Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction.

This paper proposes a novel approach to tackle the human activity recognition (HAR) problem. Four classes of body movement datasets, namely stand-up, sit-down, run, and walk, are applied to perform HAR. Instead of using vision-based solutions, we address the HAR challenge by implementing a real-time HAR system architecture with a wearable inertial measurement unit (IMU) sensor, which aims to achieve networked sensing and data sampling of human activity, data pre-processing and feature analysis, data generation and correction, and activity classification using hybrid learning models. Referring to the experimental results, the proposed system selects the pre-trained eXtreme Gradient Boosting (XGBoost) model and the Convolutional Variational Autoencoder (CVAE) model as the classifier and generator, respectively, with 96.03% classification accuracy.

Design of Edge-IoMT Network Architecture with Weight-Based Scheduling.

Population health monitoring based on the Internet of Medical Things (IoMT) is becoming an important application trend healthcare improvement. This work aims to develop an autonomous network architecture, collecting sensor data with a cluster topology, forwarding information through relay nodes, and applying edge computing and transmission scheduling for network scalability and operational efficiency. The proposed distributed network architecture incorporates data compression technologies and effective scheduling algorithms for handling the transmission scheduling of various physiological signals. Compared to existing scheduling mechanisms, the experimental results depict the network performance and show that in analyzing the delay and jitter, the proposed WFQ-based algorithms have reduced the delay and jitter ratio by about 40% and 19.47% compared to LLQ with priority queueing scheme, respectively. The experimental results also demonstrate that the proposed network topology is more effective than the direct path transmission approach in terms of energy consumption, which suggests that the proposed network architecture may improve the development of medical applications with body area networks such that the goal of self-organizing population health monitoring can be achieved.

A Novel Deep Neural Network Method for HAR-Based Team Training Using Body-Worn Inertial Sensors.

Human activity recognition (HAR) became a challenging issue in recent years. In this paper, we propose a novel approach to tackle indistinguishable activity recognition based on human wearable sensors. Generally speaking, vision-based solutions struggle with low illumination environments and partial occlusion problems. In contrast, wearable inertial sensors can tackle this problem and avoid revealing personal privacy. We address the issue by building a multistage deep neural network framework that interprets accelerometer, gyroscope, and magnetometer data that provide useful information of human activities. Initially, the stage of variational autoencoders (VAE) can extract the crucial information from raw data of inertial measurement units (IMUs). Furthermore, the stage of generative adversarial networks (GANs) can generate more realistic human activities. Finally, the transfer learning method is applied to enhance the performance of the target domain, which builds a robust and effective model to recognize human activities.

Multi-Target PIR Indoor Localization and Tracking System with Artificial Intelligence.

Pyroelectric infrared (PIR) sensors are low-cost, low-power, and highly reliable sensors that have been widely used in smart environments. Indoor localization systems may be wearable or non-wearable, where the latter are also known as device-free localization systems. Since binary PIR sensors detect only the presence of a subject's motion in their field of view (FOV) without other information about the actual location, information from overlapping FOVs of multiple sensors can be useful for localization. This study introduces the PIRILS (pyroelectric infrared indoor localization system), in which the sensing signal processing algorithms are augmented by deep learning algorithms that are designed based on the operational characteristics of the PIR sensor. Expanding to the detection of multiple targets, the PIRILS develops a quantized scheme that exploits the behavior of an artificial neural network (ANN) model to demonstrate localization performance in tracking multiple targets. To further improve the localization performance, the PIRILS incorporates a data augmentation strategy that enhances the training data diversity of the target's motion. Experimental results indicate system stability, improved positioning accuracy, and expanded applicability, thus providing an improved indoor multi-target localization framework.

Cooperative Networked PIR Detection System for Indoor Human Localization.

Pyroelectric Infrared (PIR) sensors are low-cost, low-power, and highly reliable sensors that have been widely used in smart environments. Indoor localization systems can be categorized as wearable and non-wearable systems, where the latter are also known as device-free localization systems. Since the binary PIR sensor detects only the presence of a human motion in its field of view (FOV) without any other information about the actual location, utilizing the information of overlapping FOV of multiple sensors can be useful for localization. In this study, a PIR detector and sensing signal processing algorithms were designed based on the characteristics of the PIR sensor. We applied the designed PIR detector as a sensor node to create a non-wearable cooperative indoor human localization system. To improve the system performance, signal processing algorithms and refinement schemes (i.e., the Kalman filter, a Transferable Belief Model, and a TBM-based hybrid approach (TBM + Kalman filter)) were applied and compared. Experimental results indicated system stability and improved positioning accuracy, thus providing an indoor cooperative localization framework for PIR sensor networks.

Real-Time Weather Monitoring and Prediction Using City Buses and Machine Learning.

Accurate weather data are important for planning our day-to-day activities. In order to monitor and predict weather information, a two-phase weather management system is proposed, which combines information processing, bus mobility, sensors, and deep learning technologies to provide real-time weather monitoring in buses and stations and achieve weather forecasts through predictive models. Based on the sensing measurements from buses, this work incorporates the strengths of local information processing and moving buses for increasing the measurement coverage and supplying new sensing data. In Phase I, given the weather sensing data, the long short-term memory (LSTM) model and the multilayer perceptron (MLP) model are trained and verified using the data of temperature, humidity, and air pressure of the test environment. In Phase II, the trained learning model is applied to predict the time series of weather information. In order to assess the system performance, we compare the predicted weather data with the actual sensing measurements from the Environment Protection Administration (EPA) and Central Weather Bureau (CWB) of Taichung observation station to evaluate the prediction accuracy. The results show that the proposed system has reliable performance at weather monitoring and a good forecast for one-day weather prediction via the trained models.

Design of Carryable Intravenous Drip Frame with Automatic Balancing.

Due to the inconvenience of the conventional intravenous drip frame, the piggyback intravenous drip frame is developed to improve the mobility of the patient. However, the current design of the drip frame leads to a lack of balance control and increment of blood returning. To this end, the proposed system aims to solve this problem, and a fuzzy proportionalintegral-derivative control technique is developed to demonstrate the system feasibility. Accordingly, a reliable balanced system can be applied to facilitate patients' movements and ensure patient safety with compensating the inclination angle of the drip frame such that the reduction of blood returning and the balance control of the piggyback intravenous drip frame can be achieved.

A Virtual Reality Soldier Simulator with Body Area Networks for Team Training.

Soldier-based simulators have been attracting increased attention recently, with the aim of making complex military tactics more effective, such that soldiers are able to respond rapidly and logically to battlespace situations and the commander's decisions in the battlefield. Moreover, body area networks (BANs) can be applied to collect the training data in order to provide greater access to soldiers' physical actions or postures as they occur in real routine training. Therefore, due to the limited physical space of training facilities, an efficient soldier-based training strategy is proposed that integrates a virtual reality (VR) simulation system with a BAN, which can capture body movements such as walking, running, shooting, and crouching in a virtual environment. The performance evaluation shows that the proposed VR simulation system is able to provide complete and substantial information throughout the training process, including detection, estimation, and monitoring capabilities.

Distributed Information Compression for Target Tracking in Cluster-Based Wireless Sensor Networks.

Target tracking is a critical wireless sensor application, which involves signal and information processing technologies. In conventional target position estimation methods, an estimate is usually demonstrated by an average target position. In contrast, this work proposes a distributed information compression method to describe the measurement uncertainty of tracking problems in cluster-based wireless sensor networks. The leader-based information processing scheme is applied to perform target positioning and energy conservation. A two-level hierarchical network topology is adopted for energy-efficient target tracking with information compression. A Level 1 network architecture is a cluster-based network topology for managing network operations. A Level 2 network architecture is an event-based and leader-based topology, utilizing the concept of information compression to process the estimates of sensor nodes. The simulation results show that compared to conventional schemes, the proposed data processing scheme has a balanced system performance in terms of tracking accuracy, data size for transmission and energy consumption.

Confirmed False Positive Proteinuria in Patients with Systemic Lupus Erythematosus Taking Hydroxychloroquine: a Spot Sample Measurement.

BACKGROUND: A false-positive screening result is associated with harmful treatment or follow-up costs. This study aimed to estimate the rate of false positive proteinuria with the dipstick in patients with systemic lupus erythematosus (SLE) taking hydroxychloroquine. METHODS: A total of 334 patients with a positive dipstick and confirmed by total urine protein with quantification assay were enrolled. The experimental group included those with SLE taking hydroxychloroquine, and the rest was the control group. The difference of the rate of false positive in the dipstick was analyzed using the chi-square test and odds ratio (OR) between groups. Qualitative tracking of potential interference in the dipstick was performed. RESULTS: The results revealed that the rate of false positive with a dipstick for the experimental and control groups were 29.5% and 5.0% (p = 0.000), respectively. The OR with 95% confidence interval (CI) of the rate of false positive for the experimental group with respect to the control group was 5.95 (95% CI: 2.80 - 12.65). Qualitative tracking showed that the dipstick was influenced to become false-positive when hydroxychloroquine concentration was ≥ 30 mg/dL. CONCLUSIONS: Hydroxychloroquines like plaquenil or geniquin may lead to a high rate of false positive with the dipstick method. A quantification assay is recommended for proteinuria measurement in patients with SLE taking hydroxychloroquines.

Evaluating the performance of urine conductivity as screening for early stage chronic kidney disease.

BACKGROUND: This study aimed to determine if urine conductivity (Cond) is better for screening early stage chronic kidney disease (CKD) instead of the currently routinely used parameters of urine creatinine (UCr), urine osmolality (Osmo), urine specific gravity (SpGr), and urine protein (UP). METHODS: One hundred and forty participants (86 male, 54 female) with eGFR > 60 were grouped as either early stage CKD (kidney damage longer than 3 months with either structural or functional abnormalities [n = 72]) or the control group (without CKD and without kidney damage or functional abnormalities [n = 681]). Sensitivty (Sn) and specificity (Sp) of UP and the ROC curves were calculated. The area under the curve (AUC) with 95% confidence interval (CI) was used to compare Cond, UCr, Osmo, and SpGr. Pearson's correlation was used to analyze the correlation between Cond and UCr, Osmo, and SpGr in the early stage CKD group. RESULTS: The Sn and Sp of UP were 22.2% and 92.6%, respectively. By ROC analysis, Cond had the largest AUC (0.752, 95% CI: 0.672-0.832), with 52.9% Sn and 86.1% Sp. Pearson's correlation showed that the coefficient (p < 0.01) of Cond to UCr, Osmo, and SpG were 0.696, 0.907, and 0.820, respectively. CONCLUSIONS: Cond has better screening ability than UP for early stage CKD and may be a potential surrogate parameter for Osmo, SpGr and UCr.

Using hybrid angle/distance information for distributed topology control in vehicular sensor networks.

In a vehicular sensor network (VSN), the key design issue is how to organize vehicles effectively, such that the local network topology can be stabilized quickly. In this work, each vehicle with on-board sensors can be considered as a local controller associated with a group of communication members. In order to balance the load among the nodes and govern the local topology change, a group formation scheme using localized criteria is implemented. The proposed distributed topology control method focuses on reducing the rate of group member change and avoiding the unnecessary information exchange. Two major phases are sequentially applied to choose the group members of each vehicle using hybrid angle/distance information. The operation of Phase I is based on the concept of the cone-based method, which can select the desired vehicles quickly. Afterwards, the proposed time-slot method is further applied to stabilize the network topology. Given the network structure in Phase I, a routing scheme is presented in Phase II. The network behaviors are explored through simulation and analysis in a variety of scenarios. The results show that the proposed mechanism is a scalable and effective control framework for VSNs.

Decentralized cooperative TOA/AOA target tracking for hierarchical wireless sensor networks.

This paper proposes a distributed method for cooperative target tracking in hierarchical wireless sensor networks. The concept of leader-based information processing is conducted to achieve object positioning, considering a cluster-based network topology. Random timers and local information are applied to adaptively select a sub-cluster for the localization task. The proposed energy-efficient tracking algorithm allows each sub-cluster member to locally estimate the target position with a Bayesian filtering framework and a neural networking model, and further performs estimation fusion in the leader node with the covariance intersection algorithm. This paper evaluates the merits and trade-offs of the protocol design towards developing more efficient and practical algorithms for object position estimation.

A Pervasive Pulmonary Function Estimation System with Six-Minute Walking Test.

Self-monitoring for spirometry is beneficial to assess the progression of lung disease and the effect of pulmonary rehabilitation. However, home spirometry fails to meet both accuracy and repeatability criteria in a satisfactory manner. The study aimed to propose a pervasive spirometry estimation system with the six-minute walking test (6MWT), where the system with information management, communication protocol, predictive algorithms, and a wrist-worn device, was developed for pulmonary function. A total of 60 subjects suffering from respiratory diseases aged from 25 to 90 were enrolled in the study. Pulmonary function test, walking steps, and physical status were measured before and after performing the 6MWT. The significant variables were extracted to predict per step distance (PSD), forced vital capacity (FVC) and forced expiratory volume in one second (FEV1). These predicted formulas were then implemented in a wrist-worn device of the proposed pervasive estimation system. The predicted models of PSD, and FVC, FEV1 with the 6MWT were created. The estimated difference for PSD was-0.7 ± 9.7 (cm). FVC and FEV1 before performing 6MWT were 0.2 ± 0.6 (L) and 0.1 ± 0.6 (L), respectively, and with a sensitivity (Sn) of 81.8%, a specificity (Sp) of 63.2% for obstructive lung diseases, while FVC and FEV1 after performing the 6MWT were 0.2 ± 0.7 (L) and 0.1 ± 0.6 (L), respectively, with an Sn of 90.9% and an Sp of 63.2% for obstructive lung diseases. Furthermore, the developed wristband prototype of the pulmonary function estimation system was demonstrated to provide effective self-estimation. The proposed system, consisting of hardware, application and algorithms was shown to provide pervasive assessment of the pulmonary function status with the 6MWT. This is a potential tool for self-estimation on FVC and FEV1 for those who cannot conduct home-based spirometry.

A Fuzzy Neural Network Model for Rapid Prediction of Optimal Positive Airway Pressures in OSAS Patients.

Manual titration of positive airway pressure (PAP) is a gold standard to provide an optimal pressure for the treatment of obstructive sleep apnea-hypopnea syndrome (OSAS). Since manual titration studies were costly and time-consuming, many statistical models for predicting effective PAPs were reported. However, the prediction accuracies of the models associated with nocturnal parameters still remain low. This study proposes a fuzzy neural prediction network (FNPN) with input candidate variables, selected among easily available measurements (e.g., body mass index (BMI), waist circumstance (WC), and body composition) and OSAS related questionnaires, to rapidly predict an optimal PAP. The FNPN comprises fuzzy rules and is characterized with the ability of automatic rule growing and pruning from training data. A total of 147 participants from April 2018 to April 2019 were enrolled in Taichung Veterans General Hospital, Taiwan. After two selection processes for feature extraction, WC and BMI were the significant variables for entering the FNPN to predict optimal PAP. Experimental results showed that the average successful prediction rate of the proposed method was 71.8%. This study also found that Epworth sleepiness scales (ESS) and body composition, such as visceral fat area and percent body fat, were excluded in the final prediction model. Compared with existing models, the proposed prediction approach provided a rapid prediction of optimal PAP with higher accuracy.

Interactions between Obstructive Sleep Apnea Syndrome Severity, Obesity, Sex Difference and Attention-Deficit/Hyperactivity Disorder on Health-Related Quality of Life: A Non-Interventional Prospective Observational Study.

Obstructive sleep apnea syndrome (OSAS) severity, obesity, sex difference, and attention-deficit/hyperactivity disorder (ADHD) had a complex impact on health-related quality of life (HRQoL). However, the interactive effects among these features on HRQoL remained to be clarified. This study aimed to investigate the individual and interactive associations between the four characteristics of interest and HRQoL as determined by 36-Item Short Form Health Survey, Pittsburgh Sleep Quality Index (PSQI), and Epworth Sleepiness Scale (ESS). This non-interventional, prospective, observational study enrolled a total of 132 patients with suspected OSAS for analysis. While OSAS severity and ADHD detected by adult ADHD Self-Report Scale, termed as screened ADHD, interact with each other, all the four studied features were individually associated with HRQoL. After adjusting for potential physiological and polysomnographic confounders, screened ADHD was independently correlated with PSQI > 5 (OR = 4.126, 95% CI, 1.490−11.424), mental component score < 50 (OR = 5.873, 95% CI, 2.262−15.251) and ESS > 10 (OR = 3.648, 95% CI, 1.738−7.657). Our results show that ADHD detection is necessary and should be incorporated into clinical practice for OSAS management.

Explainable fuzzy neural network with easy-to-obtain physiological features for screening obstructive sleep apnea-hypopnea syndrome.

OBJECTIVE/BACKGROUND: Recently, several tools for screening obstructive sleep apnea-hypopnea syndrome (OSAHS) have been devised with varied shortcomings. To overcome these drawbacks, we aimed to propose a self-estimation method using an explainable prediction model with easy-to-obtain variables and evaluate its performance for predicting OSAHS. PATIENTS/METHODS: This retrospective, cross-sectional study selected significant easy-to-obtain variables from patients, suspected of having OSAHS by regression analysis, and fed these variables into the proposed explainable fuzzy neural network (EFNN), a back propagation neural network (BPNN) and a stepwise regression model to compare the screening performance for OSAHS. RESULTS: Of the 300 participants, three easily available features, such as waist circumference, mean blood pressure (BP) at the end of polysomnography and the difference in systolic BP between the end and start of polysomnography, were obtained from regression analysis with a five-fold cross-validation scheme. Feeding these three variables into the prediction models showed that the average prediction differences for apnea-hypopnea index (AHI) when using the EFNN, BPNN, and regression model were respectively 1.5 ± 18.2, 3.5 ± 19.1 and 0.1 ± 19.3, indicating none of the tested methods had good efficacy to predict the AHI values. The performance as determined by the sensitivity + specificity-1 value for screening moderate-to-severe OSAHS of the EFNN, BPNN and regression model were respectively 0.440, 0.414 and 0.380. CONCLUSIONS: When fed with easy-to-obtain physiological features, the understandable EFNN should be the preferred method to predict moderate-to-severe OSAHS.

Adaptive AOA-aided TOA self-positioning for mobile wireless sensor networks.

Location-awareness is crucial and becoming increasingly important to many applications in wireless sensor networks. This paper presents a network-based positioning system and outlines recent work in which we have developed an efficient principled approach to localize a mobile sensor using time of arrival (TOA) and angle of arrival (AOA) information employing multiple seeds in the line-of-sight scenario. By receiving the periodic broadcasts from the seeds, the mobile target sensors can obtain adequate observations and localize themselves automatically. The proposed positioning scheme performs location estimation in three phases: (I) AOA-aided TOA measurement, (II) Geometrical positioning with particle filter, and (III) Adaptive fuzzy control. Based on the distance measurements and the initial position estimate, adaptive fuzzy control scheme is applied to solve the localization adjustment problem. The simulations show that the proposed approach provides adaptive flexibility and robust improvement in position estimation.

Cooperative anchor-free position estimation for hierarchical wireless sensor networks.

This paper proposes a distributed algorithm for establishing connectivity and location estimation in cluster-based wireless sensor networks. The algorithm exploits the information flow while coping with distributed signal processing and the requirements of network scalability. Once the estimation procedure and communication protocol are performed, sensor clusters can be merged to establish a single global coordinate system without GPS sensors using only distance information. In order to adjust the sensor positions, the refinement schemes and cooperative fusion approaches are applied to reduce the estimation error and improve the measurement accuracy. This paper outlines the technical foundations of the localization techniques and presents the tradeoffs in algorithm design. The feasibility of the proposed schemes is shown to be effective under certain assumptions and the analysis is supported by simulation and numerical studies.

Secure adaptive topology control for wireless ad-hoc sensor networks.

This paper presents a secure decentralized clustering algorithm for wireless ad-hoc sensor networks. The algorithm operates without a centralized controller, operates asynchronously, and does not require that the location of the sensors be known a priori. Based on the cluster-based topology, secure hierarchical communication protocols and dynamic quarantine strategies are introduced to defend against spam attacks, since this type of attacks can exhaust the energy of sensor nodes and will shorten the lifetime of a sensor network drastically. By adjusting the threshold of infected percentage of the cluster coverage, our scheme can dynamically coordinate the proportion of the quarantine region and adaptively achieve the cluster control and the neighborhood control of attacks. Simulation results show that the proposed approach is feasible and cost effective for wireless sensor networks.