Implementation of Lightweight Convolutional Neural Networks with an Early Exit Mechanism Utilizing 40 nm CMOS Process for Fire Detection in Unmanned Aerial Vehicles

The advancement of unmanned aerial vehicles (UAVs) enables early detection of numerous disasters. Efforts have been made to automate the monitoring of data from UAVs, with machine learning methods recently attracting significant interest. These solutions often face challenges with high computational costs and energy usage. Conventionally, data from UAVs are processed using cloud computing, where they are sent to the cloud for analysis. However, this method might not meet the real-time needs of disaster relief scenarios. In contrast, edge computing provides real-time processing at the site but still struggles with computational and energy efficiency issues. To overcome these obstacles and enhance resource utilization, this paper presents a convolutional neural network (CNN) model with an early exit mechanism designed for fire detection in UAVs. This model is implemented using TSMC 40 nm CMOS technology, which aids in hardware acceleration. Notably, the neural network has a modest parameter count of 11.2 k. In the hardware computation part, the CNN circuit completes fire detection in approximately 230,000 cycles. Power-gating techniques are also used to turn off inactive memory, contributing to reduced power consumption. The experimental results show that this neural network reaches a maximum accuracy of 81.49% in the hardware implementation stage. After automatic layout and routing, the CNN hardware accelerator can operate at 300 MHz, consuming 117 mW of power.

Implementation and analysis of a parallel kalman filter algorithm for lidar localization based on CUDA technology

Introduction: Navigation satellite systems can fail to work or work incorrectly in a number of conditions: signal shadowing, electromagnetic interference, atmospheric conditions, and technical problems. All of these factors can significantly affect the localization accuracy of autonomous driving systems. This emphasizes the need for other localization technologies, such as Lidar. Methods: The use of the Kalman filter in combination with Lidar can be very effective in various applications due to the synergy of their capabilities. The Kalman filter can improve the accuracy of lidar measurements by taking into account the noise and inaccuracies present in the measurements. Results: In this paper, we propose a parallel Kalman algorithm in three-dimensional space to speed up the computational speed of Lidar localization. At the same time, the initial localization accuracy of the latter is preserved. A distinctive feature of the proposed approach is that the Kalman localization algorithm itself is parallelized, rather than the process of building a map for navigation. The proposed algorithm allows us to obtain the result 3.8 times faster without compromising the localization accuracy, which was 3% for both cases, making it effective for real-time decision-making. Discussion: The reliability of this result is confirmed by a preliminary theoretical estimate of the acceleration rate based on Ambdahl's law. Accelerating the Kalman filter with CUDA for Lidar localization can be of significant practical value, especially in real-time and in conditions where large amounts of data from Lidar sensors need to be processed.

A Real-Time Vessel Detection and Tracking System Based on LiDAR

Vessel detection and tracking is of utmost importance to river traffic. Efficient detection and tracking technology offer an effective solution to address challenges related to river traffic safety and congestion. Traditional image-based object detection and tracking algorithms encounter issues such as target ID switching, difficulties in feature extraction, reduced robustness due to occlusion, target overlap, and changes in brightness and contrast. To detect and track vessels more accurately, a vessel detection and tracking algorithm based on the LiDAR point cloud was proposed. For vessel detection, statistical filtering algorithms were integrated into the Euclidean clustering algorithm to mitigate the effect of ripples on vessel detection. Our detection accuracy of vessels improved by 3.3% to 8.3% compared to three conventional algorithms. For vessel tracking, L-shape fitting of detected vessels can improve the efficiency of tracking, and a simple and efficient tracking algorithm is presented. By comparing three traditional tracking algorithms, an improvement in multiple object tracking accuracy (MOTA) and a reduction in ID switch times and number of missed detections were achieved. The results demonstrate that LiDAR point cloud-based vessel detection can significantly enhance the accuracy of vessel detection and tracking.

CNN Hardware Accelerator for Real-Time Bearing Fault Diagnosis

This paper introduces a one-dimensional convolutional neural network (CNN) hardware accelerator. It is crafted to conduct real-time assessments of bearing conditions using economical hardware components, implemented on a field-programmable gate array evaluation platform, negating the necessity to transfer data to a cloud-based server. The adoption of the down-sampling technique augments the visible time span of the signal in an image, thereby enhancing the accuracy of the bearing condition diagnosis. Furthermore, the proposed method of quaternary quantization enhances precision and shrinks the memory demand for the neural network model by an impressive 89%. Provided that the current signal data sampling rate stands at 64 K samples/s, the proposed design can accomplish real-time fault diagnosis at a clock frequency of 100 MHz. Impressively, the response duration of the proposed CNN hardware system is a mere 0.28 s, with the fault diagnosis precision reaching a remarkable 96.37%.

A Real-Time Endoscope Motion Tracker

OBJECTIVE

In colonoscopy, it is desirable to accurately localize the position of the endoscope's distal tip. Current tip localization techniques are not sufficient for recording the position and movement of the tip, nor is its rotation measured. We hypothesize that integration of multiple tracking modalities can effectively record the endoscope's motion in real time and continuously corrects cumulative errors.

METHODS

A dual modality tracking method is developed to measure the motion of the endoscope's insertion tube in real time, including insertion length, rotation angle, and their velocities. Optical trackballs were used to measure the endoscope insertion tube's motion and cameras were used to correct cumulative errors.

RESULTS

The accuracy of insertion length and rotational angle were measured. For speeds ≤ 10 mm/s, the median and 90th percentile insertion position errors were 0.88 mm and 2.2 mm, respectively. The insertion position error increases with the speed, reaching a maximum of 10 mm for speeds < 40 mm/s. 11° and 21° were the median and 90th percentile rotation angle errors for angular speeds < 40°/s. Cumulative errors are sufficiently reduced by the imaging modality.

CONCLUSION

The prototype device can precisely measure an unmodified endoscope's position, rotation, and motion in real time without significant accumulative error. The prototype device is small and compatible with existing commercial endoscopes as an add-on accessory, which could be used for reporting, localizing the lesions in follow up procedures, operational guidance, quality assurance, and training. Clinical and Translational Impact Statement-This preclinical research develops an endoscope tracker that can be integrated into colonoscopy training, automatically record endoscope motion, and be further developed to improve polyp and tumor localization during colonoscopy.

Using Python Modules in Real-Time Plasma Systems for Fusion

One of the most important applications of sensors is feedback control, in which an algorithm is applied to data that are collected from sensors in order to drive system actuators and achieve the desired outputs of the target plant. One of the most challenging applications of this control is represented by magnetic confinement fusion, in which real-time systems are responsible for the confinement of plasma at a temperature of several million degrees within a toroidal container by means of strong electromagnetic fields. Due to the fast dynamics of the underlying physical phenomena, data that are collected from electromagnetic sensors must be processed in real time. In most applications, real-time systems are implemented in C++; however, Python applications are now becoming more and more widespread, which has raised potential interest in their applicability in real-time systems. In this study, a framework was set up to assess the applicability of Python in real-time systems. For this purpose, a reference operating system configuration was chosen, which was optimized for real time, together with a reference framework for real-time data management. Within this framework, the performance of modules that computed PID control and FFT transforms was compared for C++ and Python implementations, respectively. Despite the initial concerns about Python applicability in real-time systems, it was found that the worst-case execution time (WCET) could also be safely defined for modules that were implemented in Python, thereby confirming that they could be considered for real-time applications.

GPU-Accelerated PD-IPM for Real-Time Model Predictive Control in Integrated Missile Guidance and Control Systems

This paper addresses the problem of real-time model predictive control (MPC) in the integrated guidance and control (IGC) of missile systems. When the primal-dual interior point method (PD-IPM), which is a convex optimization method, is used as an optimization solution for the MPC, the real-time performance of PD-IPM degenerates due to the elevated computation time in checking the Karush-Kuhn-Tucker (KKT) conditions in PD-IPM. This paper proposes a graphics processing unit (GPU)-based method to parallelize and accelerate PD-IPM for real-time MPC. The real-time performance of the proposed method was tested and analyzed on a widely-used embedded system. The comparison results with the conventional PD-IPM and other methods showed that the proposed method improved the real-time performance by reducing the computation time significantly.

Real-Time Multirate Multiband Amplification for Hearing Aids

Hearing loss is a common problem affecting the quality of life for thousands of people. However, many individuals with hearing loss are dissatisfied with the quality of modern hearing aids. Amplification is the main method of compensating for hearing loss in modern hearing aids. One common amplification technique is dynamic range compression, which maps audio signals onto a person's hearing range using an amplification curve. However, due to the frequency dependent nature of the human cochlea, compression is often performed independently in different frequency bands. This paper presents a real-time multirate multiband amplification system for hearing aids, which includes a multirate channelizer for separating an audio signal into eleven standard audiometric frequency bands, and an automatic gain control system for accurate control of the steady state and dynamic behavior of audio compression as specified by ANSI standards. The spectral channelizer offers high frequency resolution with low latency of 5.4 ms and about 14× improvement in complexity over a baseline design. Our automatic gain control includes a closed-form solution for satisfying any designated attack and release times for any desired compression parameters. The increased frequency resolution and precise gain adjustment allow our system to more accurately fulfill audiometric hearing aid prescriptions.

Real-Time System for Daily Modal Split Estimation and OD Matrices Generation Using IoT Data: A Case Study of Tartu City

In recent years, we have witnessed the emergence of the implementation and integration of significant working solutions in transportation, especially within the smart city concept. A lot of cities in Europe and around the world support this initiative of making their cities smarter for enhanced mobility and a sustainable environment. In this paper, we present a case study of Tartu city, where we developed and designed a daily real-time system for extracting and performing a modal split analysis. Our web-based platform relied on an optimization approach for calibrating our simulation in order to perform the analysis with the use of real data streams from IoT devices installed around the city. The results obtained from our system demonstrated acceptable performance versus the quality of the available data source. In addition, our platform provides downloadable OD matrices for each mode of mobility for the community.

Task Migration and Scheduler for Mixed-Criticality Systems

The interference between software components is increasing in safety-critical domains, such as autonomous driving. Low-criticality (LC) tasks, such as vehicle communication, may control high-criticality (HC) tasks, such as acceleration. In such cases, the LC task should also be considered as an HC task because the HC tasks relies on the LC task. However, the difficulty in guaranteeing these LC tasks is the catastrophic cost of computing resources, the electronic control unit in the domain of vehicles, required for every task. In this paper, we theoretically and practically provide safety-guaranteed and inexpensive scheduling for LC tasks by borrowing the computational power of neighbored systems in distributed systems, obviating the need for additional hardware components. As a result, our approach extended the schedulability of LC tasks without violating the HC tasks. Based on the deadline test, the compatibility of our approach with the task-level MC scheduler was higher than that of the system-level MC scheduler, such that the task-level had all dropped LC tasks recovered while the system-level only had 25.5% recovery. Conversely, from the worst-case measurement of violated HC tasks, the HC tasks were violated by the task-level MC scheduler more often than by the system-level MC scheduler, with 70.3% and 15.4% average response time overhead, respectively. In conclusion, under the condition that the HC task ratio has lower than 47% of the overall task systems at 80% of total utilization, the task-level approach with task migration has extensively higher sustainability on LC tasks.

Partnering a Compensatory Application with Activity-Aware Prompting to Improve Use in Individuals with Amnestic Mild Cognitive Impairment: A Randomized Controlled Pilot Clinical Trial

BACKGROUND

Compensatory aids can help mitigate the impact of progressive cognitive impairment on daily living.

OBJECTIVE

We evaluate whether the learning and sustained use of an Electronic Memory and Management Aid (EMMA) application can be augmented through a partnership with real-time, activity-aware transition-based prompting delivered by a smart home.

METHODS

Thirty-two adults who met criteria for amnestic mild cognitive impairment (aMCI) were randomized to learn to use the EMMA app on its own (N = 17) or when partnered with smart home prompting (N = 15). The four-week, five-session manualized EMMA training was conducted individually in participant homes by trained clinicians. Monthly questionnaires were completed by phone with trained personnel blind to study hypotheses. EMMA data metrics were collected continuously for four months. For the partnered condition, activity-aware prompting was on during training and post-training months 1 and 3, and off during post-training month 2.

RESULTS

The analyzed aMCI sample included 15 EMMA-only and 14 partnered. Compared to the EMMA-only condition, by week four of training, participants in the partnered condition were engaging with EMMA more times daily and using more basic and advanced features. These advantages were maintained throughout the post-training phase with less loss of EMMA app use over time. There was little differential impact of the intervention on self-report primary (everyday functioning, quality of life) and secondary (coping, satisfaction with life) outcomes.

CONCLUSION

Activity-aware prompting technology enhanced acquisition, habit formation and long-term use of a digital device by individuals with aMCI. (ClinicalTrials.gov NCT03453554).

Efficient Face Recognition System for Operating in Unconstrained Environments

Facial recognition is fundamental for a wide variety of security systems operating in real-time applications. Recently, several deep neural networks algorithms have been developed to achieve state-of-the-art performance on this task. The present work was conceived due to the need for an efficient and low-cost processing system, so a real-time facial recognition system was proposed using a combination of deep learning algorithms like FaceNet and some traditional classifiers like SVM, KNN, and RF using moderate hardware to operate in an unconstrained environment. Generally, a facial recognition system involves two main tasks: face detection and recognition. The proposed scheme uses the YOLO-Face method for the face detection task which is a high-speed real-time detector based on YOLOv3, while, for the recognition stage, a combination of FaceNet with a supervised learning algorithm, such as the support vector machine (SVM), is proposed for classification. Extensive experiments on unconstrained datasets demonstrate that YOLO-Face provides better performance when the face under an analysis presents partial occlusion and pose variations; besides that, it can detect small faces. The face detector was able to achieve an accuracy of over 89.6% using the Honda/UCSD dataset which runs at 26 FPS with darknet-53 to VGA-resolution images for classification tasks. The experimental results have demonstrated that the FaceNet+SVM model was able to achieve an accuracy of 99.7% using the LFW dataset. On the same dataset, FaceNet+KNN and FaceNet+RF achieve 99.5% and 85.1%, respectively; on the other hand, the FaceNet was able to achieve 99.6%. Finally, the proposed system provides a recognition accuracy of 99.1% and 49 ms runtime when both the face detection and classifications stages operate together.

A Low-Cost, Point-of-Care Test for Confirmation of Nasogastric Tube Placement via Magnetic Field Tracking

In this work, we aim to achieve low-cost real-time tracking for nasogastric tube (NGT) insertion by using a tracking method based on two magnetic sensors. Currently, some electromagnetic (EM) tracking systems used to detect the misinsertion of the NGT are commercially available. While the EM tracking systems can be advantageous over the other conventional methods to confirm the NGT position, their high costs are a factor hindering such systems from wider acceptance in the clinical community. In our approach, a pair of magnetic sensors are used to estimate the location of a permanent magnet embedded at the tip of the NGT. As the cost of the magnet and magnetic sensors is low, the total cost of the system can be less than one-tenth of that of the EM tracking systems. The experimental results exhibited that tracking can be achieved with a root mean square error (RMSE) of 2-5 mm and indicated a great potential for use as a point-of-care test for NGT insertion, to avoid misplacement into the lung and ensure correct placement in the stomach.

An intelligent indoor guidance and navigation system for the visually impaired

Intelligent guidance in complex environments where various procedures are required for navigation is critical to achieving mobility for the visually impaired. This study presents a newly developed software prototype with a hybrid RFID/BLE infrastructure to provide intelligent navigation and guidance to the visually impaired in complex indoor environments. The system enables the users to input their purpose via a specially designed user interface, and provides intelligent guidance through a chain of destination targets which are determined according to the inherent procedures of the environment. Path optimization is performed by adaptation of the traveling salesman problem, and real-time instantaneous instructions are provided to guide the users through the predetermined destination points. For evaluation purposes, a hospital environment is constructed as an example of a complex environment and the system is tested by visually impaired participants. The results show that the intelligent purpose selection and destination evaluation mechanism modules of the system are found to be effective by all the participants.

Adoption of Digital Health Technologies in the Practice of Behavioral Health: Qualitative Case Study of Glucose Monitoring Technology

Background

Evaluation of patients with serious mental illness (SMI) relies largely on patient or caregiver self-reported symptoms. New digital technologies are being developed to better quantify the longitudinal symptomology of patients with SMI and facilitate disease management. However, as these new technologies become more widely available, psychiatrists may be uncertain about how to integrate them into daily practice. To better understand how digital tools might be integrated into the treatment of patients with SMI, this study examines a case study of a successful technology adoption by physicians: endocrinologists’ adoption of digital glucometers.

Objective

This study aims to understand the key facilitators of and barriers to clinician and patient adoption of digital glucose monitoring technologies to identify lessons that may be applicable across other chronic diseases, including SMIs.

Methods

We conducted focus groups with practicing endocrinologists from 2 large metropolitan areas using a semistructured discussion guide designed to elicit perspectives of and experiences with technology adoption. The thematic analysis identified barriers to and facilitators of integrating digital glucometers into clinical practice. Participants also provided recommendations for integrating digital health technologies into clinical practice more broadly.

Results

A total of 10 endocrinologists were enrolled: 60% (6/10) male; a mean of 18.4 years in practice (SD 5.6); and 80% (8/10) working in a group practice setting. Participants stated that digital glucometers represented a significant change in the treatment paradigm for diabetes care and facilitated more effective care delivery and patient engagement. Barriers to the adoption of digital glucometers included lack of coverage, provider reimbursement, and data management support, as well as patient heterogeneity. Participant recommendations to increase the use of digital health technologies included expanding reimbursement for clinician time, streamlining data management processes, and customizing the technologies to patient needs.

Conclusions

Digital glucose monitoring technologies have facilitated more effective, individualized care delivery and have improved patient engagement and health outcomes. However, key challenges faced by the endocrinologists included lack of reimbursement for clinician time and nonstandardized data management across devices. Key recommendations that may be relevant for other diseases include improved data analytics to quickly and accurately synthesize data for patient care management, streamlined software, and standardized metrics.

Spatio-Temporal Scale Coded Bag-of-Words

The Bag-of-Words (BoW) framework has been widely used in action recognition tasks due to its compact and efficient feature representation. Various modifications have been made to this framework to increase its classification power. This often results in an increased complexity and reduced efficiency. Inspired by the success of image-based scale coded BoW representations, we propose a spatio-temporal scale coded BoW (SC-BoW) for video-based recognition. This involves encoding extracted multi-scale information into BoW representations by partitioning spatio-temporal features into sub-groups based on the spatial scale from which they were extracted. We evaluate SC-BoW in two experimental setups. We first present a general pipeline to perform real-time action recognition with SC-BoW. Secondly, we apply SC-BoW onto the popular Dense Trajectory feature set. Results showed SC-BoW representations to successfully improve performance by 2-7% with low added computational cost. Notably, SC-BoW on Dense Trajectories outperformed more complex deep learning approaches. Thus, scale coding is a low-cost and low-level encoding scheme that increases classification power of the standard BoW without compromising efficiency.

Real-Time Traffic Light Detection with Frequency Patterns Using a High-speed Camera

LEDs are widely employed as traffic lights. Because most LED traffic lights are driven by alternative power, they blink at high frequencies, even at twice their frequencies. We propose a method to detect a traffic light from images captured by a high-speed camera that can recognize a blinking traffic light. This technique is robust under various illuminations because it can detect traffic lights by extracting information from the blinking pixels at a specific frequency. The method is composed of six modules, which includes a band-pass filter and a Kalman filter. All the modules run simultaneously to achieve real-time processing and can run at 500 fps for images with a resolution of 800 × 600. This technique was verified on an original dataset captured by a high-speed camera under different illumination conditions such as a sunset or night scene. The recall and accuracy justify the generalization of the proposed detection system. In particular, it can detect traffic lights with a different appearance without tuning parameters and without datasets having to be learned.

Real-Time Hand Gesture Recognition Using Surface Electromyography and Machine Learning: A Systematic Literature Review

Today, daily life is composed of many computing systems, therefore interacting with them in a natural way makes the communication process more comfortable. Human-Computer Interaction (HCI) has been developed to overcome the communication barriers between humans and computers. One form of HCI is Hand Gesture Recognition (HGR), which predicts the class and the instant of execution of a given movement of the hand. One possible input for these models is surface electromyography (EMG), which records the electrical activity of skeletal muscles. EMG signals contain information about the intention of movement generated by the human brain. This systematic literature review analyses the state-of-the-art of real-time hand gesture recognition models using EMG data and machine learning. We selected and assessed 65 primary studies following the Kitchenham methodology. Based on a common structure of machine learning-based systems, we analyzed the structure of the proposed models and standardized concepts in regard to the types of models, data acquisition, segmentation, preprocessing, feature extraction, classification, postprocessing, real-time processing, types of gestures, and evaluation metrics. Finally, we also identified trends and gaps that could open new directions of work for future research in the area of gesture recognition using EMG.

UAV Landing Using Computer Vision Techniques for Human Detection

The capability of drones to perform autonomous missions has led retail companies to use them for deliveries, saving time and human resources. In these services, the delivery depends on the Global Positioning System (GPS) to define an approximate landing point. However, the landscape can interfere with the satellite signal (e.g., tall buildings), reducing the accuracy of this approach. Changes in the environment can also invalidate the security of a previously defined landing site (e.g., irregular terrain, swimming pool). Therefore, the main goal of this work is to improve the process of goods delivery using drones, focusing on the detection of the potential receiver. We developed a solution that has been improved along its iterative assessment composed of five test scenarios. The built prototype complements the GPS through Computer Vision (CV) algorithms, based on Convolutional Neural Networks (CNN), running in a Raspberry Pi 3 with a Pi NoIR Camera (i.e., No InfraRed—without infrared filter). The experiments were performed with the models Single Shot Detector (SSD) MobileNet-V2, and SSDLite-MobileNet-V2. The best results were obtained in the afternoon, with the SSDLite architecture, for distances and heights between 2.5–10 m, with recalls from 59%–76%. The results confirm that a low computing power and cost-effective system can perform aerial human detection, estimating the landing position without an additional visual marker.

Novel navigation assistive device for deaf drivers

There are over 466 million people in the world with disabling hearing loss. People with severe-to-profound hearing impairment need to lipread or use sign language, even with hearing aids. Assistive Technologies play a vital role in helping these people interact efficiently with their environment. Deaf drivers are not currently able to take full advantage of voice-based navigation applications. In this paper, we describe research that is aimed at developing an assistive device that (1) recognizes voice-stream navigation instructions from GPS-based navigation applications, and (2) maps each voiced navigation instruction to a vibrotactile stimulus that can be perceived and understood by deaf drivers. A 13-element feature vector is extracted from each voice stream, and classified into one of six categories, where each category represents a unique navigation instruction. The classification of the feature vectors is done using a K-Nearest-Neighbor classifier (with an accuracy of 99.05%) which was found to outperform five other classifiers. Each category is then mapped to a unique vibration pattern, which drives vibration motors in real time. A usability study was conducted with ten participants. Three different alternatives were tested, to find the best body locations for mounting the vibration motors. The solution ultimately chosen was two sets of five vibrator motors, where each set was mounted on a bracelet. Ten drivers were asked to rate the proposed device (based on eight different factors) after they used the assistive device on 8 driving routes. The overall mean rating across all eight factors was 4.67 (out of 5) This indicates that the proposed assistive device was seen as useful and effective.

Design of Lightweight Driver-Assistance System for Safe Driving in Electric Vehicles

Electric-vehicle technology is an emerging area offering several benefits such as economy due to low running costs. Electric vehicles can also help to significantly reduce CO₂ emission, which is a vital factor for environmental pollution. Modern vehicles are equipped with driver-assistance systems that facilitate drivers by offloading some of the tasks a driver does while driving. Human beings are prone to errors. Therefore, accidents and fatalities can happen if the driver fails to perform a particular task within the deadline. In electric vehicles, the focus has always been to optimize the power and battery life, and thus, any additional hardware can affect their battery life significantly. In this paper, the design of driver-assistance systems has been introduced to automate and assist in some of the vital tasks, such as a braking system, in an optimized manner. We revamp the idea of the traditional driver-assistance system and propose a generic lightweight system based on the leading factors and their impact on accidents. We model tasks for these factors and simulate a low-cost driver-assistance system in a real-time context, where these scenarios are investigated and tasks schedulability is formally proved before deploying them in electric vehicles. The proposed driver-assistance system offers many advantages. It decreases the risk of accidents and monitors the safety of driving. If, at some point, the risk index is above a certain threshold, an automated control algorithm is triggered to reduce it by activating different actuators. At the same time, it is lightweight and does not require any dedicated hardware, which in turn has a significant advantage in terms of battery life. Results show that the proposed system not only is accurate but also has a very negligible effect on energy consumption and battery life.

Data Challenges With Real-Time Safety Event Detection And Clinical Decision Support

Background

The continued digitization and maturation of health care information technology has made access to real-time data easier and feasible for more health care organizations. With this increased availability, the promise of using data to algorithmically detect health care–related events in real-time has become more of a reality. However, as more researchers and clinicians utilize real-time data delivery capabilities, it has become apparent that simply gaining access to the data is not a panacea, and some unique data challenges have emerged to the forefront in the process.

Objective

The aim of this viewpoint was to highlight some of the challenges that are germane to real-time processing of health care system–generated data and the accurate interpretation of the results.

Methods

Distinct challenges related to the use and processing of real-time data for safety event detection were compiled and reported by several informatics and clinical experts at a quaternary pediatric academic institution. The challenges were collated from the experiences of the researchers implementing real-time event detection on more than half a dozen distinct projects. The challenges have been presented in a challenge category-specific challenge-example format.

Results

In total, 8 major types of challenge categories were reported, with 13 specific challenges and 9 specific examples detailed to provide a context for the challenges. The examples reported are anchored to a specific project using medication order, medication administration record, and smart infusion pump data to detect discrepancies and errors between the 3 datasets.

Conclusions

The use of real-time data to drive safety event detection and clinical decision support is extremely powerful, but it presents its own set of challenges that include data quality and technical complexity. These challenges must be recognized and accommodated for if the full promise of accurate, real-time safety event clinical decision support is to be realized.

Energy-Efficient IoT Service Brokering with Quality of Service Support

The Internet of Things (IoT) is becoming real, and recent studies highlight that the number of IoT devices will significantly grow in the next decade. Such massive IoT deployments are typically made available to applications as a service by means of IoT platforms, which are aware of the characteristics of the connected IoT devices⁻usually constrained in terms of computation, storage and energy capabilities⁻and dispatch application's service requests to appropriate devices based on their capabilities. In this work, we develop an energy-aware allocation policy that aims at maximizing the lifetime of all the connected IoT devices, whilst guaranteeing that applications' Quality of Service (QoS) requirements are met. To this aim, we formally define an IoT service allocation problem as a non-linear Generalized Assignment Problem (GAP). We then develop a time-efficient heuristic algorithm to solve the problem, which is shown to find near-optimal solutions by exploiting the availability of equivalent IoT services provided by multiple IoT devices, as expected especially in the case of massive IoT deployments.

Securing Real-Time Internet-of-Things

Modern embedded and cyber-physical systems are ubiquitous. Many critical cyber-physical systems have real-time requirements (e.g., avionics, automobiles, power grids, manufacturing systems, industrial control systems, etc.). Recent developments and new functionality require real-time embedded devices to be connected to the Internet. This gives rise to the real-time Internet-of-things (RT-IoT) that promises a better user experience through stronger connectivity and efficient use of next-generation embedded devices. However, RT-IoT are also increasingly becoming targets for cyber-attacks, which is exacerbated by this increased connectivity. This paper gives an introduction to RT-IoT systems, an outlook of current approaches and possible research challenges towards secure RT-IoT frameworks.

A New Method of Priority Assignment for Real-Time Flows in the WirelessHART Network by the TDMA Protocol

WirelessHART is a wireless sensor network that is widely used in real-time demand analyses. A key challenge faced by WirelessHART is to ensure the character of real-time data transmission in the network. Identifying a priority assignment strategy that reduces the delay in flow transmission is crucial in ensuring real-time network performance and the schedulability of real-time network flows. We study the priority assignment of real-time flows in WirelessHART on the basis of the multi-channel time division multiple access (TDMA) protocol to reduce the delay and improve the ratio of scheduled. We provide three kinds of methods: (1) worst fit, (2) best fit, and (3) first fit and choose the most suitable one, namely the worst-fit method for allocating flows to each channel. More importantly, we propose two heuristic algorithms-a priority assignment algorithm based on the greedy strategy for C (WF-C) and a priority assignment algorithm based on the greedy strategy for U(WF-U)-for assigning priorities to the flows in each channel, whose time complexity is O ( m a x ( N &lowast; m &lowast; l o g ( m ) , ( N - m ) 2 ) ) . We then build a new simulation model to simulate the transmission of real-time flows in WirelessHART. Finally, we compare our two algorithms with WF-D and HLS algorithms in terms of the average value of the total end-to-end delay of flow sets, the ratio of schedulable flow sets, and the calculation time of the schedulability analysis. The optimal algorithm WF-C reduces the delay by up to 44.18 % and increases the schedulability ratio by up to 70.7 % , and it reduces the calculation time compared with the HLS algorithm.

Automated Modular Magnetic Resonance Imaging Clinical Decision Support System (MIROR): An Application in Pediatric Cancer Diagnosis

BACKGROUND

Advances in magnetic resonance imaging and the introduction of clinical decision support systems has underlined the need for an analysis tool to extract and analyze relevant information from magnetic resonance imaging data to aid decision making, prevent errors, and enhance health care.

OBJECTIVE

The aim of this study was to design and develop a modular medical image region of interest analysis tool and repository (MIROR) for automatic processing, classification, evaluation, and representation of advanced magnetic resonance imaging data.

METHODS

The clinical decision support system was developed and evaluated for diffusion-weighted imaging of body tumors in children (cohort of 48 children, with 37 malignant and 11 benign tumors). Mevislab software and Python have been used for the development of MIROR. Regions of interests were drawn around benign and malignant body tumors on different diffusion parametric maps, and extracted information was used to discriminate the malignant tumors from benign tumors.

RESULTS

Using MIROR, the various histogram parameters derived for each tumor case when compared with the information in the repository provided additional information for tumor characterization and facilitated the discrimination between benign and malignant tumors. Clinical decision support system cross-validation showed high sensitivity and specificity in discriminating between these tumor groups using histogram parameters.

CONCLUSIONS

MIROR, as a diagnostic tool and repository, allowed the interpretation and analysis of magnetic resonance imaging images to be more accessible and comprehensive for clinicians. It aims to increase clinicians' skillset by introducing newer techniques and up-to-date findings to their repertoire and make information from previous cases available to aid decision making. The modular-based format of the tool allows integration of analyses that are not readily available clinically and streamlines the future developments.

Error Recovery in the Time-Triggered Paradigm with FTT-CAN

Data networks are naturally prone to interferences that can corrupt messages, leading to performance degradation or even to critical failure of the corresponding distributed system. To improve resilience of critical systems, time-triggered networks are frequently used, based on communication schedules defined at design-time. These networks offer prompt error detection, but slow error recovery that can only be compensated with bandwidth overprovisioning. On the contrary, the Flexible Time-Triggered (FTT) paradigm uses online traffic scheduling, which enables a compromise between error detection and recovery that can achieve timely recovery with a fraction of the needed bandwidth. This article presents a new method to recover transmission errors in a time-triggered Controller Area Network (CAN) network, based on the Flexible Time-Triggered paradigm, namely FTT-CAN. The method is based on using a server (traffic shaper) to regulate the retransmission of corrupted or omitted messages. We show how to design the server to simultaneously: (1) meet a predefined reliability goal, when considering worst case error recovery scenarios bounded probabilistically by a Poisson process that models the fault arrival rate; and, (2) limit the direct and indirect interference in the message set, preserving overall system schedulability. Extensive simulations with multiple scenarios, based on practical and randomly generated systems, show a reduction of two orders of magnitude in the average bandwidth taken by the proposed error recovery mechanism, when compared with traditional approaches available in the literature based on adding extra pre-defined transmission slots.

Real-time geometry-aware augmented reality in minimally invasive surgery

The potential of augmented reality (AR) technology to assist minimally invasive surgery (MIS) lies in its computational performance and accuracy in dealing with challenging MIS scenes. Even with the latest hardware and software technologies, achieving both real-time and accurate augmented information overlay in MIS is still a formidable task. In this Letter, the authors present a novel real-time AR framework for MIS that achieves interactive geometric aware AR in endoscopic surgery with stereo views. The authors' framework tracks the movement of the endoscopic camera and simultaneously reconstructs a dense geometric mesh of the MIS scene. The movement of the camera is predicted by minimising the re-projection error to achieve a fast tracking performance, while the three-dimensional mesh is incrementally built by a dense zero mean normalised cross-correlation stereo-matching method to improve the accuracy of the surface reconstruction. The proposed system does not require any prior template or pre-operative scan and can infer the geometric information intra-operatively in real time. With the geometric information available, the proposed AR framework is able to interactively add annotations, localisation of tumours and vessels, and measurement labelling with greater precision and accuracy compared with the state-of-the-art approaches.

Dedicated real-time monitoring system for health care using ZigBee

Real-time monitoring systems (RTMSs) have drawn considerable attentions in the last decade. Several commercial versions of RTMS for patient monitoring are available which are used by health care professionals. Though they are working satisfactorily on various communication protocols, their range, power consumption, data rate and cost are really bothered. In this study, the authors present an efficient embedded system based wireless health care monitoring system using ZigBee. Their system has a capability to transmit the data between two embedded systems through two transceivers over a long range. In this, wireless transmission has been applied through two categories. The first part which contains Arduino with ZigBee will send the signals to the second device, which contains Raspberry with ZigBee. The second device will measure the patient data and send it to the first device through ZigBee transceiver. The designed system is demonstrated on volunteers to measure the body temperature which is clinically important to monitor and diagnose for fever in the patients.

Internet as a Source of Long-Term and Real-Time Professional, Psychological, and Nutritional Treatment: A Qualitative Case Study Among Former Israeli Soviet Union Immigrants

Background

The Internet is considered to be an effective source of health information and consultation for immigrants. Nutritional interventions for immigrants have become increasingly common over the past few decades. However, each population of immigrants has specific needs. Understanding the factors influencing the success of nutrition programs among immigrants requires an examination of their attitudes and perceptions, as well as their cultural values.

Objective

The purpose of this study was to examine perceptions of the Internet as a tool for long-term and “real-time” professional, psychological, and nutritional treatment for immigrants from the former Soviet Union who immigrated to Israel (IIFSU) from 1990 to 2012.

Methods

A sample of nutrition forum users (n=18) was interviewed and comments of 80 users were analyzed qualitatively in accordance with the grounded theory principles.

Results

The results show that IIFSU perceive the Internet as a platform for long-term and “real-time” dietary treatment and not just as an informative tool. IIFSU report benefits of online psychological support with professional dietary treatment. They attribute importance to cultural customization, which helps reduce barriers to intervention.

Conclusions

In light of the results, when formulating nutritional programs, it is essential to have a specific understanding of immigrants’ cultural characteristics and their patterns of Internet use concerning dietary care.

Sociotechnical Human Factors Involved in Remote Online Usability Testing of Two eHealth Interventions

Background

Research in the fields of human performance technology and human computer interaction are challenging the traditional macro focus of usability testing arguing for methods that help test moderators assess “use in context” (ie, cognitive skills, usability understood over time) and in authentic “real world” settings. Human factors in these complex test scenarios may impact on the quality of usability results being derived yet there is a lack of research detailing moderator experiences in these test environments. Most comparative research has focused on the impact of the physical environment on results, and rarely on how the sociotechnical elements of the test environment affect moderator and test user performance. Improving our understanding of moderator roles and experiences with conducting “real world” usability testing can lead to improved techniques and strategies

Objective

To understand moderator experiences of using Web-conferencing software to conduct remote usability testing of 2 eHealth interventions.

Methods

An exploratory case study approach was used to study 4 moderators’ experiences using Blackboard Collaborate for remote testing sessions of 2 different eHealth interventions. Data collection involved audio-recording iterative cycles of test sessions, collecting summary notes taken by moderators, and conducting 2 90-minute focus groups via teleconference. A direct content analysis with an inductive coding approach was used to explore personal accounts, assess the credibility of data interpretation, and generate consensus on the thematic structure of the results.

Results

Following the convergence of data from the various sources, 3 major themes were identified: (1) moderators experienced and adapted to unpredictable changes in cognitive load during testing; (2) moderators experienced challenges in creating and sustaining social presence and untangling dialogue; and (3) moderators experienced diverse technical demands, but were able to collaboratively troubleshoot with test users.

Conclusions

Results highlight important human-computer interactions and human factor qualities that impact usability testing processes. Moderators need an advanced skill and knowledge set to address the social interaction aspects of Web-based usability testing and technical aspects of conferencing software during test sessions. Findings from moderator-focused studies can inform the design of remote testing platforms and real-time usability evaluation processes that place less cognitive burden on moderators and test users.

Video sensor architecture for surveillance applications

This paper introduces a flexible hardware and software architecture for a smart video sensor. This sensor has been applied in a video surveillance application where some of these video sensors are deployed, constituting the sensory nodes of a distributed surveillance system. In this system, a video sensor node processes images locally in order to extract objects of interest, and classify them. The sensor node reports the processing results to other nodes in the cloud (a user or higher level software) in the form of an XML description. The hardware architecture of each sensor node has been developed using two DSP processors and an FPGA that controls, in a flexible way, the interconnection among processors and the image data flow. The developed node software is based on pluggable components and runs on a provided execution run-time. Some basic and application-specific software components have been developed, in particular: acquisition, segmentation, labeling, tracking, classification and feature extraction. Preliminary results demonstrate that the system can achieve up to 7.5 frames per second in the worst case, and the true positive rates in the classification of objects are better than 80%.

Man-machine interface system for neuromuscular training and evaluation based on EMG and MMG signals

This paper presents the UVa-NTS (University of Valladolid Neuromuscular Training System), a multifunction and portable Neuromuscular Training System. The UVa-NTS is designed to analyze the voluntary control of severe neuromotor handicapped patients, their interactive response, and their adaptation to neuromuscular interface systems, such as neural prostheses or domotic applications. Thus, it is an excellent tool to evaluate the residual muscle capabilities in the handicapped. The UVa-NTS is composed of a custom signal conditioning front-end and a computer. The front-end electronics is described thoroughly as well as the overall features of the custom software implementation. The software system is composed of a set of graphical training tools and a processing core. The UVa-NTS works with two classes of neuromuscular signals: the classic myoelectric signals (MES) and, as a novelty, the myomechanic signals (MMS). In order to evaluate the performance of the processing core, a complete analysis has been done to classify its efficiency and to check that it fulfils with the real-time constraints. Tests were performed both with healthy and selected impaired subjects. The adaptation was achieved rapidly, applying a predefined protocol for the UVa-NTS set of training tools. Fine voluntary control was demonstrated to be reached with the myoelectric signals. And the UVa-NTS demonstrated to provide a satisfactory voluntary control when applying the myomechanic signals.