Invited Paper: Perishable Data in Smart Communities

Ultra-Reliable Low Latency Communication (URLLC) is the current requirement of today's vertical industry as per 3GPP 5G standard such as smart or automotive industry, smart vehicle, smart home, remote surgery for eHealth and cloud robotics for Industry 4.0. These systems are based upon network infrastructure which will handle time critical data traffic. In Release 16, 3GPP has made an integration of the 5G system with IEEE 802.1 working group specifications covering Time Sensitive Networking (TSN). Organizations are presently utilizing this standard in their applications over different wired and wireless networks like ethernet, fiber and 5G networks. In this paper the authors have presented their successful utilization of TSN in their 5G 28 GHz radio link and tested the radio link with different use cases. They are also exploring the different systems available with them starting with PC processor and bluestacks/chromecast software to launch their applications over 5G link. Further, they are exploring the use of multiprocessor based equipments for the upgradation of their system. The inclusion of NPN(Non Public Network) in Release 16 encourages the developers/users to implement their smart 5G network without taking any resources from MNOs (Mobile Network Operator). The authors are emulating NPN and TSN assisted 5G catering for smart system like smart home and vehicle.

ABSTRACTRemote sensing technology can be a valuable tool for mapping coral reef ecosystems. However, the resolution capabilities of remote sensors, the diversity and complexity of coral reef ecosystems, and the low reflectivity of marine environments increase the difficulties in identifying and classifying their features. This research study explores the capability of high spatial resolution (WorldView-2 (WV-2) and Pleiades-1B) and low spatial resolution (Land Remote-Sensing Satellite (Landsat 8)) multispectral (MS) satellite sensors in quantitatively mapping coral density. The Kubbar coral reef ecosystem, located in Kuwait’s southern waters, was selected as the research site. The MS imagery of WV-2, Pleiades-1B and Landsat 8 were, after geometric and radiometric assessment and corrections, subjected to new image classification approach using a Multiple Linear Regression (MLR) analysis. The new approach of MLR coral density analysis used the dependent variable of coral density percentage from ground truth and independent variables of spectral reflectance from selected imagery, depth (as estimated from a surface derived from bathymetric charts) and distance to land or reef unit centre. Accuracy assessment using independent ground truth was performed for the selected approach and satellite sensors to determine the quality of the information derived from image classification processes. The results showed that coral density maps developed using the MLR coral density model proved to have some level of reliability (radiometrically corrected WV-2 image (the coefficient determination denoted as R-squared (R²) = 0.5, Root-Mean-Square Error (RMSE) = 10) and radiometrically corrected Pleiades-1B image (R² = 0.8, RMSE = 10)). This study suggested using high spectral resolution data and including additional factors (variables) (e.g. water turbidity, temperature and salinity) could contribute to improving the accuracy of coral density maps produced by application of the MLR model; however, all of these would add cost and effort to the mapping process. The outcomes of this research study provide coral reef ecosystem researchers, managers, and decision makers a tool to determine and map coral reef density in more detail than in the past. It will help quantify coral density at particular points in time leading to estimates of change, and allow coral reef ecologists to identify the current coral reef habitat health status, distribution and extent.

Transparency is an important element of smart cities, and ongoing work is exploring the use of available open data to maximize it. This position paper argues that Linked Data and visualization play similar roles, for different agents, in this context. Linked Data increases transparency for machines, while visualization increases transparency for humans. The work also proposes a quantitative approach to the evaluation of visualization insights which rests on two premises: (i) visualizations could be modelled as a set of statements made by authors at some point in time, and (ii) statements made by experts could be used as ground truth while evaluating how much insights are effectively conveyed by visualizations on the Web. Drawing on the linked data rating scheme of Tim Berners-Lee, the paper proposes a five-stars rating scheme for visualizations on the Web. The ideas suggested are relevant to the development of techniques to automatically assess the transparency level of existing visualizations on the Web.

Delayed enhancement imaging is an essential component of cardiac MRI, which is used widely for the evaluation of myocardial scar and viability. The selection of an optimal inversion time (TI) or null point (TINP ) to suppress the background myocardial signal is required. The purpose of this study was to assess the feasibility of automated selection of TINP using a convolutional neural network (CNN). We hypothesized that a CNN may use spatial and temporal imaging characteristics from an inversion-recovery scout to select TINP , without the aid of a human observer. We retrospectively collected 425 clinically acquired cardiac MRI exams performed at 1.5 T that included inversion-recovery scout acquisitions. We developed a VGG19 classifier ensembled with long short-term memory to identify the TINP . We compared the performance of the ensemble CNN in predicting TINP against ground truth, using linear regression analysis. Ground truth was defined as the expert physician annotation of the optimal TI. In a backtrack approach, saliency maps were generated to interpret the classification outcome and to increase the model's transparency. Prediction of TINP from our ensemble VGG19 long short-term memory closely matched with expert annotation (ρ = 0.88). Ninety-four percent of the predicted TINP were within ±36 ms, and 83% were at or after expert TI selection. In this study, we show that a CNN is capable of automated prediction of myocardial TI from an inversion-recovery experiment. Merging the spatial and temporal characteristics of the VGG-19 and long short-term-memory CNN structures appears to be sufficient to predict myocardial TI from TI scout.

Investigating the effects of workload on body kinematics is the first step to identify, monitor, and ultimately reduce the incidence of fatigue, a prevalent phenomenon in the workplace that leads to chronic disorders, loss of productivity, and absenteeism (Lu, Megahed, Sesek, & Cavuoto, 2017, In Press; Ricci, Chee, Lorandeau, & Berger, 2007). In fa- tigue monitoring, kinematic measures including acceleration, jerk, and body posture have been found to be informative (Lu et al., 2017, In Press; Maman, Yazdi, Cavuoto, & Megahed, 2017; Ricci et al., 2007); however, none of the previous studies have considered a comprehensive set of these kinematic metrics during simulated manufacturing tasks. This study assessed the effects of duration, ease of task, and age as three factors on different body kinematic metrics and subjective ratings as a substitute “ground truth” for fatigue development. This will serve to inform feature selection for modeling fatigue development over a broad range of industrial tasks. Nineteen participants (divided into two age groups of younger (<25, 6 males and 4 females) and older (>40, 8 males and 1 female)) completed three, three-hour sessions of parts assembly (light), supply pickup and insertion (moderate), and manual material handling (difficult). Inertial measurement units (IMUs) were attached on right wrist, middle of the trunk, the right side of the hip, and right ankle. The mean and peak values of acceleration, jerk, and posture for each body location along with the minimum value (with respect to the horizontal plane) of trunk bending posture were considered as the kinematic variables of interest. The Borg rating of perceived exertion (RPE) and subjective fatigue level (SFL) were recorded at the start of each session, and then every ten minutes for RPE, and every thirty minutes for SFL. Perceived workload, rated using the NASA Task Load Index (TLX), was obtained every one hour. The TLX, RPE, and SFL at the end of hour 1 (the first time point where all three ratings are obtained) were considered as the pre-fatigue values and at hour 3 of the tasks as the post-fatigue. Similarly, the pre-fatigue kinematic data of the IMUs was the period from minutes 10 to 20 and the post-fatigue data was the period from minutes 160 to 170. The results of repeated measures ANOVA showed a significant time ( p < 0.001) effect on all three subjective ratings. In addition, time and age interacted to affect RPE ( p = 0.018) with a 36% increase in younger and 28% in the older group. Time had significant effects only on a few of kinematic variables including mean trunk acceleration (8% decreased), mean trunk posture (3% less bent), and peak hip acceleration (10% increased) after fatigue. Moreover, there was a significant age and task interaction for peak hip acceleration (~1 m/s2 decreased), mean and peak leg posture (~4o increased and ~12o decreased, respectively), and minimum trunk posture (~5o increased) from the younger group to the older group. In addition, there was significant interaction ( p = 0.011) between time and task in bending posture denoted by hip and trunk, which provides insight into the different effects of fatigue on different tasks, i.e., 2% more bending after fatigue in manual material handling and supply pickup and insertion in comparison to parts assembly. This increased bending angle following fatigue was in agreement with the findings of Strohrmann, Harms, Kappeler-Setz, and Troster (2012). There were significant differences between the younger group to the older group in terms of kinematics, i.e., peak hip acceleration, mean and peak leg posture, and minimum trunk posture that may be attributable to different quadriceps strength and postural stability between the age groups. Overall, the results present a set of kinematic parameters influenced by fatigue; however, further analysis is required to explore more temporal and spatial movement variables from IMUs for a better understanding of fatigue effects and indicators.

Quantitative perfusion maps of cerebral blood flow, cerebral blood volume, and transit time generated using dynamic imaging data enable physicians to evaluate and prescribe the optimal plan of care for stroke patients. Validation is needed to increase the accuracy and reproducibility of this data, which can vary depending on the scanning technique and post-processing algorithm. In this work, we expand the XCAT brain phantom to incorporate a realistic model of the contrast agent dynamics in the cerebral vasculature and establish the ground truth to which the perfusion maps can be compared. For a specific stroke case, each tissue region's flow demand is calculated and used to determine the feeding flow in the upstream arteries and draining flow in the downstream veins. Using the flow values and a contrast agent injection curve, the model calculates the input and output concentration curves for each structure in the brain. The concentration curve within each structure is then calculated as the difference between the total amount of contrast agent that has entered and exited the structure up until that timepoint. A dynamic simulation framework utilizes the curves to define the contrast agent concentration within the phantom at each time point and generates simulated CT perfusion imaging data sets compatible with commercially available post-processing software. This development provides a realistic set of ground truth test data that enables quantitative validation and optimization of perfusion imaging and post-processing methods for stroke assessment.

Introduction Improving positive airway pressure (PAP) adherence is crucial to sleep apnea therapy success. Although behavioral interventions may be deployed to increase PAP adherence, operationalization remains an ongoing clinical challenge. Treatment outcomes may be optimized by forecasting PAP use to identify patients at risk for non-adherence enabling early intervention. We build upon our previous work by leveraging a larger dataset, additional metadata, and new Deep Learning approaches to forecast future PAP adherence. Methods We collected a cohort of N=21,397 subjects with daily PAP usage recorded during 2015-2021. We defined the input to models as the number of minutes the PAP machine was used during each day for the first 30-days. The ground truth was defined as the PAP adherence of the patients at the 3-month, 6- month, and 1-year endpoints. Adherence was calculated based on a 30-day window as ≥4-hours of usage for ≥70% of nights. We evaluated a Deep Neural Network (DNN) model with 10-fold cross- validation to forecast future adherence by leveraging previous daily usage information. Results were compared to a naive method which assumes adherence at each time point equals adherence during the first 30-days. Results The DNN models predicted adherence with a sensitivity of 90%, 81%, 77% and a specificity of 90%, 81%, 77%, for 3-month, 6-month, and 1-year endpoints, with ROC-AUC values of 0.97, 0.89, and 0.84 respectively. The models converged to ROC-AUC performance >0.90 for the first 90-days within the first 7 to 14-days of PAP use. Conclusion DNN models demonstrated strong predictive performance for PAP adherence, as defined by the CMS adherence criteria, measured by sensitivity, specificity, and overall ROC-AUC results at clinically relevant 90-day, 6-month, and 1-year timepoints. AI approaches show promise as early predictors of the likelihood to meet key therapy utilization thresholds within the first 1-2 weeks of therapy, enabling early PAP intervention or transition to alternative therapies. Support (if any) AASM Foundation SRA205-SR-19

This paper focuses on the problems which arise in the large hospitals when patient arrives in emergency or alone, at that moment patient is not able to deal with the conditions of hospitals in which they have to go from one department to another department for some of the other things, In the whole process most of the time is very stressful as it demands critical time of patient. A smart guided mobile tablet fitted permanently on a wheelchair or on stretcher bed is a very practical solution to resolve this issue. If an injured person just reaches the hospital by own, and unfortunately if no staff members are present at that point in time to help the patient, the patient can use the smart system embedded on wheelchair, to navigate to the emergency ward or the respective department of the hospital without the hassle of any pre-checkup registration. The user can navigate by selecting source and destination from the user interface and can reach the destination easily. The navigation is provided by the microcontroller and interrupts generated from the spokes of the wheel. The patient can use the smart system to enter his/her information to the hospital's database so that the hospital can keep a record of the health and reports of the patients.

In this paper, we aim to develop a method to create personalized and high-presence multi-channel contents for a sport game through realtime content curation from various media streams captured/created by spectators. We use the live TV broadcast as a ground truth data and construct a machine learning-based model to automatically conduct curation from multiple videos which spectators captured from different angles and zoom levels. The live TV broadcast of a baseball game has some curation rules which select a specific angle camera for some specific scenes (e.g., a pitcher throwing a ball). As inputs for constructing a model, we use meta data such as image feature data (e.g., a pitcher is on the screen) in each fixed interval of baseball videos and game progress data (e.g., the inning number and the batting order). Output is the camera ID (among multiple cameras of spectators) at each point of time. For evaluation, we targeted Spring-Selection high-school baseball games. As training data, we used image features, game progress data, and the camera position at each point of time in the TV broadcast. We used videos of a baseball game captured from 7 different points in Hanshin Koshien Stadium with handy video cameras and generated sample data set by dividing the videos to fixed interval segments. We divided the sample data set into the training data set and the test data set and evaluated our method through two validation methods: (1) 10-fold crossvalidation method and (2) hold-out methods (e.g., learning first and second innings and testing third inning). As a result, our method predicted the camera switching timings with accuracy (F-measure) of 72.53% on weighted average for the base camera work and 92.1% for the fixed camera work.

The use of Unmanned Aerial Vehicles (UAVs) for collecting data from remotely located sensor systems is emerging. The data can be time-sensitive and require to be transmitted to a data processing center. However, planning the trajectory for a swarm of UAVs depends on multi-fold constraints, such as data collection requirements, UAV maneuvering capacities, and budget limitations. Since a UAV may fail or be compromised, it is important to provide necessary resilience to such contingencies, thus ensuring data security. It is important to provide the UAVs with efficient spatio-temporal trajectories so that they can efficiently cover necessary data sources. In this work, we present Synth4UAV, a formal approach for automated synthesis of efficient trajectories for a UAV swarm by logically modeling the aerial space and data point topology, UAV moves, and associated constraints in terms of the turning and climbing angle, fuel usage, data collection point coverage, data freshness, and resiliency properties. We use efficient, logical formulas to encode and solve the complex model. The solution to the model provides the routing and maneuvering plan for each UAV, including the time to visit the points on the paths and corresponding fuel usage such that the necessary data points are visited while satisfying the resiliency requirements. We evaluate the proposed trajectory synthesizer, and the results show that the relationship among different parameters follows the requirements while the tool scales well with the problem size.

Abstract— This paper presents a smart door lock system that uses facial recognition technology to improve home security. The proposed system combines facial authentication, RFID- based identification, and servo motor control to provide a multi- layered security mechanism. Designed using Raspberry Pi, the system leverages real-time image processing and machine learning techniques. The paper discusses system architecture, implementation, and evaluation of authentication accuracy and performance.

The segmentation of neoplasms is an important part of radiotherapy treatment planning, monitoring disease progression, and predicting patient outcome. In the brain, functional magnetic resonance imaging (MRI) like dynamic susceptibility contrast enhanced (DSCE) or T1-weighted dynamic contrast enhanced (DCE) perfusion MRI are important tools for diagnosis. They play a crucial role in providing pre-operative assessment of tumor histology, grading, and biopsy guidance. However, the manual contouring of these neoplasms is tedious, expensive, time-consuming, and vulnerable to inter-observer variability. In this work, we propose a 3D mask region-based convolutional neural network (R-CNN) method to automatically segment brain tumors in DSCE MRI perfusion images. As our goal is to simultaneously localize and segment the tumor, our training process contained both a region-of-interest (ROI) localization and regression with voxel-wise segmentation. The combination of classification loss, ROI location and size regression loss, and segmentation loss were used to supervise the proposed network. We retrospectively investigated 21 patients’ perfusion images, with between 50 and 70 perfusion time point volumes, a total of 1260 3D volumes. Tumor contours were automatically segmented by our proposed method and compared against other state-of-the-art methods and those delineated by physicians as the ground truth. The results of our method demonstrated good agreement with the ground truth contours. The average DSC, precision, recall, Hausdorff distance, mean surface distance (MSD), root MSD, and center of mass distance were 0.90 ± 0.04, 0.91 ± 0.04, 0.90 ± 0.06, 7.16 ± 5.78 mm, 0.45 ± 0.34 mm, 1.03 ± 0.72 mm, and 0.86 ± 0.91 mm, respectively. These results support the feasibility of our method in accurately localizing and segmenting brain tumors in DSCE perfusion MRI. Our 3D Mask R-CNN segmentation method in DSCE perfusion imaging has great promise for future clinical use.

Modeling the Volumetric Change of Head and Neck Tumor in Response to Radiation Therapy

The creation of smart communities in the context of the era of big data is an important driving force for the transformation of economic development mode and the realization of a well-off society in an all-round way. Applying "Internet +" thinking to solve the problem of transformation and upgrading of traditional industries is an inevitable requirement of the development of the times, and it is also the way out for traditional industries in the future. This paper is based on the smart community service system model of the National Secret SM2 algorithm, from the four aspects of the smart community's artificial intelligence system architecture, the smart community integrated service cloud platform, the smart community Internet of Things platform, and the smart community APP. It is elaborated. The paper generated the smart community service system designed in this paper on the Android platform, which not only met the actual needs of community residents, but also realized the universal applicability and friendliness of the interface.

Machine-learned systems are in widespread use for making decisions about humans, and it is important that they are fair, i.e., not biased against individuals based on sensitive attributes. We present runtime verification of algorithmic fairness for systems whose models are unknown, but are assumed to have a Markov chain structure. We introduce a specification language that can model many common algorithmic fairness properties, such as demographic parity, equal opportunity, and social burden. We build monitors that observe a long sequence of events as generated by a given system, and output, after each observation, a quantitative estimate of how fair or biased the system was on that run until that point in time. The estimate is proven to be correct modulo a variable error bound and a given confidence level, where the error bound gets tighter as the observed sequence gets longer. Our monitors are of two types, and use, respectively, frequentist and Bayesian statistical inference techniques. While the frequentist monitors compute estimates that are objectively correct with respect to the ground truth, the Bayesian monitors compute estimates that are correct subject to a given prior belief about the system’s model. Using a prototype implementation, we show how we can monitor if a bank is fair in giving loans to applicants from different social backgrounds, and if a college is fair in admitting students while maintaining a reasonable financial burden on the society. Although they exhibit different theoretical complexities in certain cases, in our experiments, both frequentist and Bayesian monitors took less than a millisecond to update their verdicts after each observation.