Muhammad Mahboob Ur Rahman

Ahmed Patwa, Muhammad Mahboob Ur Rahman, Tareq Y. Al-Naffouri

Heart murmurs provide valuable information about mechanical activity of the heart, which aids in diagnosis of various heart valve diseases. This work does automatic and accurate heart murmur detection from phonocardiogram (PCG) recordings. Two public PCG datasets (CirCor Digiscope 2022 dataset and PCG 2016 dataset) from Physionet online database are utilized to train and test three custom neural networks (NN): a 1D convolutional neural network (CNN), a long short-term memory (LSTM) recurrent neural network (RNN), and a convolutional RNN (C-RNN). We first do pre-processing which includes the following key steps: denoising, segmentation, re-labeling of noise-only segments, data normalization, and time-frequency analysis of the PCG segments using wavelet scattering transform. We then conduct four experiments, first three (E1-E3) using PCG 2022 dataset, and fourth (E4) using PCG 2016 dataset. It turns out that our custom 1D-CNN outperforms other two NNs (LSTM-RNN and C-RNN). Further, our 1D-CNN model outperforms the related work in terms of accuracy, weighted accuracy, F1-score and AUROC, for experiment E3 (that utilizes the cleaned and re-labeled PCG 2022 dataset). As for experiment E1 (that utilizes the original PCG 2022 dataset), our model performs quite close to the related work in terms of weighted accuracy and F1-score.

Kawish Pervez, Waqas Aman, M. Mahboob Ur Rahman et al.

In post-covid19 world, radio frequency (RF)-based non-contact methods, e.g., software-defined radios (SDR)-based methods have emerged as promising candidates for intelligent remote sensing of human vitals, and could help in containment of contagious viruses like covid19. To this end, this work utilizes the universal software radio peripherals (USRP)-based SDRs along with classical machine learning (ML) methods to design a non-contact method to monitor different breathing abnormalities. Under our proposed method, a subject rests his/her hand on a table in between the transmit and receive antennas, while an orthogonal frequency division multiplexing (OFDM) signal passes through the hand. Subsequently, the receiver extracts the channel frequency response (basically, fine-grained wireless channel state information), and feeds it to various ML algorithms which eventually classify between different breathing abnormalities. Among all classifiers, linear SVM classifier resulted in a maximum accuracy of 88.1\%. To train the ML classifiers in a supervised manner, data was collected by doing real-time experiments on 4 subjects in a lab environment. For label generation purpose, the breathing of the subjects was classified into three classes: normal, fast, and slow breathing. Furthermore, in addition to our proposed method (where only a hand is exposed to RF signals), we also implemented and tested the state-of-the-art method (where full chest is exposed to RF radiation). The performance comparison of the two methods reveals a trade-off, i.e., the accuracy of our proposed method is slightly inferior but our method results in minimal body exposure to RF radiation, compared to the benchmark method.

M. Hashim Shahab, Hasan Mujtaba Buttar, Ahsan Mehmood et al.

Non-intrusive load monitoring (NILM) or energy disaggregation aims to extract the load profiles of individual consumer electronic appliances, given an aggregate load profile of the mains of a smart home. This work proposes a novel deep-learning and edge computing approach to solve the NILM problem and a few related problems as follows. 1) We build upon the reputed seq2-point convolutional neural network (CNN) model to come up with the proposed seq2-[3]-point CNN model to solve the (home) NILM problem and site-NILM problem (basically, NILM at a smaller scale). 2) We solve the related problem of appliance identification by building upon the state-of-the-art (pre-trained) 2D-CNN models, i.e., AlexNet, ResNet-18, and DenseNet-121, which are fine-tuned two custom datasets that consist of Wavelets and short-time Fourier transform (STFT)-based 2D electrical signatures of the appliances. 3) Finally, we do some basic qualitative inference about an individual appliance's health by comparing the power consumption of the same appliance across multiple homes. Low-frequency REDD dataset is used for all problems, except site-NILM where REFIT dataset has been used. As for the results, we achieve a maximum accuracy of 94.6\% for home-NILM, 81\% for site-NILM, and 88.9\% for appliance identification (with Resnet-based model).

Rose Alaslani, Levina Perzhilla, Muhammad Mahboob Ur Rahman et al.

This work proposes for the first time to utilize the regular smartphone -- a popular assistive gadget -- to design a novel, non-invasive method for self-monitoring of one's hydration level on a scale of 1 to 4. The proposed method involves recording a small video of a fingertip using the smartphone camera. Subsequently, a photoplethysmography (PPG) signal is extracted from the video data, capturing the fluctuations in peripheral blood volume as a reflection of a person's hydration level changes over time. To train and evaluate the artificial intelligence models, a custom multi-session labeled dataset was constructed by collecting video-PPG data from 25 fasting subjects during the month of Ramadan in 2023. With this, we solve two distinct problems: 1) binary classification (whether a person is hydrated or not), 2) four-class classification (whether a person is fully hydrated, mildly dehydrated, moderately dehydrated, or extremely dehydrated). For both classification problems, we feed the pre-processed and augmented PPG data to a number of machine learning, deep learning and transformer models which models provide a very high accuracy, i.e., in the range of 95% to 99%. We also propose an alternate method where we feed high-dimensional PPG time-series data to a DL model for feature extraction, followed by t-SNE method for feature selection and dimensionality reduction, followed by a number of ML classifiers that do dehydration level classification. Finally, we interpret the decisions by the developed deep learning model under the SHAP-based explainable artificial intelligence framework. The proposed method allows rapid, do-it-yourself, at-home testing of one's hydration level, is cost-effective and thus inline with the sustainable development goals 3 & 10 of the United Nations, and a step-forward to patient-centric healthcare systems, smart homes, and smart cities of future.

Muhammad Wasim Nawaz, Muhammad Ahmad Tahir, Ahsan Mehmood et al.

We develop and evaluate two novel purpose-built deep learning (DL) models for synthesis of the arterial blood pressure (ABP) waveform in a cuff-less manner, using a single-site photoplethysmography (PPG) signal. We train and evaluate our DL models on the data of 209 subjects from the public UCI dataset on cuff-less blood pressure (CLBP) estimation. Our transformer model consists of an encoder-decoder pair that incorporates positional encoding, multi-head attention, layer normalization, and dropout techniques for ABP waveform synthesis. Secondly, under our frequency-domain (FD) learning approach, we first obtain the discrete cosine transform (DCT) coefficients of the PPG and ABP signals, and then learn a linear/non-linear (L/NL) regression between them. The transformer model (FD L/NL model) synthesizes the ABP waveform with a mean absolute error (MAE) of 3.01 (4.23). Further, the synthesis of ABP waveform also allows us to estimate the systolic blood pressure (SBP) and diastolic blood pressure (DBP) values. To this end, the transformer model reports an MAE of 3.77 mmHg and 2.69 mmHg, for SBP and DBP, respectively. On the other hand, the FD L/NL method reports an MAE of 4.37 mmHg and 3.91 mmHg, for SBP and DBP, respectively. Both methods fulfill the AAMI criterion. As for the BHS criterion, our transformer model (FD L/NL regression model) achieves grade A (grade B).

Ahsan Mehmood, Asma Sarauji, M. Mahboob Ur Rahman et al.

In the post-covid19 era, every new wave of the pandemic causes an increased concern among the masses to learn more about their state of well-being. Therefore, it is the need of the hour to come up with ubiquitous, low-cost, non-invasive tools for rapid and continuous monitoring of body vitals that reflect the status of one's overall health. In this backdrop, this work proposes a deep learning approach to turn a smartphone-the popular hand-held personal gadget-into a diagnostic tool to measure/monitor the three most important body vitals, i.e., pulse rate (PR), blood oxygen saturation level (aka SpO2), and respiratory rate (RR). Furthermore, we propose another method that could extract a single-lead electrocardiograph (ECG) of the subject. The proposed methods include the following core steps: subject records a small video of his/her fingertip by placing his/her finger on the rear camera of the smartphone, and the recorded video is pre-processed to extract the filtered and/or detrended video-photoplethysmography (vPPG) signal, which is then fed to custom-built convolutional neural networks (CNN), which eventually spit-out the vitals (PR, SpO2, and RR) as well as a single-lead ECG of the subject. To be precise, the contribution of this paper is two-fold: 1) estimation of the three body vitals (PR, SpO2, RR) from the vPPG data using custom-built CNNs, vision transformer, and most importantly by CLIP model; 2) a novel discrete cosine transform+feedforward neural network-based method that translates the recorded video- PPG signal to a single-lead ECG signal. The proposed method is anticipated to find its application in several use-case scenarios, e.g., remote healthcare, mobile health, fitness, sports, etc.

Ahsan Mehmood, Waqas Aman, M. Mahboob Ur Rahman et al.

This work considers identity attack on a radio-frequency identification (RFID)-based backscatter communication system. Specifically, we consider a single-reader, single-tag RFID system whereby the reader and the tag undergo two-way signaling which enables the reader to extract the tag ID in order to authenticate the legitimate tag (L-tag). We then consider a scenario whereby a malicious tag (M-tag)---having the same ID as the L-tag programmed in its memory by a wizard---attempts to deceive the reader by pretending to be the L-tag. To this end, we counter the identity attack by exploiting the non-reciprocity of the end-to-end channel (i.e., the residual channel) between the reader and the tag as the fingerprint of the tag. The passive nature of the tag(s) (and thus, lack of any computational platform at the tag) implies that the proposed light-weight physical-layer authentication method is implemented at the reader. To be concrete, in our proposed scheme, the reader acquires the raw data via two-way (challenge-response) message exchange mechanism, does least-squares estimation to extract the fingerprint, and does binary hypothesis testing to do authentication. We also provide closed-form expressions for the two error probabilities of interest (i.e., false alarm and missed detection). Simulation results attest to the efficacy of the proposed method.

Waqas Aman, M. Mahboob Ur Rahman, Hassan T. Abbas et al.

Nanoscale communication systems operating in Ter-ahertz (THz) band are anticipated to revolutionise the healthcaresystems of the future. Global wireless data traffic is undergoinga rapid growth. However, wireless systems, due to their broad-casting nature, are vulnerable to malicious security breaches. Inaddition, advances in quantum computing poses a risk to existingcrypto-based information security. It is of the utmost importanceto make the THz systems resilient to potential active and passiveattacks which may lead to devastating consequences, especiallywhen handling sensitive patient data in healthcare systems. Newstrategies are needed to analyse these malicious attacks and topropose viable countermeasures. In this manuscript, we presenta new authentication mechanism for nanoscale communicationsystems operating in THz band at the physical layer. We assessedan impersonation attack on a THz system. We propose usingpath loss as a fingerprint to conduct authentication via two-stephypothesis testing for a transmission device. We used hiddenMarkov Model (HMM) viterbi algorithm to enhance the outputof hypothesis testing. We also conducted transmitter identificationusing maximum likelihood and Gaussian mixture model (GMM)expectation maximization algorithms. Our simulations showedthat the error probabilities are a decreasing functions of SNR. At 10 dB with 0.2 false alarm, the detection probability was almostone. We further observed that HMM out-performs hypothesistesting at low SNR regime (10% increase in accuracy is recordedat SNR =5 dB) whereas the GMM is useful when groundtruths are noisy. Our work addresses major security gaps facedby communication system either through malicious breachesor quantum computing, enabling new applications of nanoscalesystems for Industry 4.0.

Waqas Aman, Zeeshan Haider, S. Waqas H. Shah et al.

This paper investigates the impact of authentication on effective capacity (EC) of an underwater acoustic (UWA) channel. Specifically, the UWA channel is under impersonation attack by a malicious node (Eve) present in the close vicinity of the legitimate node pair (Alice and Bob); Eve tries to inject its malicious data into the system by making Bob believe that she is indeed Alice. To thwart the impersonation attack by Eve, Bob utilizes the distance of the transmit node as the feature/fingerprint to carry out feature-based authentication at the physical layer. Due to authentication at Bob, due to lack of channel knowledge at the transmit node (Alice or Eve), and due to the threshold-based decoding error model, the relevant dynamics of the considered system could be modelled by a Markov chain (MC). Thus, we compute the state-transition probabilities of the MC, and the moment generating function for the service process corresponding to each state. This enables us to derive a closed-form expression of the EC in terms of authentication parameters. Furthermore, we compute the optimal transmission rate (at Alice) through gradient-descent (GD) technique and artificial neural network (ANN) method. Simulation results show that the EC decreases under severe authentication constraints (i.e., more false alarms and more transmissions by Eve). Simulation results also reveal that the (optimal transmission rate) performance of the ANN technique is quite close to that of the GD method.

Sidra Zafar, Waqas Aman, Muhammad Mahboob Ur Rahman et al.

Consider impersonation attack by an active malicious nano node (Eve) on a diffusion based molecular communication (DbMC) system---Eve transmits during the idle slots to deceive the nano receiver (Bob) that she is indeed the legitimate nano transmitter (Alice). To this end, this work exploits the 3-dimensional (3D) channel impulse response (CIR) with $L$ taps as device fingerprint for authentication of the nano transmitter during each slot. Specifically, Bob utilizes the Alice's CIR as ground truth to construct a binary hypothesis test to systematically accept/reject the data received in each slot. Simulation results highlight the great challenge posed by impersonation attack--i.e., it is not possible to simultaneously minimize the two error probabilities. In other words, one needs to tolerate on one error type in order to minimize the other error type.

Waqas Aman, Aneeqa Ijaz, M. Mahboob Ur Rahman et al.

This work presents a novel method to generate secret keys shared between a legitimate node pair (Alice and Bob) to safeguard the communication between them from an unauthorized node (Eve). To this end, we exploit the {\it reciprocal carrier frequency offset} (CFO) between the legitimate node pair to extract common randomness out of it to generate shared secret keys. The proposed key generation algorithm involves standard steps: the legitimate nodes exchange binary phase-shift keying (BPSK) signals to perform blind CFO estimation on the received signals, and do equi-probable quantization of the noisy CFO estimates followed by information reconciliation--to distil a shared secret key. Furthermore, guided by the Allan deviation curve, we distinguish between the two frequency-stability regimes---when the randomly time-varying CFO process i) has memory, ii) is memoryless; thereafter, we compute the key generation rate for both regimes. Simulation results show that the key disagreement rate decreases exponentially with increase in the signal to noise ratio of the link between Alice and Bob. Additionally, the decipher probability of Eve decreases as soon as either of the two links observed by the Eve becomes more degraded compared to the link between Alice and Bob.

Waqas Aman, Muhammad Mahboob Ur Rahman, Junaid Qadir et al.

This work considers a line-of-sight underwater acoustic sensor network (UWASN) consisting of $M$ underwater sensor nodes randomly deployed according to uniform distribution within a vertical half-disc (the so-called trusted zone). The sensor nodes report their sensed data to a sink node on water surface on a shared underwater acoustic (UWA) reporting channel in a time-division multiple-access (TDMA) fashion, while an active-yet-invisible adversary (so-called Eve) is present in the close vicinity who aims to inject malicious data into the system by impersonating some Alice node. To this end, this work first considers an additive white Gaussian noise (AWGN) UWA channel, and proposes a novel, multiple-features based, two-step method at the sink node to thwart the potential impersonation attack by Eve. Specifically, the sink node exploits the noisy estimates of the distance, the angle of arrival, and the location of the transmit node as device fingerprints to carry out a number of binary hypothesis tests (for impersonation detection) as well as a number of maximum likelihood hypothesis tests (for transmitter identification when no impersonation is detected). We provide closed-form expressions for the error probabilities (i.e., the performance) of most of the hypothesis tests. We then consider the case of a UWA with colored noise and frequency-dependent pathloss, and derive a maximum-likelihood (ML) distance estimator as well as the corresponding Cramer-Rao bound (CRB). We then invoke the proposed two-step, impersonation detection framework by utilizing distance as the sole feature. Finally, we provide detailed simulation results for both AWGN UWA channel and the UWA channel with colored noise. Simulation results verify that the proposed scheme is indeed effective for a UWA channel with colored noise and frequency-dependent pathloss.

Muhammad Mahboob Ur Rahman, Aneela Yasmeen

This paper proposes to exploit the so-called {\it reciprocity parameters} (modelling non-reciprocal communication hardware) to use them as decision metric for binary hypothesis testing based authentication framework at a receiver node Bob. Specifically, Bob first learns the reciprocity parameters of the legitimate sender Alice via initial training. Then, during the test phase, Bob first obtains a measurement of reciprocity parameters of channel occupier (Alice, or, the intruder Eve). Then, with ground truth and current measurement both in hand, Bob carries out the hypothesis testing to automatically accept (reject) the packets sent by Alice (Eve). For the proposed scheme, we provide its success rate (the detection probability of Eve), and its performance comparison with other schemes.

Sahar Imtiaz, Hadi Ghauch, M. Mahboob Ur Rahman et al.

Explosive growth in the use of smart wireless devices has necessitated the provision of higher data rates and always-on connectivity, which are the main motivators for designing the fifth generation (5G) systems. To achieve higher system efficiency, massive antenna deployment with tight coordination is one potential strategy for designing 5G systems, but has two types of associated system overhead. First is the synchronization overhead, which can be reduced by implementing a cloud radio access network (CRAN)-based architecture design, that separates the baseband processing and radio access functionality to achieve better system synchronization. Second is the overhead for acquiring channel state information (CSI) of the users present in the system, which, however, increases tremendously when instantaneous CSI is used to serve high-mobility users. To serve a large number of users, a CRAN system with a dense deployment of remote radio heads (RRHs) is considered, such that each user has a line-of-sight (LOS) link with the corresponding RRH. Since, the trajectory of movement for high-mobility users is predictable; therefore, fairly accurate position estimates for those users can be obtained, and can be used for resource allocation to serve the considered users. The resource allocation is dependent upon various correlated system parameters, and these correlations can be learned using well-known \emph{machine learning} algorithms. This paper proposes a novel \emph{learning-based resource allocation scheme} for time division duplex (TDD) based 5G CRAN systems with dense RRH deployment, by using only the users' position estimates for resource allocation, thus avoiding the need for CSI acquisition. This reduces the overall system overhead significantly, while still achieving near-optimal system performance; thus, better (effective) system efficiency is achieved. (See the paper for full abstract)