More Like this

1. Adaptive Sampling and Quick Anomaly Detection in Large Networks

   Xian, X.; Semenov, A.; Hu, Y.; Wang, A.; Jin, Y. (October 2022, IEEE transactions on automation science and engineering)

   The monitoring of data streams with a network structure have drawn increasing attention due to its wide applications in modern process control. In these applications, high-dimensional sensor nodes are interconnected with an underlying network topology. In such a case, abnormalities occurring to any node may propagate dynamically across the network and cause changes of other nodes over time. Furthermore, high dimensionality of such data significantly increased the cost of resources for data transmission and computation, such that only partial observations can be transmitted or processed in practice. Overall, how to quickly detect abnormalities in such large networks with resource constraints remains a challenge, especially due to the sampling uncertainty under the dynamic anomaly occurrences and network-based patterns. In this paper, we incorporate network structure information into the monitoring and adaptive sampling methodologies for quick anomaly detection in large networks where only partial observations are available. We develop a general monitoring and adaptive sampling method and further extend it to the case with memory constraints, both of which exploit network distance and centrality information for better process monitoring and identification of abnormalities. Theoretical investigations of the proposed methods demonstrate their sampling efficiency on balancing between exploration and exploitation, as well as the detection performance guarantee. Numerical simulations and a case study on power network have demonstrated the superiority of the proposed methods in detecting various types of shifts. Note to Practitioners —Continuous monitoring of networks for anomalous events is critical for a large number of applications involving power networks, computer networks, epidemiological surveillance, social networks, etc. This paper aims at addressing the challenges in monitoring large networks in cases where monitoring resources are limited such that only a subset of nodes in the network is observable. Specifically, we integrate network structure information of nodes for constructing sequential detection methods via effective data augmentation, and for designing adaptive sampling algorithms to observe suspicious nodes that are likely to be abnormal. Then, the method is further generalized to the case that the memory of the computation is also constrained due to the network size. The developed method is greatly beneficial and effective for various anomaly patterns, especially when the initial anomaly randomly occurs to nodes in the network. The proposed methods are demonstrated to be capable of quickly detecting changes in the network and dynamically changes the sampling priority based on online observations in various cases, as shown in the theoretical investigation, simulations and case studies. 

   more » « less
2. Deep Learning Dataset Generation for Physical Layer Authentication in Wireless Sensor Networks (WSN)

   Dentremont, Christopher; Liu, Hong (May 2024, 2024 International Wireless Communications and Mobile Computing (IWCMC))

   Structural Health Monitoring (SHM) uses wireless sensor network (WSN) to monitor a civil construction’s conditions remotely and constantly for its sustainable usage. Security in WSN for SHM is essential to safeguard critical transportation infrastructure such as bridges. While WSN offers cost-effective solutions for Bridge SHM, its wireless nature expands attack surfaces, making security a significant concern. Despite progress in addressing security issues in WSN for Bridge SHM, challenges persist in device authentication due to the unique placement of sensor nodes and their resource constraints, particularly in energy conservation requirements to extend the system’s lifetime. To overcome these limitations, this paper proposes an innovative authentication scheme with deep learning at the physical layer. Our approach steers away from conventional device authentication methods: no challenge-response protocol with heavy communication overhead and no cryptography of intensive computation. Instead, we use radio frequency (RF) fingerprinting to authenticate sensor nodes. Deep learning is chosen for its ability to discover patterns in large datasets without manual feature engineering. We model our scheme on IEEE 802.11ah, Wi-Fi HaLow of long-range communication and low-power consumption for machine-to-machine (M2M) applications. Simulations and experiments using universal software radio peripheral (USRP) demonstrate the effectiveness of the proposed scheme. By integrating security into Cyber-Physical System/the Internet-of-Things (CPS/IoT) design of WSN for Bridge SHM, our work contributes to critical infrastructure protection. 

   more » « less
3. Self-Calibrating Indoor Trajectory Tracking System Using Distributed Monostatic Radars For Large Scale Deployment

   https://doi.org/10.1145/3563357.3564078  

   Xie, Zongxing; Ye, Fan (January 2022, ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation)

   24/7 continuous recording of in-home daily trajectories is informative for health status assessment (e.g., monitoring Alzheimer’s, dementia based on behavior patterns). Indoor device-free localization/tracking are ideal because no user efforts on wearing devices are needed. However, prior work mainly focused on improving the localization accuracy. They relied on well-calibrated sensor placements, which require hours of intensive manual setup and respective expertise, feasible only at small scale and by mostly re- searchers themselves. Scaling the deployments to tens or hundreds of real homes, however, would incur prohibitive manual efforts, and become infeasible for layman users. We present SCALING, a plug-and-play indoor trajectory monitoring system that layman users can easily setup by walking a one-minute loop trajectory after placing radar nodes on walls. It uses a self calibrating algorithm that estimates sensor locations through their distance measurements to the person walking the trajectory, a trivial effort without taxing layman users physically or cognitively. We evaluate SCALING via simulations and two testbeds (in lab and home configurations of sizes 3 × 6 sq m and 4.5 × 8.5 sq m). Experimental results demonstrate that SCALING outperformed the baseline using the approximate multidimensional scaling (MDS, the most relevant method in the context of self calibration) by 3.5 m/1.6 m in 80-percentile error of self calibration and tracking,respectively.Notably,only1% degradation in performance has been observed with SCALING compared to the classical multilateration with known sensor locations (anchors), which costs hours of intensive calibrating effort. 

   more » « less
4. Self-Assembled Plasmonic Structural Color Colorimetric Sensor for Smartphone-Based Point-Of-Care Ammonia Detection in Water

   https://doi.org/10.1021/acsami.4c06615  

   Soudi, Mahdi; Cencillo-Abad, Pablo; Patel, Jay; Ghimire, Suvash; Dillon, Joseph; Biswas, Aritra; Mukhopadhyay, Kausik; Chanda, Debashis (August 2024, ACS Applied Materials & Interfaces)

   Monitoring chemical levels is crucial for safeguarding both the environment and public health. Elevated levels of ammonia, for instance, can harm both humans and aquatic ecosystems, often indicating contamination from agriculture, industry, or sewage. Developing portable, high-resolution, and affordable methods for in situ monitoring of ammonia is thus imperative. Plasmonic sensors offer a promising solution, detecting ammonia by correlating changes in their optical response to the target analyte’s concentration. While they are highly sensitive and can be fabricated in a variety of portable and user-friendly formats, some still require reagents or expensive optical equipment, which hinder their widespread adoption. Here, we present a self-assembled nanoplasmonic colorimetric sensor capable of directly detecting ammonia concentrations in aqueous matrices. The proposed sensor exploits the plasmonic resonance of the nanostructures to transduce changes in the chemical environment into alterations in color, offering a label-free method for real-time analysis. The sensor is fabricated using a self-assembling technique compatible with low-cost mass production based on aluminum and aluminum oxide, ensuring affordability and avoiding the use of other toxic chemicals. We developed a model to predict ammonia concentrations based on visible color change of the sensor, achieving a detection limit of 8.5 ppm. Furthermore, to address the need for on-site detection, we integrated smartphone technology for real-time color change analysis, eliminating the need for expensive, bulky optical instruments. Indeed, our approach offers a cost-effective, portable, and user-friendly solution for ammonia detection in water without the need for chemical reagents or spectrometers, making it ideal for field applications. Interestingly, this platform extends its applicability beyond ammonia detection, enabling the monitoring of various chemicals using a smartphone, without the need for any additional costly equipment. 

   more » « less
5. Smart Bracelets for Remote Monitoring of Wearers' Physical and Affective State

   https://doi.org/10.1109/MECO49872.2020.9134093  

   Rishe, Naphtali David; Adjouadi, Malek; Ortega, Francisco (June 2020, 2020 9th Mediterranean Conference on Embedded Computing (MECO))

   null (Ed.)

   Smart bracelets able to interpret the wearer's emotional state and communicate it to a remote decision-support facility will have broad applications in healthcare, elder care, the military, and other fields. While there are existing commercial embedded devices, such as the Apple Watch, that have health-monitoring sensors, such devices cannot sufficiently support a real-time health-monitoring system with battery-efficient remote data delivery. Ongoing R&D is developing solutions capable of monitoring multiple psycho-physiological signals. Possible hardware configurations include wrist-worn devices and sensors across an augmented reality headset (e.g., HoloLens 2). The device should carry an array of sensors of psycho-physiological signals, including a galvanic skin response sensor, motion sensor, skin temperature sensor, and a heart rate sensor. Output from these sensors can be intelligently fused to monitor the affective state and to determine specific trigger events for the wearer. To enable real-time remote monitoring applications, the device needs to be low-power to allow persistent monitoring while prolonging usage before recharging. For many applications, specialized sensor arrays are required, e.g. a galvanic skin response sensor. An application-flexible device would allow adding/removing sensors and would provide a choice of communication modules (e.g., Bluetooth 5.0 low-energy vs ZigBee). Appropriate configurations of the device would support applications in military health monitoring, drug-addiction mitigation, autistic trigger monitoring, and augmented reality exploration. A configuration example is: motion sensors (3-axis accelerometers, gyroscopes, and magnetometers to track steps, falls, and energy usage), a heart-rate sensor (e.g., an optical-based heart rate sensor with a single monitoring zone using the process of photoplethysmography (PPS)), at least a Bluetooth 5.0 (but a different communication device may be needed depending on the use case), and flash memory to temporarily store data when the device is not remotely communicating. The wearables field has greatly advanced in the quality of sensors; the fusion of multi-sensor data is the current frontier. 

   more » « less