Mohammad Javad Ahmadi

Mohammad Javad Ahmadi, Rafael F. Schaefer, H. Vincent Poor

This work considers the problem of integrated sensing and communications (ISAC) with a massive number of unsourced and uncoordinated users. In the proposed model, known as the unsourced ISAC system (UNISAC), all active communication and sensing users simultaneously share a short frame to transmit their signals, without requiring scheduling with the base station (BS). Hence, the signal received from each user is affected by significant interference from numerous interfering users, making it challenging to extract the transmitted signals. UNISAC aims to decode the transmitted message sequences from communication users while simultaneously detecting active sensing users and estimating their angles of arrival, regardless of the identity of the senders. In this paper, we derive an approximate achievable result for UNISAC and demonstrate its superiority over conventional approaches such as ALOHA, time-division multiple access, treating interference as noise, and multiple signal classification. Through numerical simulations, we validate the effectiveness of UNISAC's sensing and communication capabilities for a large number of users.

Mohammad Javad Ahmadi, Rafael F. Schaefer, H. Vincent Poor

This work introduces security for unsourced random access (URA) by employing physical layer security techniques. To achieve confidentiality, the proposed system opportunistically exploits intrinsic features of feedback-aided URA without adding any overhead or altering its original structure or operational characteristics. As a result, the proposed system preserves the low-cost advantages of URA, including low delay and minimal signaling overhead, while providing secure communication. To secure transmission, each user generates a secret key from a feedback signal broadcast by the BS in a previous transmission round. This feedback depends on the BS-user channel, making it a private signal for each user. Secure transmission is achieved not only through encryption using the secret key, but also by transmitting only the parity bits of the LDPC-encoded key, thereby enabling its recovery at the legitimate receiver via Slepian-Wolf decoding with side information. For reception, a receiver algorithm is designed for the legitimate receiver, and a leakage analysis is provided to quantify the information available to the eavesdropper. The simulation results show that meaningful secrecy is achieved in URA without modifying its structure.

Farshad Rostami Ghadi, Kai-Kit Wong, Masoud Kaveh et al.

Enormous fluid antenna systems (E-FAS) have recently emerged as a surface-wave (SW)-enabled architecture that can induce controllable large-scale channel gains through guided electromagnetic routing. This paper develops a secrecy analysis framework for E-FAS-assisted downlink transmission with practical pilot-based channel estimation. We consider a multiple-input single-output (MISO) wiretap setting in which the base station (BS) performs minimum mean-square-error (MMSE) channel estimation and adopts maximum-ratio transmission (MRT) with artificial noise (AN). To capture the leakage of SW routing in EFAS, we introduce a correlated SW-leakage model that accounts for statistical coupling between the legitimate and eavesdropper channels caused by partially overlapping SW propagation paths. Exploiting the two-timescale nature-with slowly varying routing gain and small-scale block fading, we then derive a closed-form conditional expression for the secrecy outage probability (SOP) and a tractable characterization of the ergodic secrecy rate (ESR) in the presence of correlated quadratic forms. Our analysis yields three key insights: (i) secrecy collapses at high transmit power if and only if AN is not present, whereas any strictly positive AN can prevent asymptotic collapse; (ii) the optimal data-AN power split is achieved by a strictly interior solution; and (iii) routing gain improves both the received signal strength and the channelestimation quality, creating a nonlinear coupling that raises the signal-to-interference plus noise ratio (SINR) ceiling in the high signal-to-noise ratio (SNR) regime, and disperses secrecy across routing states. Numerical results indicate that E-FAS markedly enlarges the secure operating region significantly when compared with conventional space-wave transmission.

Tanaz Ghahremani, Mohammad Hoseyni, Mohammad Javad Ahmadi et al.

Data augmentation is a key technique for addressing the challenge of limited datasets, which have become a major component in the training procedures of image processing. Techniques such as geometric transformations and color space adjustments have been thoroughly tested for their ability to artificially expand training datasets and generate semi-realistic data for training purposes. Data augmentation is the most important key to addressing the challenge of limited datasets, which have become a major component of image processing training procedures. Data augmentation techniques, such as geometric transformations and color space adjustments, are thoroughly tested for their ability to artificially expand training datasets and generate semi-realistic data for training purposes. Polygons play a crucial role in instance segmentation and have seen a surge in use across advanced models, such as YOLOv8. Despite their growing popularity, the lack of specialized libraries hampers the polygon-augmentation process. This paper introduces a novel solution to this challenge, embodied in the newly developed AugmenTory library. Notably, AugmenTory offers reduced computational demands in both time and space compared to existing methods. Additionally, the library includes a postprocessing thresholding feature. The AugmenTory package is publicly available on GitHub, where interested users can access the source code: https://github.com/Smartory/AugmenTory

Arefeh Rezaei, Mohammad Javad Ahmadi, Amir Molaei et al.

This paper aims to present a novel pipeline for automated surgical skill assessment using video data and to showcase the effectiveness of the proposed approach in evaluating surgeon proficiency, its potential for targeted training interventions, and quality assurance in surgical departments. The pipeline incorporates a representation flow convolutional neural network and a novel tree-based Gaussian process classifier, which is robust to noise, while being computationally efficient. Additionally, new kernels are introduced to enhance accuracy. The performance of the pipeline is evaluated using the JIGSAWS dataset. Comparative analysis with existing literature reveals significant improvement in accuracy and betterment in computation cost. The proposed pipeline contributes to computational efficiency and accuracy improvement in surgical skill assessment using video data. Results of our study based on comments of our colleague surgeons show that the proposed method has the potential to facilitate skill improvement among surgery fellows and enhance patient safety through targeted training interventions and quality assurance in surgical departments.

Mohammad Javad Ahmadi, Iman Gandomi, Parisa Abdi et al.

The development of computer-assisted surgery systems depends on large-scale, annotated datasets. Current resources for cataract surgery often lack the diversity and annotation depth needed to train generalizable deep-learning models. To address this gap, we present a dataset of 3,000 phacoemulsification cataract surgery videos from two surgical centers, performed by surgeons with a range of experience levels. This resource is enriched with four annotation layers: temporal surgical phases, instance segmentation of instruments and anatomical structures, instrument-tissue interaction tracking, and quantitative skill scores based on the established competency rubrics like the ICO-OSCAR. The technical quality of the dataset is supported by a series of benchmarking experiments for key surgical AI tasks, including workflow recognition, scene segmentation, and automated skill assessment. Furthermore, we establish a domain adaptation baseline for the phase recognition task by training a model on a subset of surgical centers and evaluating its performance on a held-out center. The dataset and annotations are available in Google Form (https://docs.google.com/forms/d/e/1FAIpQLSfmyMAPSTGrIy2sTnz0-TMw08ZagTimRulbAQcWdaPwDy187A/viewform?usp=dialog).