Real-time Mobile Applications Research Articles

Fall Detection System based on iOS Smartphone Sensors

Activities of daily living (ADLs) are a crucial aspect of human life, especially in remote health monitoring and fall detection. As smartphones have become an integral part of our daily routines, with their ability to perform complex calculations, connect to the internet, and incorporate various sensors, researchers have been inspired to explore human activity recognition systems. This paper focuses on accelerometer and gyroscope data from iOS-based smartphones. We developed a data collection app to record fall types (e.g., Falling Right, Falling Left) and fall-like activities (e.g., Sitting Fast, Jumping). Volunteers carried smartphones naturally in their pockets during experiments, presenting a challenge of noise but enhancing user comfort. We applied different Machine Learning algorithms (Decision Trees, Random Forest, Logistic Regression, k-Nearest Neighbor, XGBoost, LightGBM, and Neural Networks) to analyze the collected dataset. In contrast to typical studies, our approach replicated real-world smartphone usage. The paper presents and analyzes promising results from the study. Furthermore, we implemented the trained model as a real-time mobile application for potential users. This research illustrates the potential of smartphones in fall detection and opens the way for user-friendly solutions in remote health monitoring.

Real-Time Inspection of Fire Safety Equipment using Computer Vision and Deep Learning

The number of accidental fires in buildings has been significantly increased in recent years in Saudi Arabia. Fire Safety Equipment (FSE) plays a crucial role in reducing fire risks. However, this equipment is prone to defects and requires periodic checks and maintenance. Fire safety inspectors are responsible for visual inspection of safety equipment and reporting defects. As the traditional approach of manually checking each piece of equipment can be time-consuming and inaccurate, this study aims to improve the inspection processes of safety equipment. Using computer vision and deep learning techniques, a detection model was trained to visually inspect fire extinguishers and identify defects. Fire extinguisher images were collected, annotated, and augmented to create a dataset of 7,633 images with 16,092 labeled instances. Then, experiments were carried out using YOLOv5, YOLOv7, YOLOv8, and RT-DETR. Pre-trained models were used for transfer learning. A comparative analysis was performed to evaluate these models in terms of accuracy, speed, and model size. The results of YOLOv5n, YOLOv7, YOLOv8n, YOLOv8m, and RT-DETR indicated satisfactory accuracy, ranging between 83.1% and 87.2%. YOLOv8n was chosen as the most suitable due to its fastest inference time of 2.7 ms, its highest mAP0.5 of 87.2%, and its compact model size, making it ideal for real-time mobile applications.

An embedded TensorFlow lite model for classification of chip images with respect to chip morphology depending on varying feed

AbstractTurning is one of the fundamental machining processes used to produce superior machine parts. It is critical to manage the machining conditions to maintain the desired properties of the final product. Chip morphology and chip control are crucial factors to be monitored. In particular, the selection of an appropriate feed has one of the most significant effects. On the other hand, machine learning is an advanced approach that is continuously evolving and helping many industries. Moreover, mobile applications with learning models have been deployed in the field, recently. Taking these motivations into account, in this study, we propose a practical mobile application that includes an embedded learning model to provide chip classification based on chip morphology. For this purpose, a dataset of chips with different morphological properties is obtained and manually labeled according to ISO 3685 standards by using 20 different feeds on AISI 4140 material. Accordingly, TensorFlow Lite is used to train a learning model, and the model is embedded into a real-time Android mobile application. Eventually, the final software is evaluated through experiments conducted on the dataset and in the field, respectively. According to the evaluation results, it can be stated that the learning model is able to predict chip morphology with a test accuracy of 85.4%. Moreover, the findings obtained from the real-time mobile application satisfy the success rate by practical usage. As a result, it can be concluded that such attempts can be utilized in the turning process to adjust the relevant feed conditions.

High efficiency lossless image recompression algorithm with asymmetric numeral systems for real-time mobile application

High efficiency lossless image recompression algorithm with asymmetric numeral systems for real-time mobile application

A prototype real-time mobile application for Thai banknote recognition to support visually impaired persons

A prototype real-time mobile application for Thai banknote recognition to support visually impaired persons

Dynamic Computation Offloading and Server Deployment for UAV-Enabled Multi-Access Edge Computing

Driven by the increasing demand of real-time mobile application processing, Multi-access Edge Computing (MEC) has been envisioned as a promising paradigm for pushing computational resources to network edges. In this paper, we investigate an MEC network enabled by Unmanned Aerial Vehicles (UAV), and consider both the multi-user computation offloading and edge server deployment to minimize the system-wide computation cost under dynamic environment, where users generate tasks according to time-varying probabilities. We decompose the minimization problem by formulating two stochastic games for multi-user computation offloading and edge server deployment respectively, and prove that each formulated stochastic game has at least one Nash Equilibrium (NE). Two learning algorithms are proposed to reach the NEs with polynomial-time computational complexities. We further incorporate these two algorithms into a chess-like asynchronous updating algorithm to solve the system-wide computation cost minimization problem. Finally, performance evaluations based on real-world data are conducted and analyzed, corroborating that the proposed algorithms can achieve efficient computation offloading coupled with proper server deployment under dynamic environment for multiple users and MEC servers.

Real-Time Student Feedback on the Surgical Learning Environment: Use of a Mobile Application

Improvements to the medical student surgical learning environment are limited by lack of granular data and recall bias on end-of-clerkship evaluations. The purpose of this study was to identify specific areas for intervention using a novel real-time mobile application. An application was designed to obtain real-time feedback from medical students regarding the learning environment on their surgical clerkship. Thematic analysis of student experiences was performed at the conclusion of 4 consecutive 12-week rotation blocks. Brigham and Women's Hospital/Harvard Medical School, Boston, Massachusetts. Fifty-four medical students at a single institution were asked to participate during their primary clerkship experience. Students submitted 365 responses over 48 weeks. Multiple themes emerged which were dichotomized into positive and negative emotions centered on specific student priorities. Approximately half of responses were associated with positive emotions (52.9%) and half with negative emotions (47.1%). Student priorities included the desire to feel included in the surgical team (resulting in feeling engaged/ignored), to have a positive relationship with members of the team (perceiving kind/rude interactions), to witness compassionate patient care (observing empathy/disrespect for patients), to have a well-planned surgical rotation (experiencing organization/disorganization within teams), and to feel that student well-being is prioritized (reporting opportunities/disregard for student wellness). A novel, user-friendly mobile application identified several areas to improve the experience and engagement of students on their surgery clerkship. Allowing clerkship directors and other educational leaders to collect longitudinal data in real time may allow for more targeted, timely improvements to the medical student surgical learning environment.

Distributed Resource Distribution and Offloading for Resource-Agnostic Microservices in Industrial IoT

Due to increase in real-time mobile applications and Industrial Internet-of-Things (IIoT) devices, the edge computing paradigm provides a systematic and eccentric platform for real-time Internet-of-Things applications. Though the paradigm provides an effective infrastructure, however the resource requirements of IIoT devices change radically with time, which is described as a resource-agnostic property. Therefore, the estimation of resource requirements of IIoT devices is a critical and resilient assignment. In addition, it requires an extensive amount of resources to process the data traffic flows and microservice offloading. Hence, we present RAISE, a novel resource-agnostic microservice offloading scheme for mobile IIoT devices. RAISE efficiently estimates the resource-agnostic nature of IIoT devices to maximize their resource utilization in the network. Based on the estimated resource requirement, we propose a resource-agnostic microservice offloading scheme to maximize the success rate. Extensive experiments show that RAISE provides better performance in terms of network throughput and Quality-of-Service (QoS) than the other existing methods, SDTO and DTOS, in terms of cost and reliability.

An Ant Colony Optimization Based Real-time Mobile Application for the Capacitated Vehicle Routing Problem

This work focuses on the capacitated vehicle routing problem. In this work, a real-time application is developed using online real-world data for mobile devices have IOS and Android operating systems. The fuzzy c-means clustering algorithm is used to group the demand points and the ant colony optimization algorithm is employed to determine the best route within each group. The customer demand points and distances between these points are obtained via Google Places and Google Directions APIs. The deviations in the route that result from the environmental and road conditions are identified immediately with the help of global positioning system technology allowing the route suggestions to be made. The developed application was evaluated on two datasets for testing. The test results showed that this real-time application can be used to find the optimum route for the capacitated vehicle routing problem and follow the route optimally.

A Novel Augmented Reality Mobile-Based Application for Biomechanical Measurement

Human posture and range of motion (ROM) measurements are important health indicators for identifying abnormalities from various disorders (e.g., scoliosis, musculoskeletal disorders, pain syndromes). A viable real-time mobile application for measuring body posture and ROM is currently lacking. To address this need, a novel Android smartphone augmented-reality-based application was developed and evaluated to enable real-time AprilTag2 marker measurement at the point of patient contact (Biomechanical Augmented Reality-Marker, BAR-M). Mobile app performance was evaluated on a body opponent bag (BOB) and 15 healthy participants by comparing smartphone app and Vicon motion analysis output (pelvis, shoulder, arm, torso angles). A Samsung Galaxy smartphone recorded live video, calculated AprilTag orientations and angle of “a line connecting the center of two tags”, and displayed outcomes in real time. For the BOB test, the absolute difference between Vicon and smartphone angles were 0.09° ± 0.05° for hip, 0.09° ± 0.06° for shoulder, and 0.69° for arm abduction. For the participant test, the absolute mean angle differences were 1.70° ± 0.23° for hip, 1.34° ± 0.27° for shoulder, and 11.18° ± 3.68° for arm abduction. Overall, the app obtained valid and reliable angle measurements for postural and ROM assessments using the smartphone’s front camera. Arm abduction results were affected by clothing movement that caused Vicon markers to move differently from AprilTag markers. Thus, with appropriate measurement methods, this real-time smartphone app is a viable tool to facilitate immediate clinical decision making based on human posture and ROM assessments.

Long Hands gesture recognition system: 2 step gesture recognition with machine learning and geometric shape analysis

A two stage real-time hand gesture recognition system is presented. It combines a machine learning trained detection step with a colour processing contour shape validation step. The detection step is done with either Adaboost Cascades or Support Vector Machines using HOG features. The system achieves a low false positive rate and a sufficient true positive rate necessary for robust real-time performance. It performs well compared to MobileNets a state of the art Neural Network for mobile real-time applications.

Development of smart application for house condition survey

Information based technologies and devices have proven their effectiveness in almost all the aspects of life. In near past it was hard to believe that, building systems and devices can be controlled through phone. However, IT has made it possible and today it is difficulty to think of a normal life without IT. Mobile application is another marvel of IT technology that allows people to carry all essential businesses through various types of mobile applications. Easiness, secure and resourceful are three factors that moves the masses of population to switch overuse of mobile technology. This study has been planned to develop a mobile application to conduct house condition survey. Methodology of study is planned on three core factors i.e. literature review, a data of building defects, and application development process. An inclusive database of low rise building defects (secondary data) was acquired from from earlier research of first author. The acquired secondary data from Chohan, A.H (2007) has surfaced the various types of building defects and their implications in low rise RCC construction/buildings. Data was validated through participation at site and 10 major segments of building defects were identified. Through review of literature research validity was established, application development process was accomplished and various IoT models and similar application were identified. In application development process, study has set the hierarchy of building defects, construed app. development process in domain of building surveying, validate the data, and developed a conceptual plan of smart survey. In addition, defined the development process of mobile application. In section 3, this research has explained the development of mobile application through three major steps i.e. classifying data, setting defects hierarchy and application development. Study has succeeded to surface a prototype framework of smart “Smart Condition Survey” (SCS) which can be practically used for development of real-time mobile application.

Applying Healthcare Failure Mode and Effect Analysis and the Development of a Real-Time Mobile Application for Modified Early Warning Score Notification to Improve Patient Safety During Hemodialysis.

ObjectivePatients undergoing hemodialysis are a high-risk population. This study identified possible errors by using a healthcare failure mode and effect analysis system to improve patient safety during hemodialysis.MethodsA multidisciplinary collaborative team, including physicians, nurses, information technicians, and medical staff members, was assembled. A flow diagram was used to indicate each process of the hemodialysis procedure from evaluating patient condition to transporting the patient back to the ward from the hemodialysis center. We scored all possible failure modes using the hazard scoring method as a combination of the occurrence frequency and severity. These potential failure modes were used to identify and evaluate possible risks by using a risk scoring matrix.ResultsThirty failure modes were identified across 6 processes, and their potential causes were explored. Four major strategies for addressing most of the failure modes were implemented: establishment of a mobile application that sends real-time automated alerts to the medical team based on the Modified Early Warning Score, design of a modified dialysis Identify-Situation-Background-Assessment-Recommendation checklist for dialysis, technician education and training, and internal auditing and monitoring of the implementation of the entire process. After the implementation of the strategies, the hazard scores of patients during dialysis dropped by 71.2% from 170 points to 49 points.ConclusionsThe healthcare failure mode and effect analysis system was useful for evaluating potential risk during dialysis. Using the mobile application reduced the occurrence of emergency resuscitation during hemodialysis and significantly improved the communication between medical personnel.

Personnel Monitoring System Using Mobile Application during the COVID 19

Corona virus disease(COVID-19) is a disease caused by the new corona virus called severe acute respiratory syndrome corona virus (SARS CoV-2). This disease has infected almost the entire world with a total of 47.5 million sufferers and a death total of 1.2 million people, WHO categorizes it as a global pandemic. Proven efforts to reduce the spread of COVID-19 include limiting physical interactions between humans or physical distance, maintaining the cleanliness of hands and limbs by washing with soap, and limiting outdoor activities by staying at home. Government and private agencies have required employees to report their health conditions via web pages. Real-time and accurate mobile applications can help prevent the spread of COVID-19. This research will develop a real-time monitoring and command system using mobile applications and cloud computing technology. The application will collect GPS-based location data and the user's body condition in the form of temperature and oxygen levels in the blood. User data is stored and processed in a real-time database in cloud computing which can be accessed through an application on the user's smart phone. The database also stores data on COVID-19 sufferers and where they live. Advice is given by the app when the recording of the body condition points to the early symptoms of COVID-19.

Optimization of mobile device energy consumption in a fog-based mobile computing offloading mechanism

The offloading of computing tasks to the fog computing system is a promising approach to reduce the response time of resource-greedy real-time mobile applications. Besides the decreasing of the response time, the offloading mechanisms may reduce the energy consumption of mobile devices. In the paper, we focused on the analysis of the energy consumption of mobile devices that use fog computing infrastructure to increase the overall system performance and to improve the battery life. We consider a three-layer computing architecture, which consists of the mobile device itself, a fog node, and a remote cloud. The tasks are processed locally or offloaded according to the threshold-based offloading criterion. We have formulated an optimization problem that minimizes the energy consumption under the constraints on the average response time and the probability that the response time is lower than a certain threshold. We also provide the numerical solution to the optimization problem and discuss the numerical results.

Architectural Exploration for Energy-Efficient Fixed-Point Kalman Filter VLSI Design

Efficient Kalman filter (KF) designs for real-time mobile applications, such as nano-drones navigation, robots localization, spacecraft orbit control, GPS positioning, image recognition, and multisensor data fusion for wearable systems, are key technology goals. The KF is a compute-intensive kernel composed of consecutive complex matrix operations, like multiplications and matrix inversions. The most complex block in the KF is the Kalman gain (KG) function, which involves matrices inversion at each iteration, applying the determinant matrix calculation and division operations. In this article, we combine architectural solutions of different types, for which balancing conflicting low-power and high-performance requirements aiming at real-time KF processing is a key design issue. The key finding in our architectural exploration herein presented is that the KF architectures in semiparallel and sequential forms offer the best balance of circuit area size, power dissipation, and processing speed. Compared to the state-of-the-art solutions, our KF architecture is more efficient, with 2.8 times fewer arithmetic operators, requiring 3.3 times fewer clock cycles. The usefulness of the developed KF in digital signal processing (DSP) is shown herein by simulations of system identification, noise elimination, and state estimation applications. These figures highlight the results of the KF architecture: the speed of adaptation for the system identification applications with root mean square error (RMSE) of 0.01 after 12 samples, precision level in noise elimination applications with RMSE of 0.13, and reliability in state estimation processes with RMSE less than 10% of system peak response.

A Review on Computational Intelligence Techniques in Cloud and Edge Computing

Cloud computing (CC) is a centralized computing paradigm that accumulates resources centrally and provides these resources to users through Internet. Although CC holds a large number of resources, it may not be acceptable by real-time mobile applications, as it is usually far away from users geographically. On the other hand, edge computing (EC), which distributes resources to the network edge, enjoys increasing popularity in the applications with low-latency and high-reliability requirements. EC provides resources in a decentralized manner, which can respond to users' requirements faster than the normal CC, but with limited computing capacities. As both CC and EC are resource-sensitive, several big issues arise, such as how to conduct job scheduling, resource allocation, and task offloading, which significantly influence the performance of the whole system. To tackle these issues, many optimization problems have been formulated. These optimization problems usually have complex properties, such as non-convexity and NP-hardness, which may not be addressed by the traditional convex optimization-based solutions. Computational intelligence (CI), consisting of a set of nature-inspired computational approaches, recently exhibits great potential in addressing these optimization problems in CC and EC. This paper provides an overview of research problems in CC and EC and recent progresses in addressing them with the help of CI techniques. Informative discussions and future research trends are also presented, with the aim of offering insights to the readers and motivating new research directions.

ECG-derived Aerobic And Anaerobic Indices For Training Efficiency Tracking

There is a continuous search for indirect methods and simple criteria to evaluate physiological effects of training. ECG analysis provides a relevant option for routine monitoring as it can be supported in real-time mobile or wearable device applications. Determination of the optimal ECG features is essential for monitoring and assessing systems. PURPOSE: To introduce ECG-derived aerobic index (AI) and anaerobic index (ANI) which could determine training effects and indicate subject’s metabolic state. METHODS: A healthy, physically active subject performed endurance and strength trainings 3 times a week. He fulfilled 55 ECG measurements using single-lead wrist-wearable device before and after 28 trainings. ECG signals were processed with detection of QRS-complex. AI and ANI were calculated as R-peak normalized to S-R complex slope and as S-T complex slope normalized to R-S slope. Correlations of AI and ANI with training load were calculated using Pearson correlation coefficient (r) with p value. RESULTS: Correlations between AI and aerobic load as well as ANI and anaerobic load were identified. The more energy was burned during training, the lower indices were registered. As shown in Figure, maximum of negative correlation between AI with aerobic load was in 60 min after training (r=-0.57, p<0.01). ANI showed negative correlation with anaerobic load (r=-0.35, p<0.01) in 30 min after training. CONCLUSION: Proposed ECG-derived aerobic and anaerobic indices showed statistically significant correlations with training load and could be used as assessed individual parameters of the degree of training in fitness and sport medicine. Figure. Dependences of ECG-derived aerobic (A) and anaerobic (B) indices on energy, burned during aerobic and anaerobic load. Correlation curves with confidence bounds (95 %).

Augmented Reality Approach for Marker-based Posture Measurement on Smartphones.

Marker tracking for postural and range of motion (ROM) measurements transcends multiple disciplines (e.g., healthcare, ergonomics, engineering). A viable real-time mobile application is currently lacking for measuring limb angles and body posture. To address this need, a novel Android smartphone augmented-reality-based application was developed using the AprilTag2 fiducial marker system. To evaluate the app, two markers were printed on paper and attached to a wall. A Samsung S6 mobile phone was fixed on a tripod, parallel to the wall. The smartphone app tracked and recorded marker orientation and 2D position data in the camera frame, from front and rear cameras, for different smartphone placements. The average error between mobile phone and measured angles was less than 1 degree for all test settings (back camera=0.29°, front camera=0.33°, yaw rotation=0.75°, tilt rotation=0.22°). The average error between mobile phone and measured distance was less than 4 mm for all test settings (back camera=1.8 mm, front camera=2.5 mm, yaw rotation=3 mm, tilt rotation=3.8 mm). Overall, the app obtained valid and reliable angle and distance measurements with smartphone positions and cameras that would be expected in practice. Thus, this app is viable for clinical ROM and posture assessments.

Global Path Planning and Path-Following for Wheeled Mobile Robot Using a Novel Control Structure Based on a Vision Sensor

This paper presents a novel design for the kinematic control structure of the wheeled mobile robot (WMR) path planning and path-following. The proposed system is focused on the implementation of practical real-time model-free algorithms based on visual servoing. The mainframe of this study is to implement a novel kinematic control structure based on visual sevoing and hybrid algorithms in real-time mobile robot applications. First, the structure of the proposed algorithm based on the visual information extracted from an overhead camera has been addressed. Then, the classification process of robot position and orientation, target, and obstacles has been addressed. Second, the path planning algorithms’ initial parameters and obstacles-free path coordinates have been determined by visual information extracted from images in real time. In this step, the interval type-2 fuzzy inference (IT2FIS) algorithm and various algorithms used in path planning have been compared and their performances have been analyzed. The third stage handled the path-following process using a novel control structure for keeping up the robot on the generated path. In this step, the proposed approach is compared with fuzzy Type-1/Type-2 and fuzzy-PID control algorithms, and their results have been analyzed statistically. The proposed system has been successfully implemented on several maps. The experimental results show that the developed design is valid in generating collision-free paths efficiently and consistently and able to guide the robot to follow the path in real time.