Search

Operating electronic systems in space environments presents significant challenges due to continuous exposure to cosmic, solar, and trapped radiation, which can induce catastrophic single-event effects. This paper introduces a novel nonintrusive mitigation apparatus designed to protect high-end commercial off-the-shelf electronics in space. The apparatus incorporates an array of real-time particle detectors coupled with a mitigation algorithm. Upon identifying potentially harmful particles, the system power cycles affected electronics, preempting permanent damage. The apparatus was evaluated using GEANT4 simulations, which were compared with empirical data from the "COTS-Capsule" experiment aboard the International Space Station, demonstrating strong agreement. Key results indicate that the system achieves a 95% detection accuracy with a power cycle rate of once every seven hours per square centimeter of sensitive electronics. The COTS-Capsule represents a cost-effective, flexible solution for integrating modern, high-end, non-space-qualified electronics into a variety of space missions, addressing critical challenges in the new-space era.

We introduce XTRA, a vision model pre-trained with a novel auto-regressive objective that significantly enhances both sample and parameter efficiency compared to previous auto-regressive image models. Unlike contrastive or masked image modeling methods, which have not been demonstrated as having consistent scaling behavior on unbalanced internet data, auto-regressive vision models exhibit scalable and promising performance as model and dataset size increase. In contrast to standard auto-regressive models, XTRA employs a Block Causal Mask, where each Block represents k $\times$ k tokens rather than relying on a standard causal mask. By reconstructing pixel values block by block, XTRA captures higher-level structural patterns over larger image regions. Predicting on blocks allows the model to learn relationships across broader areas of pixels, enabling more abstract and semantically meaningful representations than traditional next-token prediction. This simple modification yields two key results. First, XTRA is sample-efficient. Despite being trained on 152$\times$ fewer samples (13.1M vs. 2B), XTRA ViT-H/14 surpasses the top-1 average accuracy of the previous state-of-the-art auto-regressive model across 15 diverse image recognition benchmarks. Second, XTRA is parameter-efficient. Compared to auto-regressive models trained on ImageNet-1k, XTRA ViT-B/16 outperforms in linear and attentive probing tasks, using 7-16$\times$ fewer parameters (85M vs. 1.36B/0.63B)., Comment: for code, see https://github.com/elad-amrani/xtra

Wildfires pose significant threats to ecosystems, economies, and communities worldwide, necessitating advanced predictive methods for effective mitigation. This study introduces a novel and comprehensive dataset specifically designed for wildfire prediction in Morocco, addressing its unique geographical and climatic challenges. By integrating satellite observations and ground station data, we compile essential environmental indicators such as vegetation health (NDVI), population density, soil moisture levels, and meteorological data aimed at predicting next-day wildfire occurrences with high accuracy. Our methodology incorporates state-of-the-art machine learning and deep learning algorithms, demonstrating superior performance in capturing wildfire dynamics compared to traditional models. Preliminary results show that models using this dataset achieve an accuracy of up to 90%, significantly improving prediction capabilities. The public availability of this dataset fosters scientific collaboration, aiming to refine predictive models and develop innovative wildfire management strategies. Our work not only advances the technical field of dataset creation but also emphasizes the necessity for localized research in underrepresented regions, providing a scalable model for other areas facing similar environmental challenges.

Traditional Feed-Forward Neural Networks (FFNN) and one-dimensional Convolutional Neural Networks (1D CNN) often encounter difficulties when dealing with long, columnar datasets that contain numerous features. The challenge arises from two primary factors: the large volume of data and the potential absence of meaningful relationships between features. In conventional training, large datasets can overwhelm the model, causing significant portions of the input to remain underutilized. As a result, the model may fail to capture the critical information necessary for effective learning, which leads to diminished performance. To overcome these limitations, we introduce a novel architecture called Parallel Multi-path Feed Forward Neural Networks (PMFFNN). Our approach leverages multiple parallel pathways to process distinct subsets of columns from the input dataset. By doing so, the architecture ensures that each subset of features receives focused attention, which is often neglected in traditional models. This approach maximizes the utilization of feature diversity, ensuring that no critical data sections are overlooked during training. Our architecture offers two key advantages. First, it allows for more effective handling of long, columnar data by distributing the learning task across parallel paths. Second, it reduces the complexity of the model by narrowing the feature scope in each path, which leads to faster training times and improved resource efficiency. The empirical results indicate that PMFFNN outperforms traditional FFNNs and 1D CNNs, providing an optimized solution for managing large-scale data.

Finding correspondences between 3D shapes is an important and long-standing problem in computer vision, graphics and beyond. While approaches based on machine learning dominate modern 3D shape matching, almost all existing (learning-based) methods require that at least one of the involved shapes is complete. In contrast, the most challenging and arguably most practically relevant setting of matching partially observed shapes, is currently underexplored. One important factor is that existing datasets contain only a small number of shapes (typically below 100), which are unable to serve data-hungry machine learning approaches, particularly in the unsupervised regime. In addition, the type of partiality present in existing datasets is often artificial and far from realistic. To address these limitations and to encourage research on these relevant settings, we provide a generic and flexible framework for the procedural generation of challenging partial shape matching scenarios. Our framework allows for a virtually infinite generation of partial shape matching instances from a finite set of shapes with complete geometry. Further, we manually create cross-dataset correspondences between seven existing (complete geometry) shape matching datasets, leading to a total of 2543 shapes. Based on this, we propose several challenging partial benchmark settings, for which we evaluate respective state-of-the-art methods as baselines.

This paper presents a novel approach in wildfire prediction through the integration of multisource spatiotemporal data, including satellite data, and the application of deep learning techniques. Specifically, we utilize an ensemble model built on transfer learning algorithms to forecast wildfires. The key focus is on understanding the significance of weather sequences, human activities, and specific weather parameters in wildfire prediction. The study encounters challenges in acquiring real-time data for training the network, especially in Moroccan wildlands. The future work intends to develop a global model capable of processing multichannel, multidimensional, and unformatted data sources to enhance our understanding of the future entropy of surface tiles.

The COTS-Capsule Spaceborne hodoscope was launched into low earth orbit aboard the International Space Station and operated during 2021-2022. The primary objectives of the payload are: measuring and characterizing the radiation environment within the space station; serving as a technology demonstrator for the COTS-Capsule radiation mitigation apparatus; and testing the interaction of high-energy cosmic particles in space with our detectors. The payload features a particle hodoscope equipped with an array of novel detectors based on polyvinyl toluene scintillators and silicon photomultiplier sensors that are used for radiation detection and characterization. This paper provides a comprehensive account of the construction, preflight performance, testing, qualification, and in-orbit calibration of the COTS-Capsule payload. The hodoscope, sensitive to ionizing cosmic particles, facilitates impinging particle track reconstruction, energy deposition estimation, and linear energy transfer estimation. In specific instances, it also provides particle identification and energy deposition estimation., Comment: 11 pages, 6 figures

An innovative particle detector that offers a compelling combination of cost-effectiveness and high accuracy is introduced. The detector features plastic scintillators paired with a sparse arrangement of SiPMs, strategically positioned within a unique opto-mechanical framework. This configuration delivers precise measurements of spatial impact position and energy deposition of impinging particles. The manuscript describes the detector's physical model complemented by an analytical representation. These calculations underpin a numerical algorithm, facilitating the estimation of particle impingement position and energy deposition. The results of the numerical calculations are compared with the output of GEANT4 simulations and evaluated by rigorous laboratory testing. An array of these detectors, intended for deployment in a spaceborne experiment, underwent detailed design, manufacturing, and testing. Their performance and alignment with the physical model were validated through meticulously conducted ground-based laboratory experiments, conclusively affirming the detector's properties., Comment: 16 pages, 11 figures, 1 table

In recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains. This effort has attracted substantial interest from both industry and academy, highlighting its significance in the current technological landscape. Most datasets in this area are primarily focused on Key Information Extraction (KIE), where the extraction process revolves around extracting information using a specific, predefined set of keys. Unlike most existing datasets and benchmarks, our focus is on discovering key-value pairs (KVPs) without relying on predefined keys, navigating through an array of diverse templates and complex layouts. This task presents unique challenges, primarily due to the absence of comprehensive datasets and benchmarks tailored for non-predetermined KVP extraction. To address this gap, we introduce KVP10k , a new dataset and benchmark specifically designed for KVP extraction. The dataset contains 10707 richly annotated images. In our benchmark, we also introduce a new challenging task that combines elements of KIE as well as KVP in a single task. KVP10k sets itself apart with its extensive diversity in data and richly detailed annotations, paving the way for advancements in the field of information extraction from complex business documents., Comment: accepted ICDAR2024

Fault diagnosis in marine diesel engines is vital for maritime safety and operational efficiency.These engines are integral to marine vessels, and their reliable performance is crucial for safenavigation. Swift identification and resolution of faults are essential to prevent breakdowns,enhance safety, and reduce the risk of catastrophic failures at sea. Proactive fault diagnosisfacilitates timely maintenance, minimizes downtime, and ensures the overall reliability andlongevity of marine diesel engines. This paper explores the importance of fault diagnosis,emphasizing subsystems, common faults, and recent advancements in data-driven approachesfor effective marine diesel engine maintenance

Although 3D shape matching and interpolation are highly interrelated, they are often studied separately and applied sequentially to relate different 3D shapes, thus resulting in sub-optimal performance. In this work we present a unified framework to predict both point-wise correspondences and shape interpolation between 3D shapes. To this end, we combine the deep functional map framework with classical surface deformation models to map shapes in both spectral and spatial domains. On the one hand, by incorporating spatial maps, our method obtains more accurate and smooth point-wise correspondences compared to previous functional map methods for shape matching. On the other hand, by introducing spectral maps, our method gets rid of commonly used but computationally expensive geodesic distance constraints that are only valid for near-isometric shape deformations. Furthermore, we propose a novel test-time adaptation scheme to capture both pose-dominant and shape-dominant deformations. Using different challenging datasets, we demonstrate that our method outperforms previous state-of-the-art methods for both shape matching and interpolation, even compared to supervised approaches., Comment: accepted by CVPR2024

Air pollution is a major problem today that causes serious damage to human health. Urban areas are the most affected by the degradation of air quality caused by anthropogenic gas emissions. Although there are multiple proposals for air quality monitoring, in most cases, two limitations are imposed: the impossibility of processing data in Near Real-Time (NRT) for remote sensing approaches and the impossibility of reaching areas of limited accessibility or low network coverage for ground data approaches. We propose a software architecture that efficiently combines complex event processing with remote sensing data from various satellite sensors to monitor air quality in NRT, giving support to decision-makers. We illustrate the proposed solution by calculating the air quality levels for several areas of Morocco and Spain, extracting and processing satellite information in NRT. This study also validates the air quality measured by ground stations and satellite sensor data.

We report on high-temperature sensing measurements using a tubular-lattice hollow-core photonic crystal fiber displaying a microstructure formed of eight 2.4 um-thick cladding tubes. The larger thickness of our fiber's cladding tubes compared to other hollow fibers operating in the visible and infrared ranges entails multiple narrow transmission bands in its transmission spectrum (6 bands in the spectral range between 400 nm and 950 nm) and benefits the realization of the temperature sensing measurements. The principle of operation of our device is based on the thermo-optic effect and thermal expansion-induced spectral shifts of the fiber transmission bands due to temperature variations. To study the sensor operation, we monitored the fiber transmission bands' spectral positions from room temperature to 1085 oC in both ramp-up and ramp-down scenarios. Additionally, we investigated the optimization opportunities by assessing an analytical model describing the fiber transmission characteristics and discussed the alternatives for enhancing the sensor performance. Moreover, our fiber characterization experiments revealed a consistent confinement loss trend aligned with the scaling laws in tubular-lattice hollow-core fibers. We thus understand that the results presented in this manuscript highlight a relevant path for the development of temperature sensors based on microstructured hollow-core optical fibers endowed with thick cladding tubes.

Previous research has demonstrated the potential of using pre-trained language models for decoding open vocabulary Electroencephalography (EEG) signals captured through a non-invasive Brain-Computer Interface (BCI). However, the impact of embedding EEG signals in the context of language models and the effect of subjectivity, remain unexplored, leading to uncertainty about the best approach to enhance decoding performance. Additionally, current evaluation metrics used to assess decoding effectiveness are predominantly syntactic and do not provide insights into the comprehensibility of the decoded output for human understanding. We present an end-to-end deep learning framework for non-invasive brain recordings that brings modern representational learning approaches to neuroscience. Our proposal introduces the following innovations: 1) an end-to-end deep learning architecture for open vocabulary EEG decoding, incorporating a subject-dependent representation learning module for raw EEG encoding, a BART language model, and a GPT-4 sentence refinement module; 2) a more comprehensive sentence-level evaluation metric based on the BERTScore; 3) an ablation study that analyses the contributions of each module within our proposal, providing valuable insights for future research. We evaluate our approach on two publicly available datasets, ZuCo v1.0 and v2.0, comprising EEG recordings of 30 subjects engaged in natural reading tasks. Our model achieves a BLEU-1 score of 42.75%, a ROUGE-1-F of 33.28%, and a BERTScore-F of 53.86%, outperforming the previous state-of-the-art methods by 3.38%, 8.43%, and 6.31%, respectively., Comment: 12 pages, 5 figures, preprint

A shared secret key is necessary for encrypted communications. Since Wi-Fi relies on OFDM, we suggest a method to generate such a key by utilizing Wi-Fi's channel state information (CSI). CSI is typically reciprocal but very sensitive to location: While the legitimate Alice and Bob observe the same CSI, an eavesdropper Eve observes an uncorrelated CSI when positioned over 0.5 wavelength away. We show that if endpoint Bob is shaken, sufficient diversity is induced in the CSI so that it can serve as a source of true randomness. Then we show that the CSI among neighboring sub-carriers is correlated, so we select a small set of judiciously-spaced sub-carriers, and use a majority rule around each. We demonstrate that Alice and Bob observe a 5-15\% bit mismatch rate (BMR) in the extracted bitstream while Eve observes a BMR of around 50\% even when placed within 10cm of Alice. We employ the cryptography-oriented definition of min-entropy to estimate the number of secure bits within the bitstream, and use the Cascade algorithm of quantum-key-distribution to reconcile Alice and Bob's bitstreams, while quantifying the number of bits leaked by the algorithm. Accounting for both the min-entropy and the cascade leakage we quantify the Secured Bit Generation Rate of our method. We conducted extensive tests in an indoor environment. Our system exhibits a secure bit generation rate of 1.2--1.6 %secure bits per packet, at distances ranging from 0.5m--9m, and can generate a secure shared 128-bit key with 20sec of device shaking.