The Internet of Things (IoT) is increasingly deployed in critical infrastructure domains with stringent Quality of Service (QoS) requirements. The Web of Things (WoT) framework facilitates communication by enabling seamless interoperability between IoT systems and the broader Internet. However, WoT communication strategies often incur communication overhead and potential data loss, which may adversely affect QoS in IoT applications. Meanwhile, publish-subscribe systems are recognized for their lightweight, efficient, and reliable communication capabilities within IoT networks. To address the trade-off between robust intra-system communication and seamless inter-system interoperability, we propose a hybrid communication model that integrates publish-subscribe mechanisms for intra-system data exchange with REST-based protocols for inter-system communication. The architecture incorporates an AI/ML-capable Intelligent Web Gateway (IWG) to support hand-off between publish-subscribe and WoT communication. To validate the feasibility of the proposed architecture, we evaluate three commodity hardware platforms-NVIDIA Jetson Orin, Intel Next Unit of Computing (NUC), and Raspberry Pi 4-based on their ability to support expected workloads for IWGs. Our findings underscore the capability of off-the-shelf hardware platforms to support the proposed hybrid communication model and partially validate its practical deployment in IoT environments.

Tuberculosis (TB) is an infectious disease resulting in 1.5 M deaths worldwide every year. Early diagnosis can play an important role in reducing TB induced mortality rates. A common inexpensive approach to test for TB is a manual examination of sputum smear images under the light/fluorescent microscope. To enhance the process, computer-aided diagnostic devices and machine learning algorithms have been developed with the capability of identifying TB bacilli using image processing techniques. Here, we propose a novel statistical model of the shape and color of TB bacilli in Ziehl-Neelsen stained images under the light microscope to identify bacilli in these images. These simple statistical models are utilized as a general library for reconstructing any bacillus with various background colors and can overcome the difficulties associated with geometric feature extraction methods. We use various methods to classify the individual bacilli and overlapping bacilli from the rest of the image based on the eigenvalues of the shape and color models. Our results show that the k-NN classifier performs best among selected classifiers with an average accuracy of 82.7% for single bacilli and overlapping bacilli detection, and 99.1% accuracy of identifying individual bacilli alone from overlapping bacilli and other objects.

Wearable sensory devices are becoming the enabling technology for many applications in healthcare and well-being, where computational elements are tightly coupled with the human body to monitor specific events about their subjects. Classification algorithms are the most commonly used machine learning modules that detect events of interest in these systems. The use of accurate and resource-efficient classification algorithms is of key importance because wearable nodes operate on limited resources on one hand and intend to recognize critical events (e.g., falls) on the other hand. These algorithms are used to map statistical features extracted from physiological signals onto different states such as health status of a patient or type of activity performed by a subject. Conventionally selected features may lead to rapid battery depletion, mainly due to the absence of computing complexity criterion while selecting prominent features. In this paper, we introduce the notion of power-aware feature selection, which aims at minimizing energy consumption of the data processing for classification applications such as action recognition. Our approach takes into consideration the energy cost of individual features that are calculated in real-time. A graph model is introduced to represent correlation and computing complexity of the features. The problem is formulated using integer programming and a greedy approximation is presented to select the features in a power-efficient manner. Experimental results on thirty channels of activity data collected from real subjects demonstrate that our approach can significantly reduce energy consumption of the computing module, resulting in more than 30 percent energy savings while achieving 96.7 percent classification accuracy.

We introduce Hermes , a lightweight smart shoe and its supporting infrastructure aimed at extending gait and instability analysis and human instability/balance monitoring outside of a laboratory environment. We aimed to create a scientific tool capable of high-level measures, by combining embedded sensing, signal processing and modeling techniques. Hermes monitors walking behavior and uses an instability assessment model to generate quantitative value with episodes of activity identified by physician, researchers or investigators as important. The underlying instability assessment model incorporates variability and correlation of features extracted during ambulation that have been identified by geriatric motion study experts as precursor to instability, balance abnormality and possible fall risk. Hermes provides a mobile, affordable and long-term instability analysis and detection system that is customizable to individual users, and is context-aware, with the capability of being guided by experts. Our experiments demonstrate the feasibility of our model and the complimentary role our system can play by providing long-term monitoring of patients outside a hospital or clinical setting at a reduced cost, with greater user convenience, compliance and inference capabilities that meet the physician's or investigator's needs.

Many wearable embedded systems benefit from classification algorithms where statistical features extracted from physiological signals are mapped onto different user's states such as health status of a patient or type of activity performed by a subject. Conventionally selected features lead to rapid battery depletion in these battery-operated systems, mainly due to the absence of computing complexity criterion while selecting prominent features. In this paper, we introduce the notion of power-aware feature selection, which minimizes energy consumption of the signal processing for classification applications. Our approach takes into consideration the energy cost of individual features that are calculated in real-time. The problem is formulated using integer programming and a greedy approximation is presented to select the features in a power-efficient manner. Experimental results on thirty channels of activity data demonstrate that our approach can significantly reduce energy consumption of the computing module resulting in more than 30$% energy savings while achieving 96.7% classification accuracy.

Sitting posture analysis is critical for daily applications in biomedical, education and healthcare fields. However, it remains unclear how to monitor sitting posture economically and comfortably. To this end, we presented an eTextile device, called eCushion, in this paper, which can analyze the sitting posture of human being accurately and non-invasively. First, we discussed the implementation of eCushion and design challenges of sensing data, such as scale, offset, rotation and crosstalk. Then, several effective techniques have been proposed to improve the recognition rate of sitting posture. Our experimental results show that the recognition rate of our eCushion system could achieve 92% for object-oriented cases and 79% for general cases.

We present a technique to discover the position of sensors on the human body. Automatic on-body device localization ensures correctness and accuracy of measurements in health and medical monitoring systems. In addition, it provides opportunities to improve the performance and usability of ubiquitous devices. Our technique uses accelerometers to capture motion data to estimate the location of the device on the user's body, using mixed supervised and unsupervised time series analysis methods. We have evaluated our technique with extensive experiments on 25 subjects. On average, our technique achieves 89% accuracy in estimating the location of devices on the body.

We target body-wearable sensor networks, in which sensor nodes are strategically placed on the human body and the wireless communications are conducted on/off the surface of the body. The results, obtained by performing multiple experiments in outdoor environments, are presented. A single on body transmitter communicates with a single receiver node, which is located on the body or off the body at various distances. Sensor nodes utilized in our experiments are equipped with XBee and XBee Pro wireless modules for on body and off body communications, respectively. The focus of our work is to observe how the Received Signal Strength (RSS) and the Packet Reception Rate (PRR) vary as we change the communication distance and transmission power level. Our experimental results can be used to perform transmission power control with high precision in order not to exceed a certain packet error rate.

Abstract This paper presents an energy‐efficient and coverage‐preserving communication protocol which distributes a uniform energy load to the sensors in a wireless microsensor network. This protocol, called Distance‐based Segmentation (DBS), is a cluster‐based protocol that divides the entire network into equal‐area segments and applies different clustering policies to each segment to (1) reduce total energy dissipation and (2) balance the energy load among the sensors. Therefore, it prolongs the lifetime of the network and improves the sensing coverage. Moreover, the proposed routing protocol does not need any centralized support from a certain node which is at odds with aiming to establish a scalable communication protocol. Results from extensive simulations on two different network configurations show that by lowering the number of wasteful transmissions in the network, the DBS can achieve as much as a 20% reduction in total dissipated energy as compared with current cluster‐based protocols. In addition, this protocol is able to distribute energy load more evenly among the sensors in the network. Hence, it yields up to a 66% increase in the useful network lifetime. According to the simulation results, the sensing coverage degradation of the DBS is considerably slower than that of the other cluster‐based protocols. Copyright © 2009 John Wiley & Sons, Ltd.