Search

Environmental perception is crucial for unmanned mobile platforms such as autonomous vehicles and robots. Precise and fast semantic segmentation of the surrounding scene is a key task to enhance this capability. Existing real-time semantic segmentation networks are typically based on convolutional neural networks (CNNs), which have achieved good results, but they still lack control over global context features. In recent years, the Transformer architecture has achieved significant success in capturing global context, which is beneficial for improving segmentation accuracy. However, Transformers tend to ignore local connections, and their computational complexity makes real-time segmentation challenging. We propose a lightweight real-time semantic segmentation network called DTMC-Net, which combines the advantages of CNNs and Transformers. We design a special residual convolution module called the Lightweight Multi-layer Separable Convolution Attention module (LMSCA) to reduce the parameter count and perform multi-scale feature fusion to capture local features effectively. We introduce the Simple Dual-Resolution Transformer (SDR Transformer) that utilizes lightweight attention mechanisms and residual feed forward networks to capture and maintain features, with multiple bilateral fusions between two branches to exchange information. The proposed Anti-artifact Aggregation Pyramid Pooling Module (AAPPM) optimizes the upsampling process, refines features, and performs multi-scale feature fusion again. DTMC-Net only contains 4.2M parameters and achieves good performance on multiple public datasets with different scenarios. [Display omitted] • Emphasizes real-time semantic segmentation for unmanned mobile platforms. • A lightweight model that combines the strengths of CNNs and Transformers is proposed. • Proposes modules to enhance multi-scale feature capture and refinement capabilities. • Competitive results are achieved on several challenging datasets. [ABSTRACT FROM AUTHOR]

• Motorised transport is contributing to the decline of environmental and human health. • A greater understanding of the types of behavioural interventions used in active travel research is required. • Personalised travel plans and mobile applications were the most common behavioural interventions identified. • There is a need for more robust, theory-driven study designs to enable research translation. The societal reliance on motorised transport is negatively affecting the health of humans and the environment. Active travel provides a unique solution to both issues by removing the number of motorised vehicles on the road, while also increasing physical activity rates. Interventions that encourage greater uptake of active travel are considered to be highly beneficial to society. This systematic review of the literature sought to provide evidence to answer the question which behavioural interventions increase commuter cycling? Five databases were searched to identify articles that tested a behavioural intervention to increase commuter cycling. Article parameters were defined from the literature and in consultation with the research team. Study selection, quality appraisal and data extraction were undertaken using Covidence. The final 25 articles revealed that personalised travel plans and mobile phone-based platforms were the most common interventions. Unvalidated travel surveys were the most widely used mode of data collection. Modest increases in commuter cycling were observed across studies; however, the heterogeneity of study designs and reporting of results did not allow aggregation of findings. This review highlights the need for high quality behavioural science research into active travel. This will assist us to better understand the most effective interventions that increase levels of commuter cycling, subsequently improving environmental and human health. [ABSTRACT FROM AUTHOR]

Reliance on vast annotations to achieve leading performance severely restricts the practicality of large-scale point cloud semantic segmentation. For the purpose of reducing data annotation costs, effective labeling schemes are developed and contribute to attaining competitive results under weak supervision strategy. Revisiting current weak label forms, we introduce One Class One Click (OCOC), a low cost yet informative quasi scene-level label, which encapsulates both point-level and scene-level annotations. An active weakly supervised framework is proposed to leverage scarce labels by involving weak supervision from both global and local perspectives. Contextual constraints are imposed by an auxiliary scene classification task, respectively based on global feature embedding and point-wise prediction aggregation, which restricts the model prediction merely to OCOC labels within a sub-cloud. Furthermore, we design a context-aware pseudo labeling strategy, which effectively supplement point-level supervisory signals subject to OCOC labels. Finally, an active learning scheme with a uncertainty measure — temporal output discrepancy is integrated to examine informative samples and provides guidance on sub-clouds query, which is conducive to quickly attaining desirable OCOC annotations and reduces the labeling cost to an extremely low extent. Extensive experimental analysis using three LiDAR benchmarks respectively collected from airborne, mobile and ground platforms demonstrates that our proposed method achieves very promising results though subject to scarce labels. It considerably outperforms genuine scene-level weakly supervised methods by up to 25% in terms of average F1 score and achieves competitive results against full supervision schemes. On terrestrial LiDAR dataset — Semantics3D, using approximately 2‱ of labels, our method achieves an average F1 score of 85.2%, which increases by 11.58% compared to the baseline model. Codes are publicly available at https://github.com/PuzoW/One-Class-One-Click. [ABSTRACT FROM AUTHOR]

• The use of patient-generated data collected and shared with a CF app was feasible and acceptable in clinical settings. • Use of the CF app was associated with improved measures of patient-centered care, including shared decision-making and satisfaction with care. • Study results support wider use of the CF app (Genia) in clinical settings. Previously, we adapted a mobile health platform (Genia) to the needs of patients and families in a pediatric CF center in the United States. In this feasibility study, we tested the impact of Genia on measures of patient-centered care. In a one-group pre-post study with adolescents with CF and caregivers of children with CF, we tested Genia's effect over 6 months on patient satisfaction with chronic illness care (PACIC) and shared decision-making (CollaboRate). Feasibility and acceptability were assessed with exit interviews and app analytics. The intervention included 40 participants: 30 caregivers of children with CF age ≤14 years and 10 patients with CF age ≥15 years. The use of Genia was associated with increased satisfaction with care (p = 0.024), including delivery system and decision support (p = 0.017), goal setting (p = 0.006), and shared decision-making (p <0.001). The use of Genia was associated with nominal improvements in all QOL domains and symptom scales. The platform was feasible, with participants recording more than 4,400 observations (mean 84.2) and submitting 496 weekly reports (mean 13.8) and 70 quarterly reports (mean 1.8), and acceptable (95% retention rate). For participants, the most useful app feature was pre-visit reports (66.7%), and the top symptom trackers were those for cough (23.7%), appetite (21.1%), energy (18.4%), and medicines (18.4%). The use of Genia over 6 months was feasible, acceptable, and associated with improved measures of patient-centered care. Study results support wider use of Genia in clinical settings. Efficacy for clinical outcomes should be assessed in a randomized clinical trial. [ABSTRACT FROM AUTHOR]

This paper investigates the teleoperation problem of networked disturbed mobile manipulators (NDMMs), in which the human operator remotely controls multiple slave mobile manipulators through a master manipulator. Each individual of the slave ones consisted of a nonholonomic mobile platform and a holonomic constrained manipulator that is mounted on the nonholonomic mobile platform. The cooperative control objective of the considered teleoperation problem includes: (1) synchronizing the states of the slave manipulators to the human-controlled master one; (2) forcing the mobile platforms of the slave ones to form a user-defined formation; (3) controlling the geometric center of all the platforms to track a reference trajectory. We present a hierarchical finite-time cooperative control (HFTCC) framework to achieve the cooperative control goal in a finite time. The presented framework includes the distributed estimator, the weight regulator and the adaptive local controller, where the estimator generates the estimated states of the desired formation and trajectory, the regulator selects the slave robot that the master one needs to track, as well as the presented adaptive local controller guarantees the finite-time convergence of the controlled states with model uncertainties and disturbances. Additionally, for improving the telepresence, a novel super twisting observer is presented to reconstruct the interaction force between the salve mobile manipulators and the remote operating environment on the master (i.e., the human) side. Finally, the effectiveness of the proposed control framework is demonstrated by several simulation results. • This paper solves the teleoperation problem of NDMMs in a distributed manner. • A novel HFTCC framework is proposed to achieve the finite-time cooperative control of the NDMMs in the teleoperation system. • A super twisting observer is designed for reconstructing the interaction force between the slave mobile manipulators and the task environment on the human operator. [ABSTRACT FROM AUTHOR]

The widespread usage of smartphones has made accessing vast troves of data easier for everyone. Smartphones are powerful, handy, and easy to operate, making them a valuable tool for improving public health through diagnostics. When combined with other devices and sensors, smartphones have shown potential for detecting, visualizing, collecting, and transferring data, enabling rapid disease diagnosis. In resource-limited settings, the user-friendly operating system of smartphones allows them to function as a point-of-care platform for healthcare and disease diagnosis. Herein, we critically reviewed the smartphone-based biosensors for the diagnosis and detection of diseases caused by infectious human pathogens, such as deadly viruses, bacteria, and fungi. These biosensors use several analytical sensing methods, including microscopic imaging, instrumental interface, colorimetric, fluorescence, and electrochemical biosensors. We have discussed the diverse diagnosis strategies and analytical performances of smartphone-based detection systems in identifying infectious human pathogens, along with future perspectives. [ABSTRACT FROM AUTHOR]

For the purpose of developing a new kind of auxiliary learning method or tool, the author puts forward a kind of personalized mobile EFL learning system based on Android and vocabulary learning. The system consists of Remote Management Server, Client Mobile Learning System and Data Synchronization Intelligence Agent. This system has carried on the corresponding design in view of the different student, the different new word level, the different study, the different memory stage. The study found that there were 15 multiple choice questions before and after the exam, and 15 closed questions, with a full score of 30. In order to ensure accurate testing, the difficulty levels of both tests are controlled within a similar range. Although learners' academic performance in multiple choice questions did not significantly improve, their vocabulary ability in cloze tests significantly improved. It has been proven that the proposed system can effectively improve English learning performance, and the simulation also verifies the effectiveness and practicality of the system. [ABSTRACT FROM AUTHOR]

Financial Technology (FinTech) is a popular name for innovative technology utilized by financial organizations, with a focus on security and privacy concerns. These concerns include threats, attacks, hostile activity, and adversaries, as well as potential responses. The goal of this study is to undertake an assessment of current advances in financial industry security and privacy issues. FinTech is viewed as a gateway to increased business potential by financial sectors and entrepreneurs, but in order to explore such possibilities, mobile applications and other digital platforms must be established. However, security vulnerabilities to mobile applications have expanded dramatically, posing a dilemma for users and FinTech entrepreneurs. The findings of this study can be used to develop a theoretical framework for FinTech security and privacy, which will provide critical support for the establishment of a trustworthy security mechanism in FinTech. [ABSTRACT FROM AUTHOR]

Innovations in recurrent neural networks (RNNs) for time-series modelling has enabled effective prediction of sequence data prevalent in real-world dynamic processes. For example, problem domains such as speech and language modelling, weather prediction, financial forecasting and patient healthcare monitoring have all significantly benefited from developments in RNNs over the last 20 years. Today's vast availability of data has enabled models to learn from higher quality historical information, identify loopholes, and better understand and contextualise evolving information in real-time. This is arguably extremely important as access to fast reliable predictive information empowers decision makers to prepare for and effectively respond to future opportunities or crises. Also, the simpler the forecasting model, the more amenable it is to residing on multiple mobile platforms improving accessibility of predictive power. Given this, we comparatively assess the importance of the Multi-recurrent Neural Network (MRN) with a single hidden layer against current state-of-the-art models using a range of real-world problem domains from oil price prediction to predicting the spread and mortality rate of COVID-19. We find strong evidence that the simple and shallow MRN consistently offers superior performance over the Long Short-term Memory model (LSTM), the current state-of-the-art RNN and Support Vector Machines (SVM), a more traditional statistical approach. The MRN required much fewer adjustable parameters than the LSTM to learn the task and generalise competitively. This suggests that the simpler architecture offers significant value with respect to computational resources and effective predictive abilities for real-world applications which is particularly useful given the current ubiquitous shift towards the use of Internet of Things devices. [ABSTRACT FROM AUTHOR]

• Nonlinear dynamic model of N - links flexible manipulator. • Consider link-joints flexibility and mobile platform. • Investigate the modal analysis of multi-link manipulator. • Demonstrate the dynamic characteristics under harmonic joint forces. • Investigate the stability analysis and bifurcation under resonance conditions. The present work theoretically demonstrates the dynamic analysis of a planar multi-link manipulator considering flexible links and joints mounted on a moving base. A nonlinear model of a multi-manipulator (N -links) has been developed accounting for an equivalent bi-directional mobile base. The nonlinear Euler-Bernoulli beam and spring-inertia/mass system have been introduced to demonstrate the flexibilities of links and joints, respectively. Modal analysis followed by trajectory analysis has been performed to investigate the behaviors of manipulator taking into account of accurate boundary conditions. Further, vibration characteristics, steady-state responses, and their stability at resonant situations due to joint motions and inertial coupling have been studied. Results of exploiting geometric and inertial coupling due to flexible arms on stability analysis of steady-state responses have been investigated and have been subsequently verified with the findings by directly solving the governing equations. Steady-state response characteristics to explore the dynamics of the multi-link manipulators under resonant states have been studied with the varying actuator mass, the flexibility of links, lifted payload, and joint parameters. The results thus obtained, deliver a useful insight into the position analysis and long-term behavior of multi-link flexible manipulators under harmonic hub-joint motions that shall further enable its proper vibration attenuation and control. [ABSTRACT FROM AUTHOR]

Tobacco consumption is a leading cause of preventable death and, despite decades of research, smoking cessation is still a challenge. The number of smokers who attempt to quit smoking every year is high, but only 2-3% remain abstinent after 12 months. Smokers wanting to quit should have the help of healthcare professionals. However, only 1 in 20 who attempts to quit is supervised by a professional. Mobile phone technology has the potential to provide personalized smoking cessation support. Motivational messages and behavioral-changes methods used usually in face-to-face smoking cessation consultations can be modified for delivery via mobile phones. The content can be customized to be patient-centered and tailored for the age, gender and education group of the quitter. This paper presents a platform to support smoking cessation composed by a mobile application to be used by users trying to quit smoking, and a web application to be used by researchers to analyze data regarding the app users' tobacco cessation process. The app follows the transtheoretical model by Prochaska and DiClemente, allowing users to define and be aware of their wishes (what motivates them to stop smoking), barriers that hinder the quitting process and implementation plans and strategies to help them overcoming obstacles. [ABSTRACT FROM AUTHOR]

Currently, the three-dimensional (3D) distribution and characteristics of air pollution cannot be understood based on the application of any single atmospheric monitoring technology. Long-term, high-precision and large-scale 3D atmospheric monitoring might become practical by combining heterogeneous modern technologies; for this purpose, the Space-Air-Ground integrated system is a promising concept. In this system, optical remote sensing technologies employing fixed or mobile platforms are used as the main means for ground-based observations. Tethered balloons, unmanned aerial vehicles (UAV) and airborne platforms serve as the air-based observation segment. The final part, satellite remote sensing, corresponds to space-based observations. Aside from obtaining the 3D distribution of air pollution, research on emission estimation and pollution mechanisms has been extensively implemented based on the strengths of this system or some portion of it. Moreover, further research on the fusion of multi-source data, optimization of inversion algorithms, and coupling with atmospheric models is of great importance to the realization of this system. [Display omitted] [ABSTRACT FROM AUTHOR]

Ensuring safety in tunnel construction necessitates a rapid and objective evaluation of exposed tunnel faces for proactive rock mass risk assessment. The diversity of rock types and discontinuities contributes to structural complexity and local variability, introducing subjectivity and uncertainty in traditional evaluations based on the experience of field engineers. In this study, a convolutional neural network (CNN) is employed for regression to enhance the objectivity and consistency of rock mass classification via rock mass rating (RMR). The model interprets the entire tunnel face image holistically by identifying and learning from complex patterns, rather than detecting specific geological features like fractured or discontinuity zones. The network model, comprising feature extraction and regression blocks, utilizes the EfficientNet family for computational efficiency and accuracy. Data augmentation and ensemble learning address prediction variability due to image quality, optimizing the model for accurate RMR predictions and providing error ranges. The RMR predictions using excavation site images closely follow the field-evaluated evolution. A server communication-based mobile application is developed for real-time RMR evaluation, enhancing its practical field applicability. In geology, tunnel, and geotechnical engineering, where decisions rely on extensive experience, our approach demonstrates that deep learning can enhance decision-making by analyzing large accumulated datasets to predict optimal outcomes. • The proposed approach offers an objective evaluation of RMR using tunnel face images. • The model effectively captures RMR evolutionary changes, including sudden shifts. • Mobile app platform is developed for real-time RMR assessment in field use. [ABSTRACT FROM AUTHOR]

Edge computing on mobile marine platform is paramount for automated ecological monitoring. The goal of demonstrating the computational feasibility of an Artificial Intelligence (AI)-powered camera for fully automated real-time species-classification on deep-sea crawler platforms was searched by running You-Only-Look-Once (YOLO) model on an edge computing device (NVIDIA Jetson Nano), to evaluate the achievable animal detection performances, execution time and power consumption, using all the available cores. We processed a total of 337 rotating video scans (∼180°), taken during approximately 4 months in 2022 at the methane hydrates site of Barkley Canyon (Vancouver Island; BC; Canada), focusing on three abundant species (i.e., Sablefish Anoplopoma fimbria , Hagfish Eptatretus stoutii , and Rockfish Sebastes spp.). The model was trained on 1926 manually annotated video frames and showed high detection test performances in terms of accuracy (0.98), precision (0.98), and recall (0.99). The trained model was then applied on 337 videos. In 288 videos we detected a total of 133 Sablefish, 31 Hagfish, and 321 Rockfish nearly in real-time (about 0.31 s/image) with very low power consumption (0.34 J/image). Our results have broad implications on intelligent ecological monitoring. Indeed, YOLO model can meet operational-autonomy criteria for fast image processing with limited computational and energy loads. • Edge-computing allows robots to detect, classify and count animals in situ. • An animal detection routine was tuned to operate on the crawler Wally in the deep-sea. • 337 videos were processed with a Jetson Nano, seeking low computational load. • Processing and power consumption sustain autonomy in species monitoring. [ABSTRACT FROM AUTHOR]

Acoustic micromanipulation methods offer versatile tools ranging from lab-on-chip diagnostic platforms to mobile microrobots. Acoustically oscillating bubble-powered microsystems are gaining increased attention owing to their low cost and convenient operation. To date, no studies have reported on the controllability of the driving frequency on acoustic micromanipulation platforms using Helmholtz resonators. Here, we introduce a Helmholtz resonant cavity into a bubble-powered microsystem to reveal the function of the oscillation modes and frequency selectivity. The Su–Schrieffer–Heeger (SSH) model was utilized to construct a topological interfacial state and bubble-powered working location. We experimentally observed that the microparticles were captured by the oscillation bubble and underwent orbital rotation at the topological frequency. However, the microparticles were tightly bound close to the oscillation bubble area when the driving frequency was outside the topological frequency range. Our acoustic micromanipulation platform implements multiple microparticle manipulation modes based on frequency selectivity that are independent of optical or magnetic properties, which can enrich the micromanipulation toolbox and exhibit enormous application potential in the biomedical field. • A Helmholtz resonant cavity is introduced into a bubble-powered microsystem. • SSH model used for topological interfacial state and bubble-powered location. • Our platform implements multiple microparticle manipulation modes. • Modes based on frequency selectivity regardless of optical or magnetic properties. • Proposed platform has application potential in the biomedical field. [ABSTRACT FROM AUTHOR]

The growing global demand for clean water has boosted the evolution of advanced water treatment technologies. Micromotors, as artificial active matter boasting exceptional self-propulsion capabilities and facile surface modification, have emerged as promising mobile platforms to tackle water-related environmental issues. Their motion-enhanced mixing properties intensify interactions with target substances, accelerating diffusion-limited reactions, thus significantly enhancing the efficiency of various chemical processes. This overview presents the latest advancements in the application of micromotors for water quality detection and remediation. It encompasses a range of contaminants and their respective detection and removal strategies. Specifically, three prevalent contaminants are highlighted: heavy metal ions (HMIs), chemicals, and pathogenic microorganisms. Particular emphasis is placed on elucidating detection mechanisms tailored to each contaminant type, with an exhaustive enumeration of the associated mechanisms where possible. Following this, the review explicates the removal strategies for these contaminants by consolidating and outlining typical methodologies. Finally, the discussion addresses pivotal open challenges and outlines essential future research directions for the effective deployment of micromotors in water environment. [Display omitted] • The latest advances of micromotors for water quality detection and remediation are presented. • Detection mechanisms and removal strategies for three representative contaminants are systematically outlined and clarified. • Low cost, low toxicity, high sensitivity, and efficient remediation capacity are crucial factors to consider. • Research-practical discrepancy call for more realistic aquatic testing scenarios. [ABSTRACT FROM AUTHOR]

The increasing popularity of mobile applications has catalyzed advancements in object tracking algorithms for mobile platforms. This paper introduces a lightweight object tracking algorithm, designed for real-time and accurate tracking on mobile devices. We propose a feature extraction network with a quantization-friendly architecture and a novel mask-based padding method to enhance tracking precision. By refining MobileNetV3's structure, we mitigate accuracy degradation during quantization and reduce computational demands. The proposed padding technique addresses the outlier generation issue common in traditional padding methods, thereby enhancing positional accuracy. Additionally, an extent adjustment module is incorporated to facilitate prompt error correction during suboptimal tracking. Comprehensive evaluations on OTB50, OTB100, VOT2018, UAV123, and LaSOT demonstrate the superiority of our method over several state-of-the-art trackers in both speed and accuracy. Notably, our feature extraction model is only 3.4 MB, running at 243fps on an RTX 3090 GPU, and can adapt to various sizes of video inputs. • A quantization-friendly structure is designed to reduce the network model size without compromising accuracy. • A mask-based padding method is introduced to better adapt to tracking tasks. • An extent adjustment module is proposed to detect the tracking quality and adjust the size of the search area. • The proposed method achieves excellent tracking accuracy and surpasses similar algorithms in tracking speed. [ABSTRACT FROM AUTHOR]

Mobile devices have become an essential element in our day-to-day lives. The chances of mobile attacks are rapidly increasing with the growing use of mobile devices. Exploiting vulnerabilities from devices as well as stealing personal information, are the principal targets of the attackers. Researchers are also developing various techniques for detecting and analyzing mobile malware to overcome these issues. As new malware gets introduced frequently by malware developers, it is very challenging to come up with comprehensive algorithms to detect this malware. There are many machine-learning and deep-learning algorithms have been developed by researchers. The accuracy of these models largely depends on the size and quality of the training dataset. Training the model with a diversified dataset is necessary to predict new malware accurately. However, this training process may raise the issue of privacy loss due to the disclosure of sensitive information of the users. Researchers have proposed various techniques to mitigate this issue, such as differential privacy, homomorphic encryption, and federated learning. This survey paper explores the significance of applying federated learning to the mobile operating systems, contrasting traditional machine learning and deep learning approaches for mobile malware detection. We delve into the unique challenges and opportunities of the architecture of in-built mobile operating systems and their implications for user privacy and security. Moreover, we assess the risks associated with federated learning in real-life applications and recommend strategies for developing a secure federated learning framework in the domain of mobile malware detection. [ABSTRACT FROM AUTHOR]

Accurate measurement of the diameter at the breast height (DBH) is essential in forestry-related science and practice, but its measurement is currently done by labor-intensive tools such as calipers or devices designed to measure the girth. With the development in light detection and ranging (LiDAR) and augmented reality (AR) technologies, and their integration in low-cost mobile platforms, affordable proximal measurement applications were released on the market. This study examines the accuracy in DBH measurement of Arboreal Forest (hereafter DA) and Measure (hereafter DM) apps, by taking as a reference the measurements done by an accurate forestry caliper (hereafter DC). A number of 615 trees were considered, of which 395 were broadleaved (DBH between 10 and 73 cm, averaging 39.73 ± 9.91 cm) and 220 were coniferous (DBH between 25 and 89 cm, averaging 52.47 ± 12.81 cm), and measurements were taken under sunny, cloudy and rainy weather. Comparison was done in terms of agreement (Bland and Altman's method), dependence (least square simple ordinary and regression through origin), correlation (Spearman's, Pearson's and Kendall's tests), and difference (mean absolute error - MAE, root mean squared error - RMSE, and bias - BIAS). Besides a close-to-perfect fit, strong association in data, and a good degree of agreement, the results indicated the presence of centimeter-level differences when comparing DM against DC (MAE = 0.715 cm, RMSE = 0.879 cm, BIAS = 0.333 cm) and DA against DC (MAE = 0.953 cm, RMSE = 1.246 cm, BIAS = -0.108 cm). When comparing DA against DM the differences were slightly higher (MAE = 1.175 cm, RMSE = 1.531 cm, BIAS = –0.446 cm). The magnitude in differences found is rather caused by the application used and not by the environmental conditions. Further studies may consider larger data samples to provide better estimates as well as checking the limits in measurement capabilities of these apps. • Accurate measurement of the breast height diameter is essential in forestry. • Professional LiDAR scanners are expensive and less suitable in rough terrain. • Two digital methods were tested to describe and characterize their accuracy. • The statistical analysis verified the measurement comparison test. • The digital DBH measurement has been supported by LiDAR platforms. [ABSTRACT FROM AUTHOR]

• Proposition of an accurate and fast method for glaucoma screening based on the vessel displacement. • Achievement of higher performance detection with smartphone captured fundus images. • Implementation of the method into a smartphone to provide a mobile aided screening system for glaucoma. The glaucoma is an eye disease that causes blindness when it progresses in an advanced stage. Early glaucoma diagnosis is essential to prevent the vision loss. However, early detection is not covered due to the lack of ophthalmologists and the limited accessibility to retinal image capture devices. In this paper, we present an automated method for glaucoma screening dedicated for Smartphone Captured Fundus Images (SCFIs). The implementation of the method into a smartphone associated to an optical lens for retina capturing leads to a mobile aided screening system for glaucoma. The challenge consists in insuring higher performance detection despite the moderate quality of SCFIs, with a reduced execution time to be adequate for the clinical use. The main idea consists in deducing glaucoma based on the vessel displacement inside the Optic Disk (OD), where the vessel tree remains sufficiently modeled on SCFIs. Within this objective, our major contribution consists in proposing: (1) a robust processing for locating vessel centroids in order to adequately model the vessel distribution, and (2) a feature vector that relevantly reflect two main glaucoma biomarkers in terms of vessel displacement. Furthermore, all processing steps are carefully chosen based on lower complexity, to be suitable for fast clinical screening. A first evaluation of our method is performed using the two public DRISHTI-DB and DRIONS-DB databases, where 99% and 95% accuracy, 96.77% and 97,5% specificity and 100% and 95% sensitivity are respectively achieved. Thereafter, the method is evaluated using two fundus image databases respectively captured through a smartphone and retinograph for the same persons. We achieve 100% accuracy using both databases which assesses the robustness of our method. In addition, the detection is performed on 0.027 and 0.029 second when executed respectively on the Samsung-M51 on the Samsung-A70 smartphone devices. Our proposed smartphone app provides a cost-effective and widely accessible mobile platform for early screening of glaucoma in remote clinics or areas with limited access to fundus cameras and ophthalmologists. [ABSTRACT FROM AUTHOR]

• First work optimizes stereo rectification and stereo matching jointly for stereo vision system • An end-to-end network enables online self-rectification and self-supervised disparity prediction simultaneously • Rectification subnetwork can be easily combined with various existing stereo networks Stereo rectification and stereo matching are two critical components for the practical application of stereo vision systems. Previous studies treat them as two individual issues. For stereo rectification, various traditional algorithms are proposed to estimate homography transformations, but the performance and the efficiency are unsatisfactory for real-time deployment. For stereo matching, disparity accuracy has been largely improved by learning based methods. However, the input data of all previous stereo networks are assumed to be a pair of offline pre-rectified images, making them invalidate for accurate matching when the stereo vision system suffers from mechanical misalignment due to external collisions or temperature variations. In this paper, we optimize these two components jointly and propose an end-to-end learning framework to achieve online self-rectification and self-supervised disparity prediction simultaneously. The overall network contains two cascaded subnetworks which enable stereo rectification and stereo matching sequentially for a pair of unrectified images. The experimental results are evaluated on both publicly available datasets and realistic scenarios. Evaluation results demonstrate that, the proposed network produces state-of-the-art results for self-rectification in terms of computation accuracy and speed, and also produces competitive disparity results with previous self-supervised methods. Therefore, the proposed design provides a more practical and efficient solution for stereo vision systems deployed on mobile platforms. [ABSTRACT FROM AUTHOR]

The ionosphere is a region of plasma in altitudes extending up to 1000 km. Over low latitudes, steep depletions in the ionospheric density, commonly referred to as equatorial plasma bubbles, are generated after sunset as a result of plasma instabilities. Large variations in the index of refraction associated with these plasma bubbles affect the amplitude and phase of trans -ionopsheric radio signals used for communication, remote sensing and navigation, causing the so-called ionospheric scintillation. Therefore, better understanding of the ionospheric conditions is important for various applications. Unfortunately, real-time ionospheric monitoring systems have been limited, in most cases, by the cost and distribution of adequate sensors. In this work, we present and discuss an internet-of-things (IoT) system composed of a mobile application that acquires data from a network of low-cost scintillation monitors (ScintPi) capable of detecting the occurrence of ionospheric irregularities. The system, referred to as Ionik2, provides real-time information about ionospheric scintillation. A mobile app named ScintApp provides time-series of scintillation indices (S 4) and spatial distribution of scintillation using Google Maps. ScintApp also has post-processing capability allowing database queries. Finally, ScintApp is based on a native mobile smartphone application for Android operating systems. Here, we present initial results obtained with an interim prototype distribution of ScintPi monitors. We compare the information provided by ScintApp with observations made by independent instrumentation that have been widely used for ionospheric studies but do not provide real-time data. The results proof the concept of a system capable of providing realt-time information about scintillation events associated with equatorial plasma bubbles. [ABSTRACT FROM AUTHOR]

The authors have proposed an active text system (A-txt), which is a next-generation electronic teaching material that can make general books digitally more extensible with a general-purpose mobile terminal using augmented reality (AR). A-txt content is created by software called Contents Maker (C-mkr). This paper discusses the development of C-mkr for mobile terminals and this development can realize new learning methods using it by students. A-txt is our original system that can easily add and show digital contents by using figures and sentences written on papers as augmented reality (AR) markers. Since Unity is used for the development of A-txt, users can use it regardless of the OS type of the mobile terminal. C-mkr used to need PCs exclusively so far, but now that we have developed an application for mobile terminals, it is possible to create contents on smartphones and tablet computers owned by every user. Along with that, A-txt itself has undergone various improvements. In fact, the A-txt system cannot be used by anyone at present because it is operated by an intra server, but we considered how to solve the problem by reconstructing the server using cloud type. With the above development, users can easily create and upload content anytime and anywhere. We are planning to use this system for students to make textbooks into reference books by themselves. This method is named "Self-decoration (Sel-Deco)", and its effectiveness will be verified in the future. [ABSTRACT FROM AUTHOR]

Android has stood at a predominant position in mobile operating systems for many years. However, its popularity and openness make it a desirable target of malicious attackers. There is an increasing need for mobile malware detection. Existing analysis methods fall into two categories, i.e., static analysis and dynamic analysis. The dynamic analysis is more effective and timely than the static one, but it incurs a high computational overhead, thus cannot be deployed in resource-constrained mobile devices. Existing studies solve this issue by outsourcing malware detection to the cloud. However, the privacy of mobile app runtime data uploaded to the cloud is not well preserved during both detection model training and malware detection. Numerous efforts have been made to preserve privacy with cryptography, which suffers from high computational overhead and low flexibility. To address these issues, in this paper, we propose an Intel SGX-empowered mobile malware detection scheme called EPMDroid. We also design a probabilistic data structure based on cuckoo filters, named CuckooTable, to effectively fuse features for detection and achieve high space efficiency. We conduct both theoretical analysis and real-world data based tests on EPMDroid performance. Experimental results show that EPMDroid can speed up malware detection by up to 43.8 times and save memory space by up to 3.7 times with the same accuracy, as compared to a baseline method. • A privacy-preserving malware detection scheme based on Intel SGX. • An efficient way to compress runtime app features for malware detection. • Theoretical analysis on security, privacy, computation complexity and space overhead. • A prototype to evaluate effectiveness, efficiency, scalability and memory cost. [ABSTRACT FROM AUTHOR]

Free-space detection is considered as one of the most important tasks in intelligent vehicle, which remains the essential requirement for obstacle detection and path planning. As a part of Internet of Things, vehicle-based device produces a large amount of data requiring to be processed in real-time. Therefore, this study proposes a fast free-space detection system with a mobile platform based stereo vision. The current system processes the image-based perception signal in terminal equipment, which avoids lots of data transmissions between cloud and vehicle. In terms of flexibility and robustness, a fast spare disparity matching algorithm is suggested to be real-timely processed in a low-power mobile platform. Based on the spare disparity map, the current work improves the u-disparity space algorithm as the u-log-disparity space with the aim to detect the free-space for significantly lowering the running time. Besides, we also provide a complete system design including hardware and software. The experiments demonstrate that our system is precise and robust under complex real-time driving environment. [ABSTRACT FROM AUTHOR]

• Trellis network data collection platform enables name disambiguation. • Trellis network data collection platform enables multiple language interviews. • Trellis report allows for real-time monitoring of data collection. • Trellis network data collection platform can be used offline in remote areas. Trellis is a mobile platform created by the Human Nature Lab at the Yale Institute for Network Science to collect high-quality, location-aware, off-line/online, multi-lingual, multi-relational social network and behavior data in hard-to-reach communities. Respondents use Trellis to identify their social contacts by name and photograph, a procedure especially useful in low-literacy populations or in contexts where names may be similar or confusing. We use social network data collected from 1,969 adult respondents in two villages in Kenya to demonstrate Trellis ' ability to provide unprecedented metadata to monitor and report on the data collection process including artifactual variability based on surveyors, time of day, or location. [ABSTRACT FROM AUTHOR]

Android, as the most prevalent mobile operating system (OS) in recent years, has been widely applied in various cell phones, tablets, and embedded devices, greatly facilitating people's lives. However, Android malware is also emerging, which significantly endangers people's information security. The current Android malware detection systems are often suffering from cumbersome structures and massive computational resources, which seriously limits their direct deployment on mobile devices. We design a lightweight Android malware detection system named MCADS, which consists of a two-layer structure. At the first layer, we use an augmented Multilayer Perceptron (MLP) for the preliminary analysis of malware. At the second layer, we propose a new lightweight variant of Convolutional Neural Network (CNN) to further analyze the Apps that cannot be accurately identified in the first layer. Finally, a careful experimental investigation has been conducted. The proposed method achieves an accuracy of 98.12%, surpassing that of the compared methods. The promising results demonstrate the potential of MCADS as a practical adjunctive solution for detecting malware, complementing existing complex detection methods. • A lightweight Android malware detection system MCADS is proposed. • A novel variant of CNN is proposed to learn more distinguishing features. • MCADS shows its satisfactory performance on malware detection. [ABSTRACT FROM AUTHOR]

This paper presents a mobile supernumerary robotic approach to physical assistance in human–robot conjoined actions. The study starts with the description of the SUPER-MAN concept. The idea is to develop and utilize mobile collaborative systems that can follow human loco-manipulation commands to perform industrial tasks through three main components: (i) an admittance-type interface, (ii) a human–robot interaction controller and (iii) a supernumerary robotic body. Next, we present two possible implementations within the framework — from theoretical and hardware perspectives. The first system is called MOCA-MAN, and is composed of a redundant torque-controlled robotic arm and an omni-directional mobile platform. The second one is called Kairos-MAN, formed by a high-payload 6-DoF velocity-controlled robotic arm and an omni-directional mobile platform. The systems share the same admittance interface, through which user wrenches are translated to loco-manipulation commands, generated by whole-body controllers of each system. Besides, a thorough user-study with multiple and cross-gender subjects is presented to reveal the quantitative performance of the two systems in effort demanding and dexterous tasks. Moreover, we provide qualitative results from the NASA-TLX questionnaire to demonstrate the SUPER-MAN approach's potential and its acceptability from the users' viewpoint. [Display omitted] • Extension of the MOCA-MAN concept into the unified SUPER-MAN framework. • Evaluation of the framework through multiple experiments using two specific robotic platforms: MOCA and Kairos. • A usability study with 12 human subjects performing industrial-like tasks with and without robotic assistance. • Demonstration of the SUPER-MAN's effectiveness for both interaction and load-handling tasks based on both objective and subjective analysis. • SUPER-MAN allows for robotic assistance in conjoined loco-manipulation tasks without constraining user mobility. [ABSTRACT FROM AUTHOR]

This study presents a 3D object detection technology for mobile platforms and its application. Rather than an innovative high-performance model, we proposed a "useable" model for the robot industry at the current technology stage by combining various techniques. To reduce computation time, a 2D region proposal was obtained using a RGB image-based CNN model. By applying the DBSCAN clustering technique to the point cloud corresponding to the 2D region proposal, a method of obtaining a 3D region proposal was proposed. This allowed for 3D object detection using an RGB image dataset, which has been widely researched, while reducing the computation load to a level suitable for use in mobile robots. Furthermore, the 3D object detection was integrated into a ROS 2-based mobile platform, which was used to perform pedestrian-safe avoidance tasks and elevator button operation tasks. The performance was confirmed through experiments. [ABSTRACT FROM AUTHOR]

Android OS is a widely-used platform for mobile devices. However, with the increasing number of Android applications and ongoing advancements in application development, there is a need for flexible and scalable malware detection methods that can address the challenges posed by big data. Recently, researchers have developed methods based on complex network analysis that aim to reduce the complexity and enhance the scalability of malware detection. These methods have shown high accuracy in identifying Android malware. Our proposed method involves generating two weighted graphs that depict the relationships between applications in benign and malware states, respectively, by extracting the functions of each application. Network-analysis-based features are then extracted from the graphs and combined with static application features to distinguish malware applications from benign ones. Our approach demonstrated an increase in accuracy, achieving 99% and 98% accuracy on the DataMD and IntDroid datasets, respectively. We further demonstrate our proposed method's superiority against state-of-the-art approaches. • Generating two label-homogeneous application networks. • Utilizing static analysis and bipartite projection to create application network. • Analyzing application networks using centrality measures. • Optimizing networks by weighting and edge removal process. • Identifying the distinguishing centrality measures for classification. [ABSTRACT FROM AUTHOR]

• A novel FEM-DEM coupling model is developed to study the interaction between the small wheeled mobile platform tire and forest soil. • The coupling model are accurately established in ABAQUS-PFC3D. • The accuracy of the model was verified by the soil-bin test. • The model can present the force evolution of forest soil and the stress-strain distribution of the tire when the tire is rolling. Due to forest soil environment being short of structured terrain, research of tire-soil interaction is critical to enhance the performance for small wheeled mobile platform in forest. A novel model coupled finite element method (FEM) and discrete element method (DEM), which can be used to investigate the interaction behavior between the small wheeled mobile platform tire and forest soil, was proposed in this paper. In particular, the tire model based on rubber parameters that were obtained by uniaxial tensile tests is established in ABAQUS. The mechanical parameters of the soil in forest were obtained by the standard of geotechnical test and the triaxial compression test. The soil model was established in PFC3D. Significantly, the novel tire-soil interaction model based on the coupling ABAQUS and PFC3D was proposed accurately. The drawbar pull, the sinkage and the soil vertical stress were obtained through the proposed tire-soil interaction model. Meanwhile, soil-bin tests for tire-soil interaction were established. The drawbar pull, the sinkage and the soil vertical stress were obtained in soil-bin tests, which were consistent with the results from the proposed tire-soil interaction model. The results validated the effectiveness of the coupling method and the accuracy of the proposed tire-soil interaction model. Moreover, the flow state of soil particles was described by the proposed tire-soil interaction model, which analyzed the forces evolution in the area where the tire was in contact with the soil. [ABSTRACT FROM AUTHOR]

Recovering autonomous underwater vehicles (AUVs) by a mobile platform is a complex challenge. Traditional docking stations require strict pose deviation from the underwater vehicle. To overcome this issue, we propose a novel solution: an in-situ fluid-driven soft dock. This system comprises three soft robotic manipulators that possess guiding, capturing, and securing functionalities, respectively. We present the design, fabrication, and control methods for each manipulator considering the requirements of underwater docking operations. The theoretically allowable docking pose deviation range during AUV docking is analyzed. Additionally, the required force of soft grippers was evaluated through simulation and equivalent experimental tests. To enable dynamic recovery of AUVs while the soft robotic manipulators remain mobile on the experimental platform, we introduce a hydraulic control method based on attitude and pressure feedback. The test results indicate that the designed soft manipulators can operate and maintain good sealing performance under an external pressure of no less than 11 MPa. Moreover, the soft dock successfully recovered and secured AUVs of two different diameters in 20 dynamic tests, achieving a 90% success rate with a maximum AUV velocity of 1.6 m/s. • We propose an underwater soft dock that can dynamically guide, capture, and secure AUVs of different diameters without modifying their shape. • We design the sealing structure and manufacturing method for the soft dock that is capable of sealing under high pressure while maintaining their bending capability. • We design an in-situ hydraulic control method, which achieves more flexible relative pose and velocity tolerance for AUVs. [ABSTRACT FROM AUTHOR]

Teleoperation technology has become a feasible solution for the mobile manipulator to carry out complex tasks in remote environments, with its advantages of mobility and manipulability. However, due to the high redundancy of the mobile manipulator, its application in the field of teleoperation inevitably suffers from the problem of heterogeneity. This paper proposed an automatic-switching-based teleoperation framework with asymmetrical mapping and force feedback. Namely, special coefficients are designed to automatically switch the motion states of the remote robot, so that the traditional manual-based switching strategy can be replaced. Based on these coefficients, the hybrid asymmetrical mapping including the position–velocity and position–position modes can be achieved, as well as the force feedback considering the switching between the remote mobile platform and the manipulator, and thereby accomplishing the automatic switching during the teleoperation of the mobile manipulator. The comparative experiments and user study were carried out on the teleoperation platform. The experimental results show that this proposed teleoperation framework can reduce the time needed to complete the tasks and decrease the decision-making pressure of the operator, thus demonstrating the feasibility of the proposed framework. [ABSTRACT FROM AUTHOR]

• An interactive simulation is used as a tool for logistics and maintenance processes analysis. • It makes it possible to operate virtual maintenance equipment like cranes, virtual logistics equipment like mobile platforms for transport and a manikin representing a maintenance worker. • Features for the analysis of the operations such as clash detection, distance measures and custom defined cameras. • An agile analysis of the planned procedure, clashes and assessment of the design of equipment is presented. Pre-configured virtual reality (VR) simulations of the logistics and maintenance processes have proven to be useful for identifying potential design issues as well as planning operations during an early design phase of facility. But VR simulations can also be used to deeply explore the feasibility of these procedures in a more interactive manner, so that we can identify potential risks and difficulty levels from early stages and study different maintenance strategies to assist the maintenance worker during these procedures. This article presents a framework to design and validate logistics and maintenance procedures in complex facilities, such as the International Fusion Materials Irradiation Facility DEMO Oriented Neutron Source (IFMIF-DONES). Our framework begins with a preparatory phase where essential information about the procedures and Computer-Aided Design (CAD) models is compiled into a comprehensive Virtualization Task Document (VTD). Differently from previous work, this VTD allows representation of parallel tasks. We implement the interactive version of the virtual environment, where the different maintenance and logistics equipment, as well as a virtual maintenance worker is controlled by the user (the person executing the interactive simulation). We have validated this interactive framework with two simulations for the installation process of the Superconducting Radio Frequency Linear accelerator (SRF Linac) modules in IFMIF-DONES. In one simulation (the automatic one), the procedures are reproduced as they are planned, while in the second simulation (the interactive one) the user freely controls the movements of the moving parts of the crane, grab and release plant equipment, move platforms, etc. Based on our simulations, the interactive version allows easier detection of potential points of collisions as well as more precise assessment of the difficulty of the tasks to be performed. [ABSTRACT FROM AUTHOR]

The introduction of alternative messaging platforms on mobile devices have not been able to phase off Short Messaging Service (SMS) as the most widely used means of textual communication. Over the decades, SMS has remained the most responsive way of communication that has been embraced by individuals and organizations in passing information across to their intended recipients. However, hackers have been employing this tool as a way to deceive the gullible into divulging sensitive information about their financial dealings as well as gain access to their mobile devices. A lot of innocent but ignorant individuals have become victims of this smishing acts and have lost huge sum of money as a result. Though existing research have extensively proposed and implemented different techniques for detecting and separating spam SMS from ham SMS, a mobile application that uses a rule-based RIPPER and C4.5 classifiers in detecting smishing acts is proposed. The rule-based classifiers were used to formulate rules used in detecting and separating spam from ham while a mobile application was developed to use the rule-based model in smishing detection. An Application Programming Interface (API) was designed to intercept incoming SMS, forward them to the rule-based model for analysis and then relay the results to the user via the developed mobile application. The user then decides to either retain or discard the SMS. [ABSTRACT FROM AUTHOR]

A key element for water supply systems is the design of the water intake components. Mobile floating platforms (barges) are helpful when the hydraulic system displays substantial variations in water levels. This study presents the hydrological considerations that should be considered for the design of the barge's pipeline runway. The analysis takes into consideration the maximum and minimum water levels measured at the location. The study was carried out at the Magdalena River -Plato (Colombia) station, finding variations in water levels of between 12.3 m and 16.1 m for return periods of 25 and 100 years, respectively. This information is helpful for designers and consultants in order to design an appropriate barge pipeline runway. [ABSTRACT FROM AUTHOR]

Fuel cells are considered to be a promising system that is utilized in several applications and in various sectors. Particle image velocimetry is extremely practicable for the exploration of the flow field inside fuel cells and channels. This paper reviews fuel cell studies focusing on the particle image velocimetry technique in the open literature. In this regard, state-of-the-art and comparative evaluation have been investigated and are discussed. Additionally, challenges, opportunities and future direction have been studied in terms of fuel cell type, size, voltage value, current value, power output capacity, and CFD applications. It is concluded that the growing demand on fuel cells will increase system design, performance improvement and cost benefit efforts affected by the flow and design parameters and characteristics which are other important issues that could be covered using PIV methods in the future. Moreover, this review paper is expected to be a better guide for researchers, policy makers and technologists working on potential commercial applications of fuel cells in mobile and stationary platforms. • This work reviews fuel cell studies including the particle image velocimetry technique in the open literature. • The state of the art and comparative evaluation of the works done in the literature investigate and discuss in detail. • This paper aims to be a guideline for researchers and policymakers working on fuel cell technologies. [ABSTRACT FROM AUTHOR]

This paper is described on the improvement of the Active Textbook System (A-txt) and the consideration for Copyright Law when the A-txt is used. The A-txt is a next-generation electronic educational material system proposed by the authors that can digitally expand the general paper books with general-purpose terminals. This system is the original system that allows you to easily attach additional digital content to any location by using figures and sentences on paper as augmented reality (AR) markers. Initially, A-txt, which was developed for each type of mobile OS, is provided on a unified platform by using Unity, and it has become possible to concentrate budgets and human resources. This time, we have added new functions to make usability better and improved the screen display by modifying the source code. In addition, as a measure to use figures in books as AR markers without infringing copyright, we experimentally have found the minimum necessary range in which A-txt can be used without inconvenience. In the process, we also have found a method to increase the recognition rate of markers. [ABSTRACT FROM AUTHOR]

The widespread adoption and employment of hand-held devices is a well-known and academically acknowledged fact as digital pervasiveness and hardware availability has triggered off this massive and convenient trend of accessing and consuming online resources and services from anywhere at any time. In this paper we argue that five areas in the mobile learning platform and the computer networks that support the processes and environments, require particular attention and proper training of the people involved to ensure the soundness of all the security methods and best practices are maintained, along with continual maintenance and updating of systems and procedures in each of these five categories. The paper closes with numerous recommendations regarding security in a mobile learning environment. [ABSTRACT FROM AUTHOR]

Multi-robotic systems are used to solve many practical tasks in wide areas, including military surveillance, reconnaissance, rescue operations, warehousing, etc. Such systems can be represented as groups of intelligent robots capable of interacting with each other and jointly implementing various tasks. One of the problems in the development of such systems is the safe navigation of a group of robots. The restrictions imposed by the structural elements of its agents are determined to solve it. The article presents the structure of a multi-robotic system consisting of parallel and serial robots installed on mobile platforms. The parallel robot is made based on a tripod with the possibility of rotating the robot base about the horizontal axis. Determining the workspace boundaries of robots eliminates collisions between agents and external objects. The developed algorithms are based on deterministic methods for approximating the solutions set of nonlinear inequalities systems with restrictions in spaces of coordinates in the form of n-dimensional boxes. The relative positions of mobile platforms with manipulators, at which collisions are possible, are determined. [ABSTRACT FROM AUTHOR]

The growing number of mobile devices over the past few years brings a large amount of personal information, which needs to be properly protected. As a result, several mobile authentication methods have been developed. In particular, behavioural biometrics has become one of the most relevant methods due to its ability to extract the uniqueness of each subject in a secure, non-intrusive, and continuous way. This article presents SwipeFormer, a novel Transformer-based system for mobile subject authentication by means of swipe gestures in an unconstrained scenario (i.e., subjects could use their personal devices freely, without restrictions on the direction of swipe gestures or the position of the device). Our proposed system contains two modules: (i) a Transformer-based feature extractor, and (ii) a similarity computation module. Mobile data from the touchscreen and different background sensors (accelerometer and gyroscope) have been studied, including in the analysis both Android and iOS operating systems. A complete analysis of SwipeFormer is carried out using an in-house large-scale database acquired in unconstrained scenarios. In these operational conditions, SwipeFormer achieves Equal Error Rate (EER) values of 6.6% and 3.6% on Android and iOS respectively, outperforming the state of the art. In addition, we evaluate SwipeFormer on the popular publicly available databases Frank DB and HuMIdb, achieving EER values of 11.0% and 5.0% respectively, outperforming previous approaches under the same experimental setup. • Touchscreen biometrics can enhance mobile security, being robust and user-friendly. • We present SwipeFormer, a touchscreen biometric system based on Transformers. • Experimental analysis of mobile swipe biometrics in unconstrained scenarios. • We make our experimental framework available to the research community. [ABSTRACT FROM AUTHOR]

The increasing demand for quality, year-round food production in limited space has led to the widespread adoption of protected cropping. Effectively monitoring and maintaining crops within these facilities requires substantial labour and expertise. Traditional manual monitoring is labour intensive and time consuming. Therefore, non-destructive image-based techniques, particularly those utilising 3D structural data, have gained attention. We developed a stereo vision-based system to estimate the height of vertically supported tall plants in protected facilities, given plant height serves as a vital measure of crop growth. Our system uses a mobile platform with a top-angle view of a stereo vision depth camera for data acquisition and machine learning in its core for data analysis. First, we collected weekly RGB and depth (RGBD) streams from plant gutters in three glasshouse compartments with different light treatments. We used part of the RGB data collected to train and validate a deep learning segmentation model to detect plant tops and bases. Detected tops and bases of an image were then mapped to the generated 3D scene using the depth image of the same frame. Thresholds and 3D clustering are used respectively to remove background and eliminate outliers in top and base detection mapped to 3D space. Finally, the height of each plant was calculated using the cluster centres of the tops and bases of the plants. Manually measured heights of ten selected plants per environment were used to validate the height estimations. Similar growing patterns were observed between imaged and manually measured plant heights, which showed strong correlations of 0.87, 0.96, and 0.79 R 2 scores, respectively, under unfiltered ambient light, Smart Glass film, and shifted light. These promising results demonstrate the feasibility of our proposed method for a vertically supported capsicum crop in a commercial-scale protected crop facility. • A single RGBD camera unit with top angled view on mobile platform for height estimation of vertically support tall plants. • Linear regression to correct calibration error of collected depth images. • Machine learning modelling on RGB images for plant top and base identification and neighbouring for increased detection accuracy. • 2D to 3D mapping of segmentations and 3D clustering and threshold filtering for filtering detections of foreground plants and calculation of heights. • Usability of IR based stereo vision for crop monitoring under light diffusing roof, Smart film and Lleaf film. [ABSTRACT FROM AUTHOR]

• Fruit detections in 3D pear canopies have errors > 1.8 % larger than 2D canopies. • Accurate blush coverage estimates in pears can be obtained with a mobile platform. • Pear blush coverage at harvest can be classified with ≤ 2 % within-class errors. • Narrow fruiting walls produce relatively more fruit with greater colour coverage. • Narrow fruiting walls are best suited for orchard digitising and phenotyping. Increasing farm labour and input costs and the requirement for more orchard data are leading to rapid advances in technology to improve management systems in fruit production. The study aimed to (i) validate a sensorised platform to estimate fruit number, peel colour and blush coverage in pear orchards with different pear selections and tree architectures, (ii) establish relationships between fruit number, peel colour and canopy geometry features, and (iii) evaluate the platform for mapping and digitising orchard features. The study was carried out over two years in an experimental 'ANP-0131′ orchard and in one year in two commercial pear orchards ('ANP-0131′ and 'PremP009'). Predictions of fruit number and blush coverage were compared in traditional three-dimensional (3D) and modern high-density two-dimensional (2D) training systems. Overall, prediction errors for fruit number were < 6.5 % in all the training systems, but improved performance was achieved in vertical 2D configurations (% standard errors = 2.2 %). Fruit number and blush coverage per unit of leaf area were higher in 2D compared to 3D training systems. Blush coverage predictions in 'ANP-0131′ were reliable (R2 = 0.67, RMSE = 3.70 %). Accurate predictions of blush coverage classes were achieved by modifying sample variance. Fruit number and blush coverage were negatively affected by increasing canopy size. The platform proved useful for mapping and digitisation. Spatial heatmaps of orchard features provided a valuable visual aid to identify zones for priority interventions for peel colour enhancement. [ABSTRACT FROM AUTHOR]

The abuse of antibiotics has become a global public safety issue, leading to the development of antimicrobial resistance (AMR). The development of antimicrobial susceptibility testing (AST) is crucial in reducing the growth of AMR. However, traditional AST methods are time-consuming (e.g., 24–72 h), labor-intensive, and costly. Here, we propose a controlled-diffusion centrifugal microfluidic platform (CCM) for rapid AST to obtain highly precise minimum inhibitory concentration (MIC) values. Antibiotic concentration gradients are generated by controlled moving and diffusing of antibiotic and buffer solution along the main microchannel within 3 min. The solution and bacterial suspension are then injected into the outermost reaction chamber by simple centrifugation. The CCM successfully determined the MIC for three commonly used antibiotics in clinical settings within 4–9 h. To further enhance practicality, reduce costs, and meet point-of-care testing demands, we have developed an integrated mobile detection platform for automated MIC value acquisition. The proposed CCM is a simple, low-cost, and portable method for rapid AST with broad clinical and in vitro applications. [Display omitted] • A controlled-diffusion centrifugal microfluidic for rapid AST was successfully proposed. • Antibiotic concentration gradients generated by combined diffusion and centrifugation. • An integrated mobile detection platform to automatically obtain MIC values. [ABSTRACT FROM AUTHOR]

• IoT model-based cloud framework is proposed for COVID-19 prediction. • A new deep COVID-19 model is proposed to detect infected cases. • A complex COVID-19 dataset images are used from different resources. • An end-to-end architecture is designed for a whole platform composed of frontend and backend. • Mobile App is developed to capture the images and pass these images to a centralized backend system. Due to the rapid spread of COVID-19, an urgent need arose for a quick and accurate diagnosis approach. The well-known RT-PCR test is often unavailable and too costly for many suspected cases. In contrast, the chest X-ray scan proves to be a robust and efficient tool for promptly identifying the virus, using various cost-effective tests. This study proposes a hybrid intelligent model for identifying COVID-19 patients based on their chest X-ray scans. The proposed model consists of five phases. Firstly, the X-ray images are preprocessed using a median filter to enhance and remove noise. Secondly, robust invariant and high-level engineering features are extracted using five different feature extraction methods, namely (speeded up robust features (SURF), grey-level co-occurrence matrix (GLCM), histogram of oriented gradients (HoG), segmentation-based fractal texture analysis (SFTA), and local binary pattern (LBP) to help in rapid diagnosis. Then these features are fused to complement the gap of each other and to achieve the best performance. Thirdly, a deep convolutional neural network (DCNN) is used to classify the chest X-ray scans of infected COVID-19 patients. Then, the proposed model is compared with different machine learning techniques under different quality measures. Fourthly, an IoT platform composed of a mobile client application and a backend system is designed. The mobile client application captures the content from the patient side, handles these captured images, and prepares them for rapid sending to the backend side for further processing. The backend system receives the patient images from the client side and applies the proposed model to diagnose the COVID-19 patients. Finally, a cloud-based design for the platform utilizes the modern AWS services characterized by availability, elasticity, coverage, configurability, and reliability. The results show that the proposed model has a good accuracy of around (99.31%) and outperforms the other models. Therefore, the proposed model could be used for real-time automatic early recognition of COVID-19 cases. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) has better operation efficiency in fault diagnosis. However, the recognition accuracy of ELM algorithm is actually affected by the activation function. Moreover, most of the testing dataset are coming from high precision and expensive sensors. In this paper, raw data are collected by a low-cost attitude sensor, which is installed on the mobile platform of a delta 3D printer. A doublet activation function is proposed to improve the performance of ELM, named doublet ELM (DELM). The proposed method is evaluated using experimental data collected from the 3D printer, and its advantages are demonstrated by comparing with other activation functions. The experimental results indicate that the proposed method leads to the highest accuracy in different hidden nodes and the testing classification rate achieves 93% and 96% using only 8.33% of the dataset for model training, for R75 and R90 sub-datasets, respectively. Moreover, compared with peer methods, such as random forest, echo state network, and so on, the results show that the present DELM exhibits the best performance in small-sample and improves the accuracy of the 3D printer fault diagnosis. • An attitude sensor was mounted on the moving platform to monitor printer conditions. • A doublet ELM activation function is proposed based on the attitude data. • The proposed method yields the highest classification rates in the small-sample case. [ABSTRACT FROM AUTHOR]

It has recently been discovered that large companies and nations "observe" their customers and citizens, disregarding any remaining moral and technological lines, being able to listen to telephone conversations and monitoring communications, through powerful monitoring and surveillance programs. Elsewhere on the planet, nations in turmoil or wrapped in a cloak of censorship persecute their citizens, controlling them by denying them access to the free Web without the threat of repercussions that threatens their dignity. To support the present research, an analysis of platforms that allow anonymous and secure browsing and a study of technologies and programs with potential privacy breach and computer intrusion were performed. The main objective of this work was to analyse the computer monitoring and surveillance technologies, identifying the available tools, trying to find potential solutions, developing and providing a methodology that enhances any desktop, server or mobile operating system, with characteristics that combat the exposed in this summary. [ABSTRACT FROM AUTHOR]

Sifilis is one of the most common sexually transmitted infections (STI) in the world, with millions infected every year, despite efficient prevention and treatment options. In 2016, in Brazil, syphilis became a healthcare problem. The National Program for the Improvement of Access and Quality of Primary Care (PMAQ-AB) aims to amplify access and improve basic attention by providing access to public data. This study seeks to develop a mobile application that helps Syphilis Attention Networks to map data about the infection and therefore counter its proliferation. In this work, it was developed a mobile platform, with Flutter framework, that will extract data from the PMAQAB's platform regarding syphilis specialized health units. After that, Google tools are used to provide directions. According to that, it is possible to assume that Brazil has failed in the fight against Syphilis and needs new projects to improve its efficiency against the bacteria dissemination. As a result, this application can assist the mapping of syphilis attention networks and also become a module for a case management system, being able to map a variety of diseases other than Syphilis. [ABSTRACT FROM AUTHOR]

Learning history means to learn what caused the world around us to become the way it is right now. For decades, historical events were recorded and taught to younger generations to learn from them. However, most students found that learning history is boring because they could not feel or understand the moment of those historical events. This paper aims to investigate how a game-based learning approach influences the achievement and motivation of historical learning through a mobile learning environment. We propose game-based historical learning using the role-playing game on a mobile platform. The implementation is based on the history of the first army general in Indonesia, General Sudirman. The game was tested to 63 Junior High School students in Jakarta. Based on the evaluation, using the game can increase student learning motivation and learning achievement. [ABSTRACT FROM AUTHOR]