Behrouz Far

Esmaeil Shakeri, Ronnie de Souza Santos, Behrouz Far

Deep reinforcement learning (DRL) is increasingly applied to de novo molecular design, but choices in data, rewards, and evaluation can yield uneven performance across disease areas and chemotypes. Despite this, there is no concise synthesis of how fairness is defined, measured, and tested in DRL-based drug discovery. In this rapid evidence review, we synthesize fairness definitions and metrics for DRL-driven molecule generation in healthcare. We focus on three questions: (i) how dataset composition and split strategies, especially scaffold versus random splits, affect evaluation and distribution shift; (ii) how reward design (e.g., QED, docking, toxicity, synthetic accessibility) can create or mitigate bias, with emphasis on cancer targets; and (iii) which measurable metrics best capture fairness. This includes parity across cancer versus non-cancer indications and across cancer subtypes. It also includes distributional balance in key physicochemical descriptors, scaffold/chemotype diversity, groupwise validity, toxicity, and synthetic accessibility. From 2017 onward, we searched major biomedical, computer science, and engineering literature databases and used arXiv for horizon scanning. Records were screened using PRISMA-style procedures and analyzed via content coding to link reported parity outcomes to dataset and reward choices. Our review provides a concise set of fairness definitions and metrics for DRL molecule generation. It offers practical guidance for reporting distribution parity and outcome parity. It also summarizes how dataset and reward choices relate to observed parity effects and identifies open gaps relevant to trustworthy, cancer-relevant DRL generation.

Mohammadmahdi Eshragh, Emad A. Mohammed, Behrouz Far et al.

Choroidal nevi are common benign pigmented lesions in the eye, with a small risk of transforming into melanoma. Early detection is critical to improving survival rates, but misdiagnosis or delayed diagnosis can lead to poor outcomes. Despite advancements in AI-based image analysis, diagnosing choroidal nevi in colour fundus images remains challenging, particularly for clinicians without specialized expertise. Existing datasets often suffer from low resolution and inconsistent labelling, limiting the effectiveness of segmentation models. This paper addresses the challenge of achieving precise segmentation of fundus lesions, a critical step toward developing robust diagnostic tools. While deep learning models like U-Net have demonstrated effectiveness, their accuracy heavily depends on the quality and quantity of annotated data. Previous mathematical/clustering segmentation methods, though accurate, required extensive human input, making them impractical for medical applications. This paper proposes a novel approach that combines mathematical/clustering segmentation models with insights from U-Net, leveraging the strengths of both methods. This hybrid model improves accuracy, reduces the need for large-scale training data, and achieves significant performance gains on high-resolution fundus images. The proposed model achieves a Dice coefficient of 89.7% and an IoU of 80.01% on 1024*1024 fundus images, outperforming the Attention U-Net model, which achieved 51.3% and 34.2%, respectively. It also demonstrated better generalizability on external datasets. This work forms a part of a broader effort to develop a decision support system for choroidal nevus diagnosis, with potential applications in automated lesion annotation to enhance the speed and accuracy of diagnosis and monitoring.

Farid Talebloo, Emad A. Mohammed, Behrouz Far

Driving behaviour is one of the primary causes of road crashes and accidents, and these can be decreased by identifying and minimizing aggressive driving behaviour. This study identifies the timesteps when a driver in different circumstances (rush, mental conflicts, reprisal) begins to drive aggressively. An observer (real or virtual) is needed to examine driving behaviour to discover aggressive driving occasions; we overcome this problem by using a smartphone's GPS sensor to detect locations and classify drivers' driving behaviour every three minutes. To detect timeseries patterns in our dataset, we employ RNN (GRU, LSTM) algorithms to identify patterns during the driving course. The algorithm is independent of road, vehicle, position, or driver characteristics. We conclude that three minutes (or more) of driving (120 seconds of GPS data) is sufficient to identify driver behaviour. The results show high accuracy and a high F1 score.

Mehdi Afsar, Trafford Crump, Behrouz Far

Recommender systems (RSs) are software tools and algorithms developed to alleviate the problem of information overload, which makes it difficult for a user to make right decisions. Two main paradigms toward the recommendation problem are collaborative filtering and content-based filtering, which try to recommend the best items using ratings and content available. These methods typically face infamous problems including cold-start, diversity, scalability, and great computational expense. We argue that the uptake of deep learning and reinforcement learning methods is also questionable due to their computational complexities and uninterpretability. In this paper, we approach the recommendation problem from a new prospective. We borrow ideas from cluster head selection algorithms in wireless sensor networks and adapt them to the recommendation problem. In particular, we propose Load Balanced Recommender System (LBRS), which uses a probabilistic scheme for item recommendation. Furthermore, we factor in the importance of items in the recommendation process, which significantly improves the recommendation accuracy. We also introduce a method that considers a heterogeneity among items, in order to balance the similarity and diversity trade-off. Finally, we propose a new metric for diversity, which emphasizes the importance of diversity not only from an intra-list perspective, but also from a between-list point of view. With experiments in a simulation study performed on RecSim, we show that LBRS is effective and can outperform baseline methods.

M. Mehdi Afsar, Trafford Crump, Behrouz Far

Recommender systems (RSs) have become an inseparable part of our everyday lives. They help us find our favorite items to purchase, our friends on social networks, and our favorite movies to watch. Traditionally, the recommendation problem was considered to be a classification or prediction problem, but it is now widely agreed that formulating it as a sequential decision problem can better reflect the user-system interaction. Therefore, it can be formulated as a Markov decision process (MDP) and be solved by reinforcement learning (RL) algorithms. Unlike traditional recommendation methods, including collaborative filtering and content-based filtering, RL is able to handle the sequential, dynamic user-system interaction and to take into account the long-term user engagement. Although the idea of using RL for recommendation is not new and has been around for about two decades, it was not very practical, mainly because of scalability problems of traditional RL algorithms. However, a new trend has emerged in the field since the introduction of deep reinforcement learning (DRL), which made it possible to apply RL to the recommendation problem with large state and action spaces. In this paper, a survey on reinforcement learning based recommender systems (RLRSs) is presented. Our aim is to present an outlook on the field and to provide the reader with a fairly complete knowledge of key concepts of the field. We first recognize and illustrate that RLRSs can be generally classified into RL- and DRL-based methods. Then, we propose an RLRS framework with four components, i.e., state representation, policy optimization, reward formulation, and environment building, and survey RLRS algorithms accordingly. We highlight emerging topics and depict important trends using various graphs and tables. Finally, we discuss important aspects and challenges that can be addressed in the future.