Single Mobile Phone Research Articles

CAN SMART PHONE VIDEO-BASED POSE ESTIMATION ACCURATELY CLASSIFY LOW BACK PHYSIOTHERAPY EXERCISES VIA MACHINE LEARNING?

Access to health care, including physiotherapy, is increasingly occurring through virtual formats. At-home adherence to physical therapy programs is often poor and few tools exist to objectively measure low back physiotherapy exercise participation without the direct supervision of a medical professional. The aim of this study was to develop and evaluate the potential for performing automatic, unsupervised video-based monitoring of at-home low back physiotherapy exercises using a single mobile phone camera.24 healthy adult subjects performed seven exercises based on the McKenzie low back physiotherapy program while being filmed with two smartphone cameras. Joint locations were automatically extracted using an open-source pose estimation framework. Engineered features were extracted from the joint location time series and used to train a support vector machine classifier (SVC). A convolutional neural network (CNN) was trained directly on the joint location time series data to classify exercises based on a recording from a single camera. The models were evaluated using a 5-fold cross validation approach, stratified by subject, with the class-balanced accuracy used as the performance metric.Optimal performance was achieved when using a total of 12 pose estimation landmarks from the upper and lower body, with the SVC model achieving a classification accuracy of 96±4% and the CNN model an accuracy of 97±2%.This study demonstrates the feasibility of using a smartphone camera and a supervised machine learning model to effectively assess at-home low back physiotherapy adherence. This approach could provide a low-cost, scalable method for tracking adherence to physical therapy exercise programs in a variety of settings.

Computer vision-based evaluation of dimensional accuracy for MEAM in new product development

Evaluation of dimensional accuracy for parts is a key component of quality assurance for material extrusion based additive manufacturing (MEAM) in new product development. Computer vision-based frameworks are currently the most suitable methods for MEAM dimensional accuracy evaluation due to their non-contact measurement characteristic, rapidity and high accuracy. However, the previous computer vision-based frameworks in MEAM had the limitations of high camera cost and strict installation requirements. To address this issue, a cheap and accurate computer vision-based framework is proposed for MEAM based on a single mobile phone camera without strict installation requirements. First, camera is calibrated to reduce the influence of lens distortion. Then, dimensions are measured through projective transformation and scaling. To find the best calibration pattern, three calibration pattern named checkerboard, symmetric circle and asymmetric circle are investigated. The proposed framework is validated experimentally through printing tests of a cube and a cylinder fabricated by a fused deposition modeling (FDM) 3D printer. The result shows that camera calibration using asymmetric circular grid pattern has the highest accuracy and the proposed computer vision framework is validated as the maximum relative error is less than 1%.

Network of Games: An Ecology of Games Informing Integral and Inclusive City Developments

This article analyzes possibilities for connecting individual city games for building a network of games working together. City gaming works along with the understanding that cities are self-organizing systems, influenced by multiple bottom-up and top-down actors with varying interests and powers. Affordable housing, climate adaptation, or area development are examples of urgent urban challenges city games typically focus on. The assumption is that if these specialized games could be linked, then a large game infrastructure built as a modular system, can offer various game combinations responding to urban challenges in an integral and holistic way. To test a working game network, city games, models, and digital apps have been linked through their shared datasets as well as game interfaces. Two city experiments have been conducted in two Dutch cities—Amsterdam and Breda—which enabled the testing to function as “constructive design research.” In Amsterdam (Klimaatspel) two separate city games were connected through their datasets, while in Breda (Play the Koepel) datasets and interfaces merged to create a new game. Used data models are the Energy Transition Model developed by Quintel and the urban plan cost simulator software of Urban Reality. Used game interfaces (digital and analog) include the Typeform, the Network of Games app, the Urban Reality simulator, and the Play the City table-top game format. The testing considered two different approaches for a potential game network. The first option assumes an all-encompassing digital app, reformatting and involving various games and models in a single interface. The second option is an open approach that looks to link custom-made games with existing interfaces. The second option allows both simultaneous and sequential linking. Two experiments utilizing sequential and simultaneous integration of diverse digital tools suggest that a collection of interfaces connecting to each other throughout the entire process from a digital poll to an app, a simulator or a webinar, or analog game sessions is more effective than a single mobile phone app for all potential game interactions. Considering city games as an ecology of city tools that can be linked to one another becomes through this study a concrete goal to reach. Through combining specialized games, addressing complex city challenges becomes possible. This step enables a more effective participation environment for diverse experts and non-experts.

Plant trait measurement in 3D for growth monitoring

BackgroundThere is a demand for non-destructive systems in plant phenotyping which could precisely measure plant traits for growth monitoring. In this study, the growth of chilli plants (Capsicum annum L.) was monitored in outdoor conditions. A non-destructive solution is proposed for growth monitoring in 3D using a single mobile phone camera based on a structure from motion algorithm. A method to measure leaf length and leaf width when the leaf is curled is also proposed. Various plant traits such as number of leaves, stem height, leaf length, and leaf width were measured from the reconstructed and segmented 3D models at different plant growth stages.ResultsThe accuracy of the proposed system is measured by comparing the values derived from the 3D plant model with manual measurements. The results demonstrate that the proposed system has potential to non-destructively monitor plant growth in outdoor conditions with high precision, when compared to the state-of-the-art systems.ConclusionsIn conclusion, this study demonstrated that the methods proposed to calculate plant traits can monitor plant growth in outdoor conditions.

Camera-based Hand Tracking using a Mirror-based Multi-view Setup.

Current clinical practice of measuring hand joint range of motion relies on a goniometer as it is inexpensive, portable, and easy to use, but it can only measure the static angle of a single joint at a time. To measure dynamic hand motion, a camera-based system that can perform markerless hand pose estimation is attractive, as the system is ubiquitous, low-cost, and non-contact. However, camera-based systems require line-of-sight, and tracking accuracy degrades when the joint is occluded from the camera view. Thus, we propose a multi-view setup using a readily available color camera from a single mobile phone, and plane mirrors to create multiple views of the hand. This setup eliminates the complexity of synchronizing multiple cameras and reduce the issue of occlusion. Experimental results show that the multi-view setup could help to reduce the error in measuring the flexion angle of finger joints. Dynamic hand pose estimation with object interaction is also demonstrated.

Non-destructive and cost-effective 3D plant growth monitoring system in outdoor conditions

There is a high demand for non-destructive systems in plant phenotyping which should precisely calculate plant growth and structure parameters. In this study, the growth of chilli plants (Capsicum annum L) was monitored in outdoor conditions. We also proposed a cost-effective and non-destructive solution for reconstruction of plants in 3D using a single mobile phone camera based on a structure from motion algorithm. Various plant growth and structure parameters such as number of leaves, plant height, and leaf area were measured from the reconstructed 3D models at different plant growth periods. The accuracy of our proposed system is measured by comparing the values derived from the 3D plant model with manual measurements. The results demonstrate that the proposed system has potential to monitor plant growth precisely and non-destructively in outdoor conditions when compared with state-of-the-art systems.

May electromagnetic field exposure during pregnancy have a negative effect on anthropometric measurements of the newborn?

Purpose: This study was conducted to determine the effect of low frequency electromagnetic field (EMF) exposure due to electronic media device (EMD) during pregnancy on the anthropometric measurements of newborn.Materials and Methods: A questionnaire was administered among randomly selected women offering Gaziantep University, Faculty of Medicine’s Department of Pediatrics Outpatient Clinics for any reason between November 2017-May 2018. Four hundred women who have a child aged between 0-5 years old, completed the questionnaire about their pregnancy history. Results: A negative correlation was identified between maternal single mobile phone usage during pregnancy and newborn’s birth weight. Multiple mobile phone (more than mobile phone) usage during pregnancy was negatively correlated with the birth week, birth weight and birth length of the newborn. The head circumference of the newborn was negatively correlated with watching television (TV) and living close to a base station during pregnancy.Conclusion: Watching TV, mobile phone usage and living near a base station during pregnancy may cause negative effect on the anthropometric measurements of the newborn.

A learning-based classification of indoor noise type/position in an apartment building

This study presents a learning-based method as an indoor noise source type/position classification technique closely related to the interfloor noise problem causing serious conflict between South Korean neighbors. For this study, an indoor noise dataset recorded by a single mobile phone was collected on three floors of an apartment building. Using a convolutional neural networks based classifier, the data containing five source type labels and four position labels is trained and evaluated. In addition, unlabeled data that is not used in the model development is tested for robustness evaluation of our classification system.

Impact of Maternal Obesity and Mobile Phone Use on Fetal Cardiotocography Pattern.

BACKGROUND:The fetal heart rate (FHR) is a good marker of fetal well-being during labour. Cardiotocography is used to record the FHR and uterine contractions and can detect possible fetal hypoxia. Mobile phones use, and obesity is suggested to influence the FHR and cardiovascular development.AIM:The present study aimed to study the differences in FHR pattern between fetuses of obese vs non-obese groups when using a mobile phone.METHODS:We conducted a clinical trial to test the impact of mobile phone use on FHR using a single mobile phone with Specific Absorption Rate rating of 0.99 W/kg for 10 minutes. Data from this clinical trial were analysed to compare the FHR pattern between fetuses of obese women (exposed group) vs those of non-obese women (control group). The two study groups (obese vs non-obese) were compared regarding fourFHR patterns:baseline FHR, variability, acceleration and deceleration scores. Data were analysed by SPSS software version 23.0 using the independent-samples t-tests.RESULTS:Sixty-nine women were included in the final analysis (obese group: n = 22 and non-obese group: n = 47). Fetuses of the obese women had significantly higher baseline FHR and less FHR variability scores when compared with fetuses of the non-obese women (mean difference 2.9 and 3.18, respectively).CONCLUSION:Fetuses of obese women had abnormal FHR pattern compared with fetuses of non-obese women. The use of mobile phone slightly influenced the FHR variability score. These results highlight the importance of proper management of obesity in women within the childbearing period.

Indoor scene texturing based on single mobile phone images and 3D model fusion

ABSTRACTRealistic texture mapping and coherent up-to-date rendering is one of the most important issues in indoor 3-D modelling. However, existing texturing approaches are usually performed manually during the modelling process, and cannot accommodate changes in indoor environments occurring after the model was created, resulting in out-dated and misleading texture rendering. In this study, a structured learning-based texture mapping method is proposed for automatic mapping a single still photo from a mobile phone onto an already-constructed indoor 3-D model. The up-to-date texture is captured using a smart phone, and the indoor structural layout is extracted by incorporating per-pixel segmentation in the FCN algorithm and the line constraints into a structured learning algorithm. This enables real-time texture mapping according to parts of the model, based on the structural layout. Furthermore, the rough camera pose is estimated by pedestrian dead reckoning (PDR) and map information to determine where to map the texture. The experimental results presented in this paper demonstrate that our approach can achieve accurate fusion of 3-D triangular meshes with 2-D single images, achieving low-cost and automatic indoor texture updating. Based on this fusion approach, users can have a better experience in virtual indoor3-D applications.

Design of Smart Universal Remote using Mobile for Home Automation

Controlling Home Appliances remotely is a main part of automation. There is a great deal of inconvenience in controlling each digital home appliance with its own separate remote. In this paper we present an advanced universal remote which can control and regulate lights, fans and also any IR controlled Home appliance like TV, home theater, air conditioner etc. This paper gives the design on how to build this remote and how we can turn our smart phone into a true universal remote which will be both versatile and have The rapid growth in mobile communication system in present era is changing people's life and work style. Fast development of mobile technology has brought the world in our grasp. Functionalities of electronic gadgets like computer, IPod, camera etc. are now made available in a single mobile phone. Smart phones are already feature-perfect and can be made to communicate to any other devices in an ad-hoc network with connectivity options like Bluetooth and Wi-Fi. Most of the home appliances use Infrared based controlling systems. Therefore, a simple mobile phone cannot be used directly to control any such appliances. Some special hardware is required to turn a mobile phone into a universal remote capable of controlling the IR based home appliances. Automation of the surrounding environment of a modern human being allows increased work efficiency and comfort. There has been a significant development in the area of an individual's routine tasks and those that can be automated. So, many workers are trying to implement universal remote using smart mobile as a part of Home Automation System. Panth and Jivani (1) have developed a Home Automation System using mobile in Android platform. The system has been designed to automate 8 bit Bluetooth enabled micro controller, which controls lights and fans using on and off relay switches. But this system lacks the capability of controlling any IR controlled devices.

Planners, navigators, and pragmatists: collaborative wayfinding using a single mobile phone

Shared use of mobile devices is increasingly prevalent in both research prototypes and in practice, however, little is known as to how to support best this interaction paradigm. In this paper, we present a study examining how pairs share a single mobile phone during a collaborative wayfinding activity. We provide a classification of strategies, role relationships and phone interactions employed to conduct the wayfinding activities in our study. While acknowledging that the factors determining how the phone was shared are nuanced and intertwined, our results illustrate how differences in the mobile application's interface influenced shared use, wayfinding strategy and outcome.