arXiv subjects

Muhammad Mahboob Ur Rahman

Publications and source records attributed to Muhammad Mahboob Ur Rahman.

At least 19 recordsLinked to original sources

arXiv2026

Pre- and Post-Exercise Monitoring of Physiological Skin States in Sportsmen Using 77 GHz FMCW Radar and Wavelet Scattering Transform

This paper presents a contactless radar sensing framework that classifies physiologically-induced changes in the superficial skin layer following intense fixed-duration physical activity along with water intake restriction. A 77 GHz frequency-modulated continuous wave (FMCW) radar is used to capture high-resolution range profiles from the subject's chest, seated in front of the radar, before and after sports activity. Since the electromagnetic penetration into biological tissue is inherently shallow at millimeter-wave frequencies, the sensing is confined primarily to the stratum corneum and upper epidermis. We demonstrate that exercise-induced thermoregulation, perspiration residue deposition, and transient shifts in superficial tissue hydration produce measurable alterations in quasi-static radar reflectivity. We utilize single-chirp snapshots of duration 102.4 micro sec in order to suppress confounders such as slow-varying cardiopulmonary motion, followed by lightweight feature extraction via the Wavelet Scattering Transform (WST) and classification using light-weight machine learning models suitable for edge nodes. Leave-one-subject-out cross-validation on a dataset of 15 sportsmen measured pre- and post-exercise yields a mean classification accuracy of 91.55% with a 95% confidence interval of [84.27, 98.83]%. Interpretability analysis reveals that low-order scattering coefficients (capturing overall signal energy and amplitude stability) dominate discriminative power, consistent with quasi-static changes in skin surface permittivity. The results establish a proof-of-concept for radar-based, edge deployable classification of post-exercise skin states, opening new avenues for non-contact physiological monitoring in sports science.

eess.SP↗

arXiv2026

Prayer-Gait-Auth: Smartphone IMU-based Behavioral Biometrics from Structured Islamic Prayer Movements

Islamic prayer is a structured movement activity that offers a distinctive setting for behavioral biometrics: all participants execute the same action sequence, so identity must be inferred from differences in execution. We collected inertial data from 95 participants using their own smartphones during nightly congregational Islamic prayer (Taraweeh). A label-aware pipeline converts long recordings into structurally complete two-rakaah behavioral samples (prayer units). This allows us to design unit-level and complete-session behavioral biometrics protocols. To address arbitrary smartphone orientation in worshippers' pockets, we study two motion representations: rotation-invariant magnitudes with gravity-relative acceleration components, and a metadata-aware Qibla-referenced canonicalization that harmonizes platform conventions, reconstructs device-to-world attitude, corrects Android magnetic north to true north via WMM2025, and expresses acceleration and angular velocity in a common Qibla-left-up frame. Under unit-level protocol, the invariant and Qibla-referenced representations reach learned pairwise Random Forest AUC/EER of 0.9932/4.07% and 0.9923/3.96%; under complete-session holdout, 0.9700/7.62% and 0.9618/7.81%. Qibla-frame directional ablations show the complete six-axis representation is strongest overall, with acceleration retaining most learned-verification performance and vertical motion the strongest single-axis cue. A Qibla-referenced SimCLR experiment further yields participant-template AUC 0.9805-0.9817 and EER 5.81-6.24% across two unit-level runs. Signal-, descriptor-, prayer-component ablation analyses show participant identity is distributed across movement dynamics rather than concentrated in one signal or posture. These results establish structured prayer movement as a measurable cross-session behavioral biometric.

eess.SP↗

arXiv2026

Malicious Pseudo-Ranging and Localization of Static LOS Wireless Users via Downlink Modulation Classification and Uplink Refinement

The broadcast nature of the wireless medium and openness of wireless standards, e.g., 3GPP releases 16-20, invite adversaries to launch various active and passive attacks on cellular and other wireless networks. This work identifies one such loose end of wireless standards and presents a novel passive attack method enabling an eavesdropper (Eve) to localize a line-of-sight stationary wireless user (Bob) who is communicating with a base station or WiFi access point (Alice). The proposed attack involves two phases. In the first phase, Eve performs modulation classification by intercepting the downlink channel between Alice and Bob. This enables Eve to utilize the publicly available modulation and coding scheme tables to do pesudo-ranging, i.e., the Eve determines the ring within which Bob is located, which drastically reduces the search space. In the second phase, Eve sniffs the uplink channel, and employs multiple strategies to further refine Bob's location within the ring. In simulations, the proposed attack is validated for single-user, multi-user, and multiple-antenna scenarios. Towards the end, we present our thoughts on how this attack can be extended to other scenarios such as non-line-of-sight and mobile users e.g., cars, drones, pedestrians, and how this attack could act as a scaffolding to construct a malicious digital twin map.

cs.IT↗

arXiv2026

ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook

Electrocardiogram (ECG) foundation models represent a paradigm shift from task-specific pipelines to generalizable architectures pre-trained on large-scale unlabeled waveform data. This survey presents a unified and deployment-aware review of foundation models and medical large language models (LLMs) for ECG intelligence in cardiovascular disease (CVD) diagnosis, monitoring, and clinical decision support. The central thesis of this survey paper is that next-generation cardiovascular AI systems will be inherently agentic, requiring the synergistic integration of two complementary model classes: (i) ECG foundation models that act as signal-level interpreters, learning rich electrophysiological representations via self-supervised and multimodal pretraining, and (ii) medical LLMs, trained on biomedical text corpora, that function as knowledge-based reasoning backbones for contextual inference, guideline alignment, and clinical decision support. Thus, the survey systematically reviews existing pool of generalist medical LLMs, as well as ECG foundation models that utilize techniques such as self-supervised learning, multimodal ECG-language alignment, vision transformer architectures, and possess capabilities such as zero-shot classification, automated report generation, and longitudinal risk modeling. Recognizing the constraints of consumer-grade wearable edge devices, we further examine model optimization techniques such as quantization, pruning, knowledge distillation, as well as the role of small language models in enabling low-latency, energy-efficient, and privacy-preserving ECG intelligence on edge platforms such as smartwatches. Finally, we outline future directions in multimodal ECG foundation models, agent-driven monitoring, and explainable, secure edge intelligence, with particular emphasis on real-time, on-device cardiovascular analytics in consumer electronics ecosystems.

eess.SP↗

arXiv2025

Effective Capacity Analysis of Joint Near and Far-Field Communication in 6G URLLC Networks

The emergence of 6G networks enables simultaneous near-field and far-field communications through extremely large antenna arrays and high carrier frequencies. While these regimes enhance spatial multiplexing and link capacity, their coexistence poses new challenges in ensuring quality-of-service (QoS) guarantees for delay-sensitive applications. This paper presents an effective capacity (EC) analysis framework that jointly models near- and far-field communication regimes under distance estimation uncertainty. The user location is modeled as a random variable spanning both propagation regions, and tractable closed-form expression for the EC is derived to quantify delay performance. Numerical results illustrate the impact of estimation variance, QoS exponent, far-field boundary and near-field boundary (Fraunhofer distance) on EC performance.

eess.SP↗

arXiv2025

Towards Human-AI-Robot Collaboration and AI-Agent based Digital Twins for Parkinson's Disease Management: Review and Outlook

The current body of research on Parkinson's disease (PD) screening, monitoring, and management has evolved along two largely independent trajectories. The first research community focuses on multimodal sensing of PD-related biomarkers using noninvasive technologies such as inertial measurement units (IMUs), force/pressure insoles, electromyography (EMG), electroencephalography (EEG), speech and acoustic analysis, and RGB/RGB-D motion capture systems. These studies emphasize data acquisition, feature extraction, and machine learning-based classification for PD screening, diagnosis, and disease progression modeling. In parallel, a second research community has concentrated on robotic intervention and rehabilitation, employing socially assistive robots (SARs), robot-assisted rehabilitation (RAR) systems, and virtual reality (VR)-integrated robotic platforms for improving motor and cognitive function, enhancing social engagement, and supporting caregivers. Despite the complementary goals of these two domains, their methodological and technological integration remains limited, with minimal data-level or decision-level coupling between the two. With the advent of advanced artificial intelligence (AI), including large language models (LLMs), agentic AI systems, a unique opportunity now exists to unify these research streams. We envision a closed-loop sensor-AI-robot framework in which multimodal sensing continuously guides the interaction between the patient, caregiver, humanoid robot (and physician) through AI agents that are powered by a multitude of AI models such as robotic and wearables foundation models, LLM-based reasoning, reinforcement learning, and continual learning. Such closed-loop system enables personalized, explainable, and context-aware intervention, forming the basis for digital twin of the PD patient that can adapt over time to deliver intelligent, patient-centered PD care.

eess.SP↗

arXiv2025

Electromagnetically Reconfigurable Fluid Antenna System for Wireless Communications: Design, Modeling, Algorithm, Fabrication, and Experiment

This paper presents the concept, design, channel modeling, beamforming algorithm development, prototype fabrication, and experimental measurement of an electromagnetically reconfigurable fluid antenna system (ER-FAS), in which each FAS array element features electromagnetic (EM) reconfigurability. Unlike most existing FAS works that investigate spatial reconfigurability by adjusting the position and/or orientation of array elements, the proposed ER-FAS enables direct control over the EM characteristics of each element, allowing for dynamic radiation pattern reconfigurability. Specifically, a novel ER-FAS architecture leveraging software-controlled fluidics is proposed, and corresponding wireless channel models are established. Based on this ER-FAS channel model, a low-complexity greedy beamforming algorithm is developed to jointly optimize the analog phase shift and the radiation state of each array element. The accuracy of the ER-FAS channel model and the effectiveness of the beamforming algorithm are validated through (i) full-wave EM simulations and (ii) numerical spectral efficiency evaluations. These results confirm that the proposed ER-FAS significantly enhances spectral efficiency in both near-field and far-field scenarios compared to conventional antenna arrays. To further validate this design, we fabricate prototypes for both the ER-FAS element and array, using Galinstan liquid metal alloy, fluid silver paste, and software-controlled fluidic channels. The simulation results are experimentally validated through prototype measurements conducted in an anechoic chamber. Additionally, several indoor communication experiments using a pair of software-defined radios demonstrate the superior received power and bit error rate performance of the ER-FAS prototype.

eess.SP↗

arXiv2025

Radio-PPG: photoplethysmogram digital twin synthesis using deep neural representation of 6G/WiFi ISAC signals

Digital twins for 1D bio-signals enable real-time monitoring of physiological processes of a person, which enables early disease diagnosis and personalized treatment. This work introduces a novel non-contact method for digital twin (DT) photoplethysmogram (PPG) signal synthesis under the umbrella of 6G/WiFi integrated sensing and communication (ISAC) systems. We employ a software-defined radio (SDR) operating at 5.23 GHz that illuminates the chest of a nearby person with a wideband 6G/WiFi signal and collects the reflected signals. This allows us to acquire Radio-PPG dataset that consists of 300 minutes worth of near synchronous 64-channel radio data, PPG data, along with the labels (three body vitals) of 30 healthy subjects. With this, we test two artificial intelligence (AI) models for DT-PPG signal synthesis: i) discrete cosine transform followed by a multi-layer perceptron, ii) two U-NET models (Approximation network, Refinement network) in cascade, along with a custom loss function. Experimental results indicate that U-NET model achieves an impressive relative mean absolute error of 0.194 with a small ISAC sensing overhead of 15.62%, for DT-PPG synthesis. Furthermore, we performed quality assessment of the synthetic DT-PPG by computing the accuracy of DT-PPG-based vitals estimation and feature extraction, which turned out to be at par with that of reference PPG-based vitals estimation and feature extraction. This work highlights the potential of generative AI and 6G/WiFi ISAC technologies and serves as a foundational step towards the development of non-contact screening tools for covid-19, cardiovascular diseases and well-being assessment of people with special needs.

cs.IT↗

arXiv2024

Internet of medical things for non-invasive and non-contact dehydration monitoring away from the hospital: state-of-the-art, challenges and prospects

Dehydration occurs when the body loses more water than it takes in. Mild dehydration can lead to fatigue, cognitive impairments, and physical complications, while severe dehydration can cause life-threatening conditions like heat stroke, kidney damage, and hypovolemic shock. Traditional bio chemistry-based clinical gold standard methods are expensive, time-consuming, and invasive. Thus, there is a pressing need to design novel non-invasive methods that could do in-situ, early and accurate detection of dehydration, which will in turn allow timely intervention. This article presents a methodological review of the literature on a range of innovative internet of medical things-based techniques for dehydration monitoring. We begin by briefly describing the pathophysiology of the dehydration problem, its clinical significance, and current clinical gold-standard methods for assessing hydration level. Subsequently, we critically examine a number of non-invasive and non-contact hydration assessment studies. We also discuss multi-modal sensing methods and assess the impact of dehydration among specific population groups (e.g., elderly, infants, athletes) and on different organs. We also provide a list of existing public and private datasets which make the backbone of machine learning-driven research on dehydration monitoring. Finally, we provide our opinion statement on the challenges and future prospects of non-invasive and non-contact hydration monitoring.

eess.SP↗

arXiv2024

Inferior Myocardial Infarction Detection from lead II of ECG: A Gramian Angular Field-based 2D-CNN Approach

This paper presents a novel method for inferior myocardial infarction (MI) detection using lead II of electrocardiogram (ECG). We evaluate our proposed method on a public dataset, namely, Physikalisch Technische Bundesanstalt (PTB) ECG dataset from Physionet. Under our proposed method, we first clean the noisy ECG signals using db4 wavelet, followed by an R-peak detection algorithm to segment the ECG signals into beats. We then translate the ECG timeseries dataset to an equivalent dataset of gray-scale images using Gramian Angular Summation Field (GASF) and Gramian Angular Difference Field (GADF) operations. Subsequently, the gray-scale images are fed into a custom two-dimensional convolutional neural network (2D-CNN) which efficiently differentiates between a healthy subject and a subject with MI. Our proposed approach achieves an average classification accuracy of 99.68%, 99.80%, 99.82%, and 99.84% under GASF dataset with noise and baseline wander, GADF dataset with noise and baseline wander, GASF dataset with noise and baseline wander removed, and GADF dataset with noise and baseline wander removed, respectively. Most importantly, this work opens the floor for innovation in wearable devices to measure lead II ECG (e.g., by a smart watch worn on right wrist, along with a smart patch on left leg), in order to do accurate, real-time and early detection of inferior wall MI.

eess.SP↗

arXiv2024

Cuff-less Arterial Blood Pressure Waveform Synthesis from Single-site PPG using Transformer & Frequency-domain Learning

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).

eess.SP↗

arXiv2024

Heart Murmur and Abnormal PCG Detection via Wavelet Scattering Transform & a 1D-CNN

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.

eess.SP↗

arXiv2024

Non-contact Lung Disease Classification via OFDM-based Passive 6G ISAC Sensing

This paper is the first to present a novel, non-contact method that utilizes orthogonal frequency division multiplexing (OFDM) signals (of frequency 5.23 GHz, emitted by a software defined radio) to radio-expose the pulmonary patients in order to differentiate between five prevalent respiratory diseases, i.e., Asthma, Chronic obstructive pulmonary disease (COPD), Interstitial lung disease (ILD), Pneumonia (PN), and Tuberculosis (TB). The fact that each pulmonary disease leads to a distinct breathing pattern, and thus modulates the OFDM signal in a different way, motivates us to acquire OFDM-Breathe dataset, first of its kind. It consists of 13,920 seconds of raw RF data (at 64 distinct OFDM frequencies) that we have acquired from a total of 116 subjects in a hospital setting (25 healthy control subjects, and 91 pulmonary patients). Among the 91 patients, 25 have Asthma, 25 have COPD, 25 have TB, 5 have ILD, and 11 have PN. We implement a number of machine and deep learning models in order to do lung disease classification using OFDM-Breathe dataset. The vanilla convolutional neural network outperforms all the models with an accuracy of 97%, and stands out in terms of precision, recall, and F1-score. The ablation study reveals that it is sufficient to radio-observe the human chest on seven different microwave frequencies only, in order to make a reliable diagnosis (with 96% accuracy) of the underlying lung disease. This corresponds to a sensing overhead that is merely 10.93% of the allocated bandwidth. This points to the feasibility of 6G integrated sensing and communication (ISAC) systems of future where 89.07% of bandwidth still remains available for information exchange amidst on-demand health sensing. Through 6G ISAC, this work provides a tool for mass screening for respiratory diseases (e.g., COVID-19) at public places.

eess.SP↗

arXiv2024

Non-Contact Acquisition of PPG Signal using Chest Movement-Modulated Radio Signals

We present for the first time a novel method that utilizes the chest movement-modulated radio signals for non-contact acquisition of the photoplethysmography (PPG) signal. Under the proposed method, a software-defined radio (SDR) exposes the chest of a subject sitting nearby to an orthogonal frequency division multiplexing signal with 64 sub-carriers at a center frequency 5.24 GHz, while another SDR in the close vicinity collects the modulated radio signal reflected off the chest. This way, we construct a custom dataset by collecting 160 minutes of labeled data (both raw radio data as well as the reference PPG signal) from 16 healthy young subjects. With this, we first utilize principal component analysis for dimensionality reduction of the radio data. Next, we denoise the radio signal and reference PPG signal using wavelet technique, followed by segmentation and Z-score normalization. We then synchronize the radio and PPG segments using cross-correlation method. Finally, we proceed to the waveform translation (regression) task, whereby we first convert the radio and PPG segments into frequency domain using discrete cosine transform (DCT), and then learn the non-linear regression between them. Eventually, we reconstruct the synthetic PPG signal by taking inverse DCT of the output of regression block, with a mean absolute error of 8.1294. The synthetic PPG waveform has a great clinical significance as it could be used for non-contact performance assessment of cardiovascular and respiratory systems of patients suffering from infectious diseases, e.g., covid19.

eess.SP↗

arXiv2024

You can monitor your hydration level using your smartphone camera

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.

eess.SP↗

arXiv2024

Dense Optical Flow Estimation Using Sparse Regularizers from Reduced Measurements

Optical flow is the pattern of apparent motion of objects in a scene. The computation of optical flow is a critical component in numerous computer vision tasks such as object detection, visual object tracking, and activity recognition. Despite a lot of research, efficiently managing abrupt changes in motion remains a challenge in motion estimation. This paper proposes novel variational regularization methods to address this problem since they allow combining different mathematical concepts into a joint energy minimization framework. In this work, we incorporate concepts from signal sparsity into variational regularization for motion estimation. The proposed regularization uses a robust l1 norm, which promotes sparsity and handles motion discontinuities. By using this regularization, we promote the sparsity of the optical flow gradient. This sparsity helps recover a signal even with just a few measurements. We explore recovering optical flow from a limited set of linear measurements using this regularizer. Our findings show that leveraging the sparsity of the derivatives of optical flow reduces computational complexity and memory needs.

eess.SP↗

arXiv2023

A low-cost PPG sensor-based empirical study on healthy aging based on changes in PPG morphology

We present the findings of an experimental study whereby we correlate the changes in the morphology of the photoplethysmography (PPG) signal to healthy aging. Under this pretext, we estimate the biological age of a person as well as the age group he/she belongs to, using the PPG data that we collect via a non-invasive low-cost MAX30102 PPG sensor. Specifically, we collect raw infrared PPG data from the finger-tip of 179 apparently healthy subjects, aged 3-65 years. In addition, we record the following metadata of each subject: age, gender, height, weight, family history of cardiac disease, smoking history, vitals (heart rate and SpO2). We pre-process the raw PPG data to remove noise, artifacts, and baseline wander. We then construct 60 features based upon the first four PPG derivatives, the so-called VPG, APG, JPG, and SPG signals, and the demographic features. We then do correlation-based feature-ranking (which retains 26 most important features), followed by Gaussian noise-based data augmentation (which results in 15-fold increase in the size of our dataset). Finally, we feed the feature set to three machine learning classifiers (logistic regression, decision tree, random forest), and two shallow neural networks: a feedforward neural network (FFNN) and a convolutional neural network (CNN). For the age group classification, the shallow FFNN performs the best with 98% accuracy for binary classification (3-15 years vs. 15+ years), and 97% accuracy for three-class classification (3-12 years, 13-30 years, 30+ years). For biological age prediction, the shallow FFNN again performs the best with a mean absolute error (MAE) of 1.64.

eess.SP↗

arXiv2023

Multi-class Network Intrusion Detection with Class Imbalance via LSTM & SMOTE

Monitoring network traffic to maintain the quality of service (QoS) and to detect network intrusions in a timely and efficient manner is essential. As network traffic is sequential, recurrent neural networks (RNNs) such as long short-term memory (LSTM) are suitable for building network intrusion detection systems. However, in the case of a few dataset examples of the rare attack types, even these networks perform poorly. This paper proposes to use oversampling techniques along with appropriate loss functions to handle class imbalance for the detection of various types of network intrusions. Our deep learning model employs LSTM with fully connected layers to perform multi-class classification of network attacks. We enhance the representation of minority classes: i) through the application of the Synthetic Minority Over-sampling Technique (SMOTE), and ii) by employing categorical focal cross-entropy loss to apply a focal factor to down-weight examples of the majority classes and focus more on hard examples of the minority classes. Extensive experiments on KDD99 and CICIDS2017 datasets show promising results in detecting network intrusions (with many rare attack types, e.g., Probe, R2L, DDoS, PortScan, etc.).

cs.CR↗