RESUMEN

Autonomous driving navigation relies on diverse approaches, each with advantages and limitations depending on various factors. For HD maps, modular systems excel, while end-to-end methods dominate mapless scenarios. However, few leverage the strengths of both. This paper innovates by proposing a hybrid architecture that seamlessly integrates modular perception and control modules with data-driven path planning. This innovative design leverages the strengths of both approaches, enabling a clear understanding and debugging of individual components while simultaneously harnessing the learning power of end-to-end approaches. Our proposed architecture achieved first and second place in the 2023 CARLA Autonomous Driving Challenge's SENSORS and MAP tracks, respectively. These results demonstrate the architecture's effectiveness in both map-based and mapless navigation. We achieved a driving score of 41.56 and the highest route completion of 86.03 in the MAP track of the CARLA Challenge leaderboard 1, and driving scores of 35.36 and 1.23 in the CARLA Challenge SENSOR track with route completions of 85.01 and 9.55, for, respectively, leaderboard 1 and 2. The results of leaderboard 2 raised the hybrid architecture to the first position, winning the edition of the 2023 CARLA Autonomous Driving Competition.

RESUMEN

Hybrid volumetric medical image segmentation models, combining the advantages of local convolution and global attention, have recently received considerable attention. While mainly focusing on architectural modifications, most existing hybrid approaches still use conventional data-independent weight initialization schemes which restrict their performance due to ignoring the inherent volumetric nature of the medical data. To address this issue, we propose a learnable weight initialization approach that utilizes the available medical training data to effectively learn the contextual and structural cues via the proposed self-supervised objectives. Our approach is easy to integrate into any hybrid model and requires no external training data. Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach, leading to state-of-the-art segmentation performance. Our proposed data-dependent initialization approach performs favorably as compared to the Swin-UNETR model pretrained using large-scale datasets on multi-organ segmentation task. Our source code and models are available at: https://github.com/ShahinaKK/LWI-VMS.

Asunto(s)

RESUMEN

In the field of engineering systems-particularly in underground drilling and green stormwater management-real-time predictions are vital for enhancing operational performance, ensuring safety, and increasing efficiency. Addressing this niche, our study introduces a novel LSTM-transformer hybrid architecture, uniquely specialized for multi-task real-time predictions. Building on advancements in attention mechanisms and sequence modeling, our model integrates the core strengths of LSTM and Transformer architectures, offering a superior alternative to traditional predictive models. Further enriched with online learning, our architecture dynamically adapts to variable operational conditions and continuously incorporates new field data. Utilizing knowledge distillation techniques, we efficiently transfer insights from larger, pretrained networks, thereby achieving high predictive accuracy without sacrificing computational resources. Rigorous experiments on sector-specific engineering datasets validate the robustness and effectiveness of our approach. Notably, our model exhibits clear advantages over existing methods in terms of predictive accuracy, real-time adaptability, and computational efficiency. This work contributes a pioneering predictive framework for targeted engineering applications, offering actionable insights into.

RESUMEN

BACKGROUND: Identification of difficult laryngoscopy is a frequent demand in cervical spondylosis clinical surgery. This work aims to develop a hybrid architecture for identifying difficult laryngoscopy based on new indexes. METHODS: Initially, two new indexes for identifying difficult laryngoscopy are proposed, and their efficacy for predicting difficult laryngoscopy is compared to that of two conventional indexes. Second, a hybrid adaptive architecture with convolutional layers, spatial extraction, and a vision transformer is proposed for predicting difficult laryngoscopy. The proposed adaptive hybrid architecture is then optimized by determining the optimal location for extracting spatial information. RESULTS: The test accuracy of four indexes using simple model is 0.8320. The test accuracy of optimized hybrid architecture using four indexes is 0.8482. CONCLUSION: The newly proposed two indexes, the angle between the lower margins of the second and sixth cervical spines and the vertical direction, are validated to be effective for recognizing difficult laryngoscopy. In addition, the optimized hybrid architecture employing four indexes demonstrates improved efficacy in detecting difficult laryngoscopy. TRIAL REGISTRATION: Ethics permission for this research was obtained from the Medical Scientific Research Ethics Committee of Peking University Third Hospital (IRB00006761-2015021) on 30 March 2015. A well-informed agreement has been received from all participants. Patients were enrolled in this research at the Chinese Clinical Trial Registry ( http://www.chictr.org.cn , identifier: ChiCTR-ROC-16008598) on 6 June 2016.

Asunto(s)

RESUMEN

As the first point of contact for patients, General Practitioners (GPs) play a crucial role in the National Health Service (NHS). An accurate primary diagnosis from the GP can alleviate the burden on specialists and reduce the time needed to re-confirm the patient's condition, allowing for more efficient further examinations. However, GPs have broad but less specialized knowledge, which limits the accuracy of their diagnosis. Therefore, it is imperative to introduce an intelligent system to assist GPs in making decisions. This paper introduces two data augmentation methods, the Complaint Symptoms Integration Method and Symptom Dot Separating Method, to integrate essential information into the Integration dataset. Additionally, it proposes a hybrid architecture that fuses the features of words from different representation spaces. Experiments demonstrate that, compared to commonly used pre-trained attention-based models, our hybrid architecture delivers the best classification performance for four common neurological diseases on the enhanced Integration dataset. For example, the classification accuracy of the BERT+CNN hybrid architecture is 0.897, which is a 5.1% improvement over both BERT and CNN with 0.846. Finally, this paper develops an AI diagnosis assistant web application that leverages the superior performance of this architecture to help GPs complete primary diagnosis efficiently and accurately.

Asunto(s)

RESUMEN

Plants are widely grown around the world and have high economic benefits. plant leaf diseases not only negatively affect the healthy growth and development of plants, but also have a negative impact on the environment. While traditional manual methods of identifying plant pests and diseases are costly, inefficient and inaccurate, computer vision technologies can avoid these drawbacks and also achieve shorter control times and associated cost reductions. The focusing mechanism of Transformer-based models(such as Visual Transformer) improves image interpretability and enhances the achievements of convolutional neural network (CNN) in image recognition, but Visual Transformer(ViT) performs poorly on small and medium-sized datasets. Therefore, in this paper, we propose a new hybrid architecture named FOTCA, which uses Transformer architecture based on adaptive Fourier Neural Operators(AFNO) to extract the global features in advance, and further down sampling by convolutional kernel to extract local features in a hybrid manner. To avoid the poor performance of Transformer-based architecture on small datasets, we adopt the idea of migration learning to make the model have good scientific generalization on OOD (Out-of-Distribution) samples to improve the model's overall understanding of images. In further experiments, Focal loss and hybrid architecture can greatly improve the convergence speed and recognition accuracy of the model in ablation experiments compared with traditional models. The model proposed in this paper has the best performance with an average recognition accuracy of 99.8% and an F1-score of 0.9931. It is sufficient for deployment in plant leaf disease image recognition.

RESUMEN

Blurring is one of the main degradation factors in image degradation, so image deblurring is of great interest as a fundamental problem in low-level computer vision. Because of the limited receptive field, traditional CNNs lack global fuzzy region modeling, and do not make full use of rich context information between features. Recently, a transformer-based neural network structure has performed well in natural language tasks, inspiring rapid development in the field of defuzzification. Therefore, in this paper, a hybrid architecture based on CNN and transformers is used for image deblurring. Specifically, we first extract the shallow features of the blurred images using a cross-layer feature fusion block that emphasizes the contextual information of each feature extraction layer. Secondly, an efficient transformer module for extracting deep features is designed, which fully aggregates feature information at medium and long distances using vertical and horizontal intra- and inter-strip attention layers, and a dual gating mechanism is used as a feedforward neural network, which effectively reduces redundant features. Finally, the cross-layer feature fusion block is used to complement the feature information to obtain the deblurred image. Extensive experimental results on publicly available benchmark datasets GoPro, HIDE, and the real dataset RealBlur show that the proposed method outperforms the current mainstream deblurring algorithms and recovers the edge contours and texture details of the images more clearly.

RESUMEN

Objective.Learning-based histopathology image (HI) classification methods serve as important tools for auxiliary diagnosis in the prognosis stage. However, most existing methods are focus on a single target cancer due to inter-domain differences among different cancer types, limiting their applicability to different cancer types. To overcome these limitations, this paper presents a high-performance HI classification method that aims to address inter-domain differences and provide an improved solution for reliable and practical HI classification.Approach.Firstly, we collect a high-quality hepatocellular carcinoma (HCC) dataset with enough data to verify the stability and practicability of the method. Secondly, a novel dual-branch hybrid encoding embedded network is proposed, which integrates the feature extraction capabilities of convolutional neural network and Transformer. This well-designed structure enables the network to extract diverse features while minimizing redundancy from a single complex network. Lastly, we develop a salient area constraint loss function tailored to the unique characteristics of HIs to address inter-domain differences and enhance the robustness and universality of the methods.Main results.Extensive experiments have conducted on the proposed HCC dataset and two other publicly available datasets. The proposed method demonstrates outstanding performance with an impressive accuracy of 99.09% on the HCC dataset and achieves state-of-the-art results on the other two public datasets. These remarkable outcomes underscore the superior performance and versatility of our approach in multiple HI classification.Significance.The advancements presented in this study contribute to the field of HI analysis by providing a reliable and practical solution for multiple cancer classification, potentially improving diagnostic accuracy and patient outcomes. Our code is available athttps://github.com/lms-design/DHEE-net.

Asunto(s)

RESUMEN

Evaluating the severity of ulcerative colitis (UC) through the Mayo endoscopic subscore (MES) is crucial for understanding patient conditions and providing effective treatment. However, UC lesions present different characteristics in endoscopic images, exacerbating interclass similarities and intraclass differences in MES classification. In addition, inexperience and review fatigue in endoscopists introduces nontrivial challenges to the reliability and repeatability of MES evaluations. In this paper, we propose a pyramid hybrid feature fusion framework (PHF3) as an auxiliary diagnostic tool for clinical UC severity classification. Specifically, the PHF3 model has a dual-branch hybrid architecture with ResNet50 and a pyramid vision Transformer (PvT), where the local features extracted by ResNet50 represent the relationship between the intestinal wall at the near-shot point and its depth, and the global representations modeled by the PvT capture similar information in the cross-section of the intestinal cavity. Furthermore, a feature fusion module (FFM) is designed to combine local features with global representations, while second-order pooling (SOP) is applied to enhance discriminative information in the classification process. The experimental results show that, compared with existing methods, the proposed PHF3 model has competitive performance. The area under the receiver operating characteristic curve (AUC) of MES 0, MES 1, MES 2, and MES 3 reached 0.996, 0.972, 0.967, and 0.990, respectively, and the overall accuracy reached 88.91%. Thus, our proposed method is valuable for developing an auxiliary assessment system for UC severity.

RESUMEN

A cognitive agent performing in the real world needs to learn relevant concepts about its environment (e.g., objects, color, and shapes) and react accordingly. In addition to learning the concepts, it needs to learn relations between the concepts, in particular spatial relations between objects. In this paper, we propose three approaches that allow a cognitive agent to learn spatial relations. First, using an embodied model, the agent learns to reach toward an object based on simple instructions involving left-right relations. Since the level of realism and its complexity does not permit large-scale and diverse experiences in this approach, we devise as a second approach a simple visual dataset for geometric feature learning and show that recent reasoning models can learn directional relations in different frames of reference. Yet, embodied and simple simulation approaches together still do not provide sufficient experiences. To close this gap, we thirdly propose utilizing knowledge bases for disembodied spatial relation reasoning. Since the three approaches (i.e., embodied learning, learning from simple visual data, and use of knowledge bases) are complementary, we conceptualize a cognitive architecture that combines these approaches in the context of spatial relation learning.

RESUMEN

In this work, we designed and successfully synthesized an interconnected carbon nanosheet/MoS2/polyaniline hybrid (ICN/MoS2/PANI) by combining the hydrothermal method and in situ chemical oxidative polymerization. The as-synthesized ICNs/MoS2/PANI hybrid showed a "caramel treat-like" architecture in which the sisal fiber derived ICNs were used as hosts to grow "follower-like" MoS2 nanostructures, and the PANI film was controllably grown on the surface of ICNs and MoS2. As a LIBs anode material, the ICN/MoS2/PANI electrode possesses excellent cycling performance, superior rate capability, and high reversible capacity. The reversible capacity retains 583 mA h/g after 400 cycles at a high current density of 2 A/g. The standout electrochemical performance of the ICN/MoS2/PANI electrode can be attributed to the synergistic effects of ICNs, MoS2 nanostructures, and PANI. The ICN framework can buffer the volume change of MoS2, facilitate electron transfer, and supply more lithium inset sites. The MoS2 nanostructures provide superior rate capability and reversible capacity, and the PANI coating can further buffer the volume change and facilitate electron transfer.

RESUMEN

Incidents of hydraulic or oil spills in the oceans/seas or ports occur with some regularity during the exploitation, production and transportation of petroleum products. Immediate, safe, effective and environmentally friendly measures must be adopted to reduce the impact of the oil spill on marine life. Due to the difficulty to detect and clean these areas, semi-autonomous vehicles can make a significant contribution by implementing a cooperative and coordinated response. The paper proposes a concept study of Hybrid Monitoring Detection and Cleaning System (HMDCS-UV) for a maritime region using semi-autonomous unmanned vehicles. This system is based on a cooperative decision architecture for an unmanned aerial vehicle to monitor and detect dirty zones (i.e., hydraulic spills), and clean them up using a swarm of unmanned surface vehicles. The proposed solutions were implemented in a real cloud and were evaluated using different simulation scenarios. Experimental results show that the proposed HMDCS-UV can detect and reduce the level of hydraulic pollution in maritime regions with a significant gain in terms of energy consumption.

RESUMEN

Numerical simulation of wildland fire spread is useful to predict the locations that are likely to burn and to support decision in an operational context, notably for crisis situations and long-term planning. For short-term, the computational time of traditional simulators is too high to be tractable over large zones like a country or part of a country, especially for fire danger mapping. This issue is tackled by emulating the area of the burned surface returned after simulation of a fire igniting anywhere in Corsica island and spreading freely during one hour, with a wide range of possible environmental input conditions. A deep neural network with a hybrid architecture is used to account for two types of inputs: the spatial fields describing the surrounding landscape and the remaining scalar inputs. After training on a large simulation dataset, the network shows a satisfactory approximation error on a complementary test dataset with a MAPE of 32.8%. The convolutional part is pre-computed and the emulator is defined as the remaining part of the network, saving significant computational time. On a 32-core machine, the emulator has a speed-up factor of several thousands compared to the simulator and the overall relationship between its inputs and output is consistent with the expected physical behavior of fire spread. This reduction in computational time allows the computation of one-hour burned area map for the whole island of Corsica in less than a minute, opening new application in short-term fire danger mapping.

Asunto(s)

RESUMEN

Coronavirus disease 2019 (COVID-2019), which emerged in Wuhan, China in 2019 and has spread rapidly all over the world since the beginning of 2020, has infected millions of people and caused many deaths. For this pandemic, which is still in effect, mobilization has started all over the world, and various restrictions and precautions have been taken to prevent the spread of this disease. In addition, infected people must be identified in order to control the infection. However, due to the inadequate number of Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests, Chest computed tomography (CT) becomes a popular tool to assist the diagnosis of COVID-19. In this study, two deep learning architectures have been proposed that automatically detect positive COVID-19 cases using Chest CT X-ray images. Lung segmentation (preprocessing) in CT images, which are given as input to these proposed architectures, is performed automatically with Artificial Neural Networks (ANN). Since both architectures contain AlexNet architecture, the recommended method is a transfer learning application. However, the second proposed architecture is a hybrid structure as it contains a Bidirectional Long Short-Term Memories (BiLSTM) layer, which also takes into account the temporal properties. While the COVID-19 classification accuracy of the first architecture is 98.14%, this value is 98.70% in the second hybrid architecture. The results prove that the proposed architecture shows outstanding success in infection detection and, therefore this study contributes to previous studies in terms of both deep architectural design and high classification success.

RESUMEN

Carbonaceous materials, especially with graphite-layers structure, as anode for potassium-ion batteries (PIBs), are the footstone for industrialization of PIBs. However, carbonaceous materials with graphite-layers structure usually suffer from poor cycle life and inferior stability, not to mention freestanding and flexible PIBs. Here, a freestanding and flexible 3D hybrid architecture by introducing carbon dots on the reduced graphene oxide surface (CDs@rGO) is synthesized as high performance PIBs anode. The CDs@rGO paper has efficient electron and ion transfer channels due to its unique structure, thus enhancing reaction kinetics. In addition, the CDs provide abundant defects and oxygen-containing functional groups, which can improve the electrochemical performance. This freestanding and flexible anode exhibits the high capacity of 310 mAh g-1 at 100 mA g-1, ultra-long cycle life (840 cycles with a capacity of 244 mAh g-1 at 200 mA g-1), and excellent rate performance (undergo six consecutive currents changing from 100 to 500 mA g-1, high capacity 185 mAh g-1 at 500 mA g-1), outperforming many existing carbonaceous PIB anodes. The results may provide a starting point for high-performance freestanding and flexible PIBs and promote the rapid development of next-generation flexible batteries.

RESUMEN

The stacking of complementary two-dimensional (2D) materials into hybrid architectures is desirable for batteries with enhanced capacity, fast charging, and long lifetime. However, the 2D heterostructures for energy storage are still underdeveloped, and some associated problems like low Coulombic efficiencies need to be tackled. Herein, we reported a phosphorene/MXene hybrid anode with an in situ formed fluorinated interphase for stable and fast sodium storage. The combination of phosphorene nanosheets with Ti3C2Tx MXene not only facilitates the migration of both electrons and sodium cations but also alleviates structural expansion of phosphorene and thereby improves the cycling performance of the hybrid anode. X-ray photoelectron spectroscopy in-depth analysis reveals that the fluorine terminated MXene stabilize the solid electrolyte interphase by forming fluorine-rich compounds on the anode surface. Density functional theory calculations confirm that the sodium affinities and diffusion kinetics are significantly enhanced in the phosphorene/MXene heterostructure, particularly in the phosphorene/Ti3C2F2. As a result, the hybrid electrode achieved a high reversible capacity of 535 mAh g-1 at 0.1 A g-1 and superior cycling performance (343 mAh g-1 after 1000 cycles at 1 A g-1 with a capacity retention of 87%) in a fluorine-free carbonate electrolyte.

RESUMEN

Semantic segmentation and depth estimation are two important tasks in computer vision, and many methods have been developed to tackle them. Commonly these two tasks are addressed independently, but recently the idea of merging these two problems into a sole framework has been studied under the assumption that integrating two highly correlated tasks may benefit each other to improve the estimation accuracy. In this paper, depth estimation and semantic segmentation are jointly addressed using a single RGB input image under a unified convolutional neural network. We analyze two different architectures to evaluate which features are more relevant when shared by the two tasks and which features should be kept separated to achieve a mutual improvement. Likewise, our approaches are evaluated under two different scenarios designed to review our results versus single-task and multi-task methods. Qualitative and quantitative experiments demonstrate that the performance of our methodology outperforms the state of the art on single-task approaches, while obtaining competitive results compared with other multi-task methods.

RESUMEN

Augmented reality (AR) is becoming increasingly popular due to its numerous applications. This is especially evident in games, medicine, education, and other areas that support our everyday activities. Moreover, this kind of computer system not only improves our vision and our perception of the world that surrounds us, but also adds additional elements, modifies existing ones, and gives additional guidance. In this article, we focus on interpreting a reality-based real-time environment evaluation for informing the user about impending obstacles. The proposed solution is based on a hybrid architecture that is capable of estimating as much incoming information as possible. The proposed solution has been tested and discussed with respect to the advantages and disadvantages of different possibilities using this type of vision.

Asunto(s)

RESUMEN

h-BN, as an isoelectronic analogue of graphene, has improved thermal mechanical properties. Moreover, the liquid-phase production of h-BN is greener since harmful oxidants/reductants are unnecessary. Here we report a novel hybrid architecture by employing h-BN nanosheets as 2D substrates to load 0D Fe3O4 nanoparticles, followed by phenol/formol carbonization to form a carbon coating. The resulting carbon-encapsulated h-BN@Fe3O4 hybrid architecture exhibits synergistic interactions: 1) The h-BN nanosheets act as flexible 2D substrates to accommodate the volume change of the Fe3O4 nanoparticles; 2) The Fe3O4 nanoparticles serve as active materials to contribute to a high specific capacity; and 3) The carbon coating not only protects the hybrid architecture from deformation but also keeps the whole electrode highly conductive. The synergistic interactions translate into significantly enhanced electrochemical performances, laying a basis for the development of superior hybrid anode materials.