Qatar Mobility Innovations Center

While food waste remains a significant global climate burden, effective demand planning in retail can reduce overstocking, propagating toward sustainable Agri-Food Supply Chains (AFSCs). From here, this paper employs density map modeling with Edge Intelligence (Edge-AI) technology to identify the On-Shelf Availability (OSA) index in retailers. A lightweight and efficient variant of the Multi-Column Convolutional Neural Network (MCNN), referred to as Modified Multi-Column Convolutional Neural Network (mMCNN), is proposed for edge-based density estimation. Moreover, a novel dataset called AgriShelf is curated to serve as a benchmark for this application. Extensive tests on edge platforms, Jetson Nano and Jetson Orin Nano, show that mMCNN outperforms the original MCNN in computational efficiency, with only a nominal drop in counting accuracy. Notably, Jetson Orin Nano achieves superior performance, reaching an inference speed of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{0. 0 1 5}$</tex> seconds. To this end, the integration of Edge-AI and density map modeling provides real-time insights that reduce food waste, optimize replenishments, and drive sustainable policy decisions across AFSCs.

Recent advancements have sparked a growing interest in integrating spatiotemporal analysis with large-scale language models. However, spatiotemporal data often contains sensitive information, making it unsuitable for open third-party access. To address this challenge, we propose a Graph-GAN-based model for generating privacy-protected spatiotemporal data. Our approach incorporates spatial and temporal attention blocks in the discriminator and a spatiotemporal deconvolution structure in the generator. These enhancements enable efficient training under Gaussian noise to achieve differential privacy. Extensive experiments conducted on three real-world spatiotemporal datasets validate the efficacy of our model. Our method provides a privacy guarantee while maintaining the data utility. The prediction model trained on our generated data maintains a competitive performance compared to the model trained on the original data.

In-vehicle networks (IVNs) connect numerous sensors, processors, and Electronic Control Units (ECUs) to enable real-time communication, but their growing complexity has amplified cybersecurity concerns. The Controller Area Network (CAN) bus, along with its variants CAN-FD, CAN-XL, and complementary protocols such as LIN and FlexRay, remains the backbone of IVNs. However, these protocols (the CAN specifically) were not originally designed to meet the stringent security demands of emerging autonomous and electric vehicles. This survey critically examines existing IVN security literature with a particular focus on intrusion detection systems (IDS) developed for CAN-based architectures. Unlike prior reviews that emphasize algorithmic design or attack taxonomy, this survey provides a comparison of IDS approaches (typically CAN-based due to its dominance in industry and research domain) based on physical-layer features, statistical parameters, information theory, and learning-based methods. We highlight unresolved security limitations of the CAN bus, synthesize mitigation strategies across industrial domains (automotive, aerospace, marine, agricultural, and battery systems), and identify overlooked challenges. Finally, we outline key research frontiers, such as hardware-assisted protection, edge intelligence, blockchainbased authentication, generative AI-driven anomaly detection, and quantum-safe cryptography—toward building resilient next-generation IVNs.

The exposure of insular species to local disturbances can influence their evolutionary trajectory resulting in specific adaptations. On the island La Palma, Canary Islands, the archipelago-endemic tree species Pinus canariensis forms forest ecosystems and has been described to be adapted to wildfires. The frequency of these in the recent past, however, is higher due to anthropogenic activities. Recent studies suggest that the species traits might also be an evolutionary response to volcanic outbreaks, consisting of massive sulfur dioxide (SO₂) emissions and ash fall. Several stands of P. canariensis have been exposed to both disturbances, wildfires and volcanic outbreaks, in the recent past. We assess the recovery of P. canariensis after double exposure to these disturbances. P. canariensis recovery was assessed based on Sentintel-2 NDVI images within a 7 km radius of the craters of the Tajogaite volcano that erupted in 2021. Within the same area, wildfires occurred in 2009, 2012 and 2016. We used a Generalized Additive Model (GAM) to assess the recovery of P. canariensis after volcanic and wildfire disturbances. The model shows the P. canariensis forest recovers after the volcanic outbreak with a peak at a distance of 1000–1200 m to the eruption crater, which is in line with our first hypothesis. Our second hypothesis was met with unexpected results, forests exposed to the recent wildfire in 2016 showed an increased recovery, which underlines that P. canariensis exhibits traits related to fire adaptation or might also be the result of stand-specific characteristics such as forest height or local topography. The double pressure of volcanic and forest fire disturbances did not lead to suppressed recovery of the Canary-endemic tree species and highlights the resilience of P. canariensis.

Visible Light Communication (VLC) is an emerging technology that has gained significant attention in recent years due to its immense potential for transforming transportation systems. VLC enables short-range high-speed, secure, and reliable vehicle-to-vehicle and vehicle-to-infrastructure communication in various use cases. This work delves into compelling applications of VLC in transportation, highlighting its unique advantages over traditional communication technologies. Leveraging high-speed, secure, and reliable vehicle and vehicle-to-infrastructure communication, VLC offers unprecedented opportunities for enhancing road safety, traffic management, and overall transportation efficiency.

This paper presents Haris, an advanced autonomous mobile robot system for tracking the location of vehicles in crowded car parks using license plate recognition. The system employs simultaneous localization and mapping (SLAM) for autonomous navigation and precise mapping of the parking area, eliminating the need for GPS dependency. In addition, the system utilizes a sophisticated framework using computer vision techniques for object detection and automatic license plate recognition (ALPR) for reading and associating license plate numbers with location data. This information is subsequently synchronized with a back-end service and made accessible to users via a user-friendly mobile app, offering effortless vehicle location and alleviating congestion within the parking facility. The proposed system has the potential to improve the management of short-term large outdoor parking areas in crowded places such as sports stadiums. The demo of the robot can be found on https://youtu.be/ZkTCM35fxa0?si=QjggJuN7M1o3oifx.

Recent advances in deep learning techniques have achieved remarkable performance in several computer vision problems. A notably intuitive technique called Curriculum Learning (CL) has been introduced recently for training deep learning models. Surprisingly, curriculum learning achieves significantly improved results in some tasks but marginal or no improvement in others. Hence, there is still a debate about its adoption as a standard method to train supervised learning models. In this work, we investigate the impact of curriculum learning in crowd counting using the density estimation method. We performed detailed investigations by conducting 112 experiments using six different CL settings using eight different crowd models. Our experiments show that curriculum learning improves the model learning performance and shortens the convergence time.

Density estimation is one of the most widely used method for crowd counting in which a deep learning model learns from head annotated crowd images to estimate crowd density in unseen images. Typically, the learning performance of the model is highly impacted by the accuracy of the annotations and inaccurate annotations may lead to localization and counting errors during prediction. A significant amount of works exist on crowd counting using perfectly labelled datasets but none of these explore the impact of annotation errors on the model accuracy. In this paper, we investigate the impact of imperfect labels (both noisy and missing labels) on crowd counting accuracy. We propose a system that automatically generate imperfect labels using a deep learning model (called annotator) which are then used to train a new crowd counting model (target model). Our analysis on two crowd counting models and two benchmark datasets shows that the proposed scheme achieves accuracy closer to that of the model trained with perfect labels showing robustness of crowd models to annotation errors.

The rapid outbreak of COVID-19 pandemic invoked scientists and researchers to prepare the world for future disasters. During the pandemic, global authorities on healthcare urged the importance of disinfection of objects and surfaces. To implement efficient and safe disinfection services during the pandemic, robots have been utilized for indoor assets. In this paper, we envision the use of drones for disinfection of outdoor assets in hospitals and other facilities. Such heterogeneous assets may have different service demands (e.g., service time, quantity of the disinfectant material etc.), whereas drones have typically limited capacity (i.e., travel time, disinfectant carrying capacity). To serve all the facility assets in an efficient manner, the drone to assets allocation and drone travel routes must be optimized. In this paper, we formulate the capacitated vehicle routing problem (CVRP) to find optimal route for each drone such that the total service time is minimized, while simultaneously the drones meet the demands of each asset allocated to it. The problem is solved using mixed integer programming (MIP). As CVRP is an NP-hard problem, we propose a lightweight heuristic to achieve sub-optimal performance while reducing the time complexity in solving the problem involving a large number of assets.