Search for: All records

We present a directed high-energy radio wave exposure detection sensor using radio frequency (RF) energy harvesting techniques. The sensor comprises a small dipole antenna and a tunable rectifier circuit. Reverse biasing the diode allows high levels of RF radiation to be detected by the sensor. We also demonstrate how the frequency-dependent nature of the rectifier can be alleviated. The proposed sensor performance is experimentally evaluated in the 5–10 GHz range. 

Reconfigurable intelligent surfaces (RISs) are an emerging transmission technology to aid wireless communication. However, the potential of using RIS to mitigate directed energy weapons (DEW) is not widely recognized. In this paper, we propose to leverage RIS (based on spiral antenna elements) to aid the mitigation of high-energy radio-frequency (RF) sources applied to a DEW. For example, integrating a broadband circularly-polarized antenna system with RIS technology can successfully mitigate DEW attacks across a wide range of frequencies regardless of how the radio waves are polarized. We simulated a spiral antenna that operates within a frequency band of 1.3 GHz to 7 GHz with a 3-dB axial ratio bandwidth (ARBW) covering from 2 GHz to 7 GHz. Full-wave simulation results show the potential promising application of RIS for the mitigation of DEW attacks. 

Although much of the work in behaviorally detecting malware lies in collecting the best explanatory data and using the most efficacious machine learning models, the processing of the data can sometimes prove to be the most important step in the data pipeline. In this work, we collect kernel-level system calls on a resource-constrained Internet of Things (IoT) device, apply lightweight Natural Language Processing (NLP) techniques to the data, and feed this processed data to two simple machine learning classification models: Logistic Regression (LR) and a Neural Network (NN). For the data processing, we group the system calls into n-grams that are sorted by the timestamp in which they are recorded. To demonstrate the effectiveness, or lack thereof, of using n-grams, we deploy two types of malware onto the IoT device: a Denial-of-Service (DoS) attack, and an Advanced Persistent Threat (APT) malware. We examine the effects of using lightweight NLP on malware like the DoS and the stealthy APT malware. For stealthier malware, such as the APT, using more advanced, but far more resource-intensive, NLP techniques will likely increase detection capability, which is saved for future work. 

Passive ultra high frequency (UHF) radio frequency identification (RFID) tags have the potential to find ubiquitous use in indoor object tracking, localization, and contact tracing. We propose a machine learning-based method for RFID indoor localization using a pattern reconfigurable UHF RFID reader antenna array. The received signal strength indicator (RSSI) values (from 10,000 tags) recorded at the reader antenna units are used as features to evaluate the machine learning models with a train-test split of 75%-25%. The training and testing data is generated by a wireless ray tracing simulator. Five machine learning models: random forest regressor, decision tree regressor, Nu support vector regressor, k nearest regressor, and kernel ridge regressor are compared. Random forest regressor has the lowest localization error both in terms of average Euclidean distance (AED) and root-mean-square error (RMSE). For random forest regressor, localization error results show that 90% of the tags are within 1 meter of their true position, and 67% are within 50 cm of their true position based on Euclidean distance. 

Precise monitoring of respiratory rate in premature newborn infants is essential to initiating medical interventions as required. Wired technologies can be invasive and obtrusive to the patients. We propose a deep-learning-enabled wearable monitoring system for premature newborn infants, where respiratory cessation is predicted using signals that are collected wirelessly from a non-invasive wearable Bellypatch put on the infant’s body. We propose a five-stage design pipeline involving data collection and labeling, feature scaling, deep learning model selection with hyperparameter tuning, model training and validation, and model testing and deployment. The model used is a 1-D convolutional neural network (1DCNN) architecture with one convolution layer, one pooling layer, and three fully-connected layers, achieving 97.15% classification accuracy. To address the energy limitations of wearable processing, several quantization techniques are explored, and their performance and energy consumption are analyzed for the respiratory classification task. Results demonstrate a reduction of energy footprints and model storage overhead with a considerable degradation of the classification accuracy, meaning that quantization and other model compression techniques are not the best solution for respiratory classification problem on wearable devices. To improve accuracy while reducing the energy consumption, we propose a novel spiking neural network (SNN)-based respiratory classification solution, which can be implemented on event-driven neuromorphic hardware platforms. To this end, we propose an approach to convert the analog operations of our baseline trained 1DCNN to their spiking equivalent. We perform a design-space exploration using the parameters of the converted SNN to generate inference solutions having different accuracy and energy footprints. We select a solution that achieves an accuracy of 93.33% with 18x lower energy compared to the baseline 1DCNN model. Additionally, the proposed SNN solution achieves similar accuracy as the quantized model with a 4× lower energy. 

Modern-day radar is used extensively in applications such as autonomous driving, robotics, air traffic control, and maritime operations. The commonality between the aforementioned examples is the underlying tracking filter used to process ambiguous detections and track multiple targets. In this paper, we present a Software-Defined Radio-based radar testbed that leverages controllable and repeatable large-scale wireless channel emulation to evaluate diverse radar applications experimentally without the complexity and expense of field testing. Through over-the-air (OTA) and emulated evaluation, we demonstrate the capa-bilities of this testbed to perform multiple-target tracking (MTT) via Joint Probabilistic Data Association (JPDA) filtering. This testbed features the use of flexible sub-6 GHz or mmWave operation, electromagnetic ray tracing for site-specific emulation, and software reconfigurable radar waveforms and processing. Although the testbed is designed generalizable, for this paper we demonstrate its capabilities using an advanced driver-assistance system radar application. 

We present a step-by-step approach for designing a recofigurable Alford loop antenna (RALA). The design of an 3.5 GHz RALA is shown. The antenna is fabricated using a 1.6 mm thick double-sided FR4 substrate. We sweep antenna geometrical parameters and show the effect on antenna input impedance, reflection coefficient (S 11 ), and radiation patterns. The final antenna structure resonates at 3.5 GHz with eight directional and one omnidirectional radiation patterns. We also present a simplistic control circuit responsible for activating the antenna elements. Tri-state impedance matching- a major challenge in the design of RALA is also discussed and analyzed along with a proposed method for mitigation. 3D radiation patterns of the RALA was measured using an EMScan and a maximum gain of 4.5 dBi is found.