Real-time Alerts Research Articles

A study on digital payment applications in India

This Research Paper is based on the in-depth study of applications that deals with Unified Payment Interface (UPI) in India. It shows how the dynamics are changing in the UPI sector and which companies are leading the table. The study was conducted in Pune Region and the survey was done with the help of questionnaire. A response of 82 respondents has been collected and then accordingly a conclusion is made. The Data for the study was also conducted from secondary sources which eventually helped us to get a fair understanding of the Industry. In today’s world one word is common that is “Digitalisation” and it is also gaining popularity due to increase in use of Smartphone by the people, the same has applied to the financial sector. In India, the Unified Payment Interface (UPI) was launched in the year 2016 by National Payments Corporation of India (NPCI). UPI is a payment server which allows its users to transfer the money on real-time basis from Peer-to-Peer (P2P) or from Personto-Merchant (P2M). It is an application that allows the users to use multiple bank accounts in single application. UPI has become so popular in India, also around world due to its ease of use, security, real-time alerts, etc. In India, UPI is currently in a growth stage and showing a robust growth year-onyear. In this research we will have an in-depth study on 5 major UPI apps in India namely GooglePay, PhonePe, Amazon Pay, Paytm and BHIM.

YOLO-Rip: A modified lightweight network for Rip currents detection

Rip currents form on beaches worldwide and pose a potential safety hazard for beach visitors. Therefore, effectively identifying rip currents from beach scenes and providing real-time alerts to beach managers and beachgoers is crucial. In this study, the YOLO-Rip model was proposed to detect rip current targets based on current popular deep learning techniques. First, based on the characteristics of a large target size in rip current images, the neck region in the YOLOv5s model was streamlined. The 80 × 80 feature map branches suitable for detecting small targets were removed to reduce the number of parameters, decrease the complexity of the model, and improve the real-time detection performance. Subsequently, we proposed adding a joint dilated convolutional (JDC) module to the lateral connection of the feature pyramid network (FPN) to expand the perceptual field, improve feature information utilization, and reduce the number of parameters, while keeping the model compact. Finally, the SimAM module, which is a parametric-free attention mechanism, was added to optimize the target detection accuracy. Several mainstream neural network models have been used to train self-built rip current image datasets. The experimental results show that (i) the detection results from different models using the same dataset vary greatly and (ii) compared with YOLOv5s, YOLO-Rip increased the mAP value by approximately 4% (to 92.15%), frame rate by 2.18 frames per second, and the model size by only 0.46 MB. The modified model improved the detection accuracy while keeping the model streamlined, indicating its efficiency and accuracy in the detection of rip currents.

SARS-CoV-2 Surveillance in Indoor Air Using Electrochemical Sensor for Continuous Monitoring and Real-Time Alerts.

The severe acute respiratory syndrome related coronavirus 2 (SARS-CoV-2) has spread globally and there is still a lack of rapid detection techniques for SARS-CoV-2 surveillance in indoor air. In this work, two test rigs were developed that enable continuous air monitoring for the detection of SARS-CoV-2 by sample collection and testing. The collected samples from simulated SARS-CoV-2 contaminated air were analyzed using an ultra-fast COVID-19 diagnostic sensor (UFC-19). The test rigs utilized two air sampling methods: cyclone-based collection and internal impaction. The former achieved a limit of detection (LoD) of 0.004 cp/L in the air (which translates to 0.5 cp/mL when tested in aqueous solution), lower than the latter with a limit of 0.029 cp/L in the air. The LoD of 0.5 cp/mL using the UFC-19 sensor in aqueous solution is significantly lower than the best-in-class assays (100 cp/mL) and FDA EUA RT-PCR test (6250 cp/mL). In addition, the developed test rig provides an ultra-fast method to detect airborne SARS-CoV-2. The required time to test 250 L air is less than 5 min. While most of the time is consumed by the air collection process, the sensing is completed in less than 2 s using the UFC-19 sensor. This method is much faster than both the rapid antigen (<20 min) and RT-PCR test (<90 min).

Moving toward Smart Manufacturing with an Autonomous Pallet Racking Inspection System Based on MobileNetV2

Pallet racking is a fundamental component within the manufacturing, storage, and distribution centers of companies around the World. It requires continuous inspection and maintenance to guarantee the protection of stock and the safety of personnel. At present, racking inspection is manually carried out by certified inspectors, leading to operational down-time, inspection costs and missed damage due to human error. As companies transition toward smart manufacturing, we present an autonomous racking inspection mechanism using a MobileNetV2-SSD architecture. We propose a solution that is affixed to the adjustable cage of a forklift truck, enabling adequate coverage of racking in the immediate vicinity. Our proposed approach leads to a classifier that is optimized for deployment onto edge devices, providing real-time alerts of damage to forklift drivers, with a mean average precision of 92.7%.

A pilot study to investigate real-time digital alerting from wearable sensors in surgical patients

BackgroundContinuous vital sign monitoring may identify changes sooner than current standard monitoring.ObjectiveTo investigate if the use of real-time digital alerts sent to healthcare staff can improve the time taken to identify unwell patients and those with sepsis.DesignA prospective cohort study design.SettingWest Middlesex University Hospital, UK.ParticipantsFifty acutely unwell surgical patients admitted to hospital.InterventionPatients wore a lightweight wearable sensor measuring heart rate (HR), respiratory rate (RR) and temperature every 2 min whilst standard intermittent ward monitoring of vital signs was performed by nurses. Digital alerts were sent to healthcare staff from the sensor to a smartphone device. All alerts were reviewed for recruited patients to identify the exact time on the sensor in which deterioration occurred. The time to acknowledgement was then reviewed for each action and an average time to acknowledgement calculated.ResultsThere were 50 patients recruited in the pilot study, of which there were vital sign alerts in 18 patients (36%). The total number of vital sign alerts generated in these 18 patients was 51. Of these 51 alerts, there were 7 alerts for high HR (13.7%), 33 for RR (64.7%) and 11 for temperature (21.6%). Out of the 27 acknowledged alerts, there were 2 alerts for HR, 17 for RR and 8 for temperature. The average time to staff acknowledgement of the notification for all alerts was 154 min (2.6 h).There were some patients which had shown signs of deterioration in the cohort. The frequency of routine observation monitoring was increased in 2 cases, 3 patients were referred to a senior clinician and 2 patients were initiated on the sepsis pathway.ConclusionThis study demonstrates the evaluation of digital alerts to nurses in real time. Although not all alerts were acknowledged, deterioration on the ward observations was detected and actions were taken accordingly. Patients were started on the sepsis pathway and escalation to senior clinicians occurred. Further research is required to review why only some alerts were acknowledged and the effects of digital alerting on patient outcomes.Trial registrationClinicalTrials.gov, NCT04638738

A scoping review of real-time automated clinical deterioration alerts and evidence of impacts on hospitalised patient outcomes

BackgroundHospital patients experiencing clinical deterioration are at greater risk of adverse events. Monitoring patients through early warning systems is widespread, despite limited published evidence that they improve patient outcomes. Current...

Detection and quantification of anomalies in communication networks based on LSTM-ARIMA combined model.

The anomaly detection for communication networks is significant for improve the quality of communication services and network reliability. However, traditional communication monitoring methods lack proactive monitoring and real-time alerts and the prediction effect of a single machine learning model on communication data containing multiple features is not ideal. To solve the problem, A prediction-then-detection anomaly detection method was proposed, and quantitative assessment of network anomalies was developed. Specifically, anomaly-free data was obtained by eliminating outliers, and the long short-term memory (LSTM) and autoregressive integral moving average (ARIMA) were combined via residual weighting to predict the future state of the key performance indicators (KPI) without outliers. Anomalies were identified using the error comparison between the prediction and actual values, and the network condition was quantified using the scoring method. It is observed that the proposed LSTM-ARIMA hybrid model has better prediction effect, which can well represent the performance of KPIs of the future state, and the prediction-then-detection anomaly detection method has excellent performance on both precision and recall.

68-LB: The First Real-World Experience with Bigfoot Unity—A Three-Month Retrospective Analysis

Background: In the US, approximately 10 million people with diabetes require insulin; the vast majority using MDI therapy. Diabetes is associated with sustained daily burdens due to complex, demanding, and often confusing self-care directives, which may be more pronounced with MDI. Bigfoot Unity is a unique, interconnected smart pen cap diabetes management system designed to address an unmet medical need to support MDI therapy, incorporating CGM data (Abbott FreeStyle Libre 2) , real-time alerts and clinician-directed dose recommendations. Methods: The Bigfoot Unity System received FDA clearance in May 2021. We report a retrospective analysis on an initial cohort (N=49 at 11 clinics) with insulin-requiring diabetes managing MDI with Bigfoot Unity for 90 days. Deidentified data were evaluated to analyze glycemic metrics during use, and HbA1c obtained from medical records prior to use. Results: Within the cohort, mean age was 60 years and 40 (82%) had T2D. The mean HbA1c prior to Bigfoot Unity use was 8.5±2.0% (N=43) . Mean GMI was 7.5±0.9% after 3 months use. Discussion: These data show that for people using MDI with suboptimal glycemic control, using the Bigfoot Unity System has the potential for rapid and durable improvement in glycemic control. Considering the mean age of the cohort, results demonstrate close adherence to established glycemic targets including a short time spent in the hypoglycemia range. Further studies are planned to investigate this hypothesis. Disclosure B. Baliga: Speaker’s Bureau; Abbott Diabetes, Amarin Corporation, AstraZeneca, Bigfoot Biomedical, Inc., Boehringer Ingelheim International GmbH, Eli Lilly and Company, Intuity Medical, Inc., Merck &amp; Co., Inc., Novo Nordisk, Stock/Shareholder; Amarin Corporation, Insulet Corporation, Merck &amp; Co., Inc., Moderna, Inc., Senseonics. J. Tillman: Employee; Bigfoot Biomedical, Inc. B. P. Olson: Employee; Bigfoot Biomedical, Inc. S. Vaughan: Employee; Bigfoot Biomedical, Inc. F. Sheikh: Employee; Bigfoot Biomedical, Inc. J. K. Malone: Consultant; Eli Lilly and Company, Insulet Corporation, Thermalin Inc., Employee; Bigfoot Biomedical, Inc. Funding Bigfoot Biomedical

Making waves: Uses of real-time, hyperlocal flood sensor data for emergency management, resiliency planning, and flood impact mitigation

Flooding is expected to increase due to intensification of extreme precipitation events, sea-level rise, and urbanization. Low-cost water level sensors have the ability to fill a critical data gap on the presence, depth, and duration of street-level floods by measuring flood profiles (i.e., flood stage hydrographs) in real-time with a time interval on the order of minutes. Hyperlocal flood data collected by low-cost sensors have many use cases for a variety of stakeholders including municipal agencies, community members, and researchers. Here we outline examples of potential uses of flood sensor data before, during, and after flood events, based on dialog with stakeholders in New York City. These uses include inputs to predictive flood models, generation of real-time flood alerts for community members and emergency response teams, storm recovery assistance and cataloging of storm impacts, and informing infrastructure design and investment for long-term flood resilience project planning.

Monitoring activity and detecting unexpected events in surveillance footage using Deep CNN

Security is always a primary concern in any domain, because there is an increasing in crime rate and illegal activities. Computer vision learning places a premium on abnormal detection and monitoring, which has numerous applications for dealing with a wide range of issues. We are all aware that there is a high demand for safety protection, personal properties and security, in recent years, video surveillance in systems has become a major focus in people's lives, particularly in government agencies and businesses. The technique we are employing is anomaly detection, which aids in distinguishing various patterns and identifying unusual patterns in a short period of time; these patterns are referred to as outliers. Surveillance videos provide real-time output of unusual events. Anomaly detection in video surveillance entails breaking the process down into three layers: video labelers, image processing, and activity detection. As a result, it detects abnormalities in videos for video surveillance, providing an application by providing accurate results in real-time scenarios. In this proposed work, abnormal events are detected with 98.5 percent accuracy using images and videos. To prevent virus transmissions across the world the government forced to announce the lockdown due to COVID-19 pandemic. As a result, production at manufacturing plants in most areas was halted, resulting in the cessation of all economic activity. There is an even greater need to ensure the safety of youngsters. While there is a pressing need to revive workforce production. The work helps in maintaining social distance and wearing face masks while at work clearly reduces the risk of transmission. Monitor activity decided to identify violations using computer vision (Not Wearing Mask) Real-time alerts that send a trigger and an email with a photo of a rule violation to the appropriate authority as evidence of a rule violation

A Secure and Stable Humanoid Healthcare Information Processing and Supervisory Method with IoT-Based Sensor Network

Nowadays, the Internet of things- (IoT-) based emerging technologies are playing a very pervasive role in healthcare systems where information is required on a real-time basis. These systems may provide real-time alerts with continuous monitoring to the concern in the odd conditions. Thus, these systems help the elderly and ill person with a good quality life and reduce the number of caregiver persons. Based on the above facts, this paper proposes a secure, efficient, and stable humanoid healthcare information processing and supervisory method with an IoT-based sensor network. Here, five different parameters specifically network residual energy, node density, node average energy, number of neighbors surrounded of a node, and distance between the sensor node and sink are considered for effective utilization of the energy of the sensor nodes. This method also reduces the communication distance of the nodes which helps in proficient data collection from the human body. The performance of the proposed and the existing work is considered the stability period, number of alive and dead nodes, total energy consumption, number of packets send to cluster heads, and base station metrics with two different monitoring areas. Thus, the stability period of the proposed method is increased by 144.52% with respect to the existing method protocol.

False Alert Detection Based on Deep Learning and Machine Learning

Among the large number of network attack alerts generated every day, actual security incidents are usually overwhelmed by a large number of redundant alerts. Therefore, how to remove these redundant alerts in real time and improve the quality of alerts is an urgent problem to be solved in large-scale network security protection. This paper uses the method of combining machine learning and deep learning to improve the effect of false alarm detection and then more accurately identify real alarms, that is, in the process of training the model, the features of a hidden layer output of the DNN model are used as input to train the machine learning model. In order to verify the proposed method, we use the marked alert data to do classification experiments, and finally use the accuracy recall rate, precision, and F1 value to evaluate the model. Good results have been obtained.

Using Cloud Computing to Analyze Model Output Archived in Zarr Format

Abstract Numerical weather prediction centers rely on the Gridded Binary Second Edition (GRIB2) file format to efficiently compress and disseminate model output as two-dimensional grids. User processing time and storage requirements are high if many GRIB2 files with size O(100 MB, where B = bytes) need to be accessed routinely. We illustrate one approach to overcome such bottlenecks by reformatting GRIB2 model output from the High-Resolution Rapid Refresh (HRRR) model of the National Centers for Environmental Prediction to a cloud-optimized storage type, Zarr. Archives of the original HRRR GRIB2 files and the resulting Zarr stores on Amazon Web Services (AWS) Simple Storage Service (S3) are available publicly through the Amazon Sustainability Data Initiative. Every hour, the HRRR model produces 18- or 48-hourly GRIB2 surface forecast files of size O(100 MB). To simplify access to the grids in the surface files, we reorganize the HRRR model output for each variable and vertical level into Zarr stores of size O(1 MB), with chunks O(10 kB) containing all forecast lead times for 150 × 150 gridpoint subdomains. Open-source libraries provide efficient access to the compressed Zarr stores using cloud or local computing resources. The HRRR-Zarr approach is illustrated for common applications of sensible weather parameters, including real-time alerts for high-impact situations and retrospective access to output from hundreds to thousands of model runs. For example, time series of surface pressure forecast grids can be accessed using AWS cloud computing resources approximately 40 times as fast from the HRRR-Zarr store as from the HRRR-GRIB2 archive. Significance Statement The rapid evolution of computing power and data storage have enabled numerical weather prediction forecasts to be generated faster and with more detail than ever before. The increased temporal and spatial resolution of forecast model output can force end users with finite memory and storage capabilities to make pragmatic decisions about which data to retrieve, archive, and process for their applications. We illustrate an approach to alleviate this access bottleneck for common weather analysis and forecasting applications by using the Amazon Web Services (AWS) Simple Storage Service (S3) to store output from the High-Resolution Rapid Refresh (HRRR) model in Zarr format. Zarr is a relatively new data storage format that is flexible, compressible, and designed to be accessed with open-source software either using cloud or local computing resources. The HRRR-Zarr dataset is publicly available as part of the AWS Sustainability Data Initiative.

Design and Development of a VHF Telemetry Two-way Radio Device Network Downtime/Uptime Alerting Prototype

This paper presents the design and development of a VHF telemetry Two-way radio device network downtime/uptime alerting prototype. Telemetry network monitoring using VHF 2-way radio Streaming is a paradigm in networking management that has not been deployed. The framework enables continuous monitoring of the mobile and fixed access points of the mining fleet management Wi-Fi system (in the case of the Barrick Lumwana mine, Zambia). Considering the significance of real-time alerts in a mining facility, critical systems such as slope monitoring radars, mobile emergency alerts, and timely copper production reports must be monitored in real-time. The results for the performance warnings of the telemetry access points collectively accounted for a response alert time of 1999ms from the samples collected which translated to 0.29% compared to the SNMP system that registered a total of 689500ms for the samples collected which translates to 99.71% of the total response time of 691499ms. The results derived from the VHF 2-way radio telemetry prototype show that this system performs better than the traditional SNMP network monitoring system. We recommend that this IP network prototype is used in open-pit mines alongside Motorola telemetry two-way radios.

Wearable technology for hazardous remote environments: Smart shirt and Rugged IoT network for forestry worker health

This paper introduces the architecture and details of our wearable IoT solution for workplace health and safety in rugged outdoor environments. We focus on the specific requirements defined by the New Zealand forestry environment as it is the industry with the most fatalities and highest accident rate in New Zealand. Neither consumer-level products nor professional wearables have been found to be suitable for forestry conditions. Furthermore, forestry workplaces cannot rely on existing networking infrastructure, and due to their remote and rugged nature, no permanent setup is possible. We describe the Hakituri project in which we integrate wearable devices, networking, data analytics, and a buddy system into a novel monitoring solution for worker health and safety. Our wearable IoT solution includes a dynamic network set-up, wearables suitable for forestry conditions, contextual rule-based data analytics, and real-time alerts. A wearable smart shirt carries sensors for collecting personal data from forestry workers, while further environmental sensors capture contextual data. The IoT network is set up for communication in unreliable and rugged outdoor environments. We explore a variety of setups to achieve the best quality outcomes for health and safety in the forestry domain.

Inferring safety critical events from vehicle kinematics in naturalistic driving environment: Application of deep learning Algorithms

Advances in sensing technology has enabled the collection of countless terabytes of second-by-second kinematics data. Such data provides opportunities for real-time monitoring of driving behavior and identification of safety critical events (SCEs) including crashes and near crashes. The concept of volatility is relevant in this context, which identifies instability and erratic variations in driving behavior prior to involvement in SCEs. This study utilized vehicle kinematics from a large-scale naturalistic driving data to develop a deep learning approach based on 1D convolutional neural networks (CNN) for inferring SCEs. The data are unique in the sense that such accurate pre-crash data at high fidelity are not available in traditional crash repositories. This study contributes to the literature by providing a first attempt at predicting responses to SCEs by developing deep learning-based CNN architectures using novel driving volatility based kinematic thresholds for a sample of 9553 events. The key contribution lies in developing a volatility-based CNN input layout that is acceptable to CNN schemes and represents the motion kinematics such as speed, acceleration and volatility measures. Several 1D-CNN architectures were developed using layers, numbers of convolutions, layer patterns, and kernels. Shallow and deep architectures were tested, revealing higher accuracy of shallow architectures in detecting SCEs. The optimal number of epochs were identified using an early stopping method while the CNN performance was improved by increasing the number of epochs. The ensemble CNN had the highest predictive accuracy of 95.6% for detection of crashes and near crashes, which was 2.5% higher than the optimal CNN using 20% hold out test data. The ensemble CNN also outperformed classical machine learning models and model performance reported in past studies on detection of SCEs. These results have implications for identification of safety hotspots and providing real-time alerts and warnings in connected and highly automated vehicle environment including society of automotive engineers levels 3–5.

Quantitative Neuromuscular Monitoring in Clinical Practice: A Professional Practice Change Initiative.

Residual neuromuscular blockade can be avoided with quantitative neuromuscular monitoring. The authors embarked on a professional practice initiative to attain documented train-of-four ratios greater than or equal to 0.90 in all patients for improved patient outcomes through reducing residual paralysis. The authors utilized equipment trials, educational videos, quantitative monitors in all anesthetizing locations, and electronic clinical decision support with real-time alerts, and initiated an ongoing professional practice metric. This was a retrospective assessment (2016 to 2020) of train-of-four ratios greater than or equal to 0.9 that were documented before extubation. Anesthesia records were manually reviewed for neuromuscular blockade management details. Medical charts of surgical patients who received a neuromuscular blocking drug were electronically searched for patient characteristics and outcomes. From pre- to postimplementation, more patients were assigned American Society of Anesthesiologists Physical Status III to V, fewer were inpatients, the rocuronium average dose was higher, and more patients had a prereversal train-of-four count less than 4. Manually reviewed anesthesia records (n = 2,807) had 2 of 172 (1%) cases with documentation of train-of-four ratios greater than or equal to 0.90 in November 2016, which was fewer than the cases in December 2020 (250 of 269 [93%]). Postimplementation (February 1, 2020, to December 31, 2020), sugammadex (650 of 935 [70%]), neostigmine (195 of 935 [21%]), and no reversal (90 of 935 [10%]) were used to attain train-of-four ratios greater than or equal to 0.90 in 856 of 935 (92%) of patients. In the electronically searched medical charts (n = 20,181), postimplementation inpatients had shorter postanesthesia care unit lengths of stay (7% difference; median [in min] [25th, 75th interquartile range], 73 [55, 102] to 68 [49, 95]; P < 0.001), pulmonary complications were less (43% difference; 94 of 4,138 [2.3%] to 23 of 1,817 [1.3%]; P = 0.010; -1.0% difference [95% CI, -1.7 to -0.3%]), and hospital length of stay was shorter (median [in days] [25th, 75th], 3 [2, 5] to 2 [1, 4]; P < 0.001). In this professional practice initiative, documentation of train-of-four ratios greater than or equal to 0.90 occurred for 93% of patients in a busy clinical practice. Return-of-strength documentation is an intermediate outcome, and only one of many factors contributing to patient outcomes.

Simulações virtuais para educação em saúde: como são avaliadas as habilidades do usuário?

Abstract: Introduction: A virtual simulator, or one based on virtual reality, can computationally recreate real contexts. Objective: To analyze works on virtual simulations for training clinical procedures, focusing on the assessment of user skills. Method: Integrative literature review, carried out between 2010 and 2020. A total of 56 studies were selected 56 studies. Results: The selected studies showed that the variables and parameters of virtual simulators are usually obtained by consulting experts or through medical literature. These simulators mainly focus on developing psychomotor skills and assessing the learner’s performance through real-time alerts, progress indicators, and performance reports after the end of each training. Conclusion: Considering the expert’s knowledge exclusively to define the requirements of virtual simulators can limit their reliability and accuracy. The participation of experts in these projects does not follow standards regarding the selection and frequency with which they collaborate. Few simulators provide insightful and pertinent feedback on user performance.

Applying Apache Spark on Streaming Big Data for Health Status Prediction

Big data applications in healthcare have provided a variety of solutions to reduce costs, errors, and waste. This work aims to develop a real-time system based on big medical data processing in the cloud for the prediction of health issues. In the proposed scalable system, medical parameters are sent to Apache Spark to extract attributes from data and apply the proposed machine learning algorithm. In this way, healthcare risks can be predicted and sent as alerts and recommendations to users and healthcare providers. The proposed work also aims to provide an effective recommendation system by using streaming medical data, historical data on a user’s profile, and a knowledge database to make the most appropriate real-time recommendations and alerts based on the sensor’s measurements. This proposed scalable system works by tweeting the health status attributes of users. Their cloud profile receives the streaming healthcare data in real time by extracting the health attributes via a machine learning prediction algorithm to predict the users’ health status. Subsequently, their status can be sent on demand to healthcare providers. Therefore, machine learning algorithms can be applied to stream health care data from wearables and provide users with insights into their health status. These algorithms can help healthcare providers and individuals focus on health risks and health status changes and consequently improve the quality of life.

Comparison of two electronic hand hygiene systems using real-time feedback via wireless technology to improve hand hygiene compliance in an intensive care unit.

Most hand hygiene (HH) intervention studies use a quasi-experimental design, are primarily uncontrolled before-and-after studies, or are controlled before-and-after studies with a nonequivalent control group. Well-funded studies with improved designs and HH interventions are needed. To evaluate healthcare worker (HCW) HH compliance with alcohol-based hand rub (ABHR) through direct observation (human observer), 2 electronic technologies, a radio frequency identification (RFID) badge system, and an invasive device sensor. In our controlled experimental study, 2,269 observations were made over a 6-month period from July 1 to December 30, 2020, in a 4-bed intensive care unit. We compared HH compliance between a basic feedback loop system with RFID badges and an enhanced feedback loop system that utilized sensors on invasive devices. Real-time feedback by wireless technology connected to a patient's invasive device (enhanced feedback loop) resulted in a significant increase in HH compliance (69.5% in the enhanced group vs 59.1% in the basic group; P = .0001). An enhanced feedback loop system connected to invasive devices, providing real-time alerts to HCWs, is effective in improving HH compliance.