisdictional coordination that is essential to addressing the problem of AIS, and highlight the important role that anglers can play in providing accurate data and preventing invasions. The advantages of mobile devices as both sources of data and a means of engaging the public in their shared responsibility to prevent invasions are probably general to all forms of tourism and recreation that contribute to the spread of invasive species.