A regression model represents the relationship between explanatory and response variables. In real life, explanatory variables often affect a response variable with a certain time lag, rather than immediately. For exa...
详细信息
A regression model represents the relationship between explanatory and response variables. In real life, explanatory variables often affect a response variable with a certain time lag, rather than immediately. For example, the marriage rate affects the birth rate with a time lag of 1 to 2 years. Although deeplearning models have been successfully used to model various relationships, most of them do not consider the time lags between explanatory and response variables. Therefore, in this paper, we propose an extension of deeplearning models, which automatically finds the time lags between explanatory and response variables. The proposed method finds out which of the past values of the explanatory variables minimize the error of the model, and uses the found values to determine the time lag between each explanatory variable and response variables. After determining the time lags between explanatory and response variables, the proposed method trains the deeplearning model again by reflecting these time lags. Through various experiments applying the proposed method to a few deeplearning models, we confirm that the proposed method can find a more accurate model whose error is reduced by more than 60% compared to the original model.
Fuzzy image target classification detection plays an important role in imageprocessing. Traditional classification detection methods are easily affected by environmental and equipment factors, and there are certain l...
详细信息
Wood processing is one of the most widely used in agriculture and industry. Low precision and high time delay of machine learning in wood defect detection are currently the main factors restricting the production effi...
详细信息
Wood processing is one of the most widely used in agriculture and industry. Low precision and high time delay of machine learning in wood defect detection are currently the main factors restricting the production efficiency and product quality of the wood processing industry. An SPP-improved deeplearning method was proposed to detect wood defects based on the basic framework of the YOLO V3 network to improve accuracy and real-time performance. The extended dataset was firstly established by image data enhancement and preprocessing based on the limited samples of the wood defect dataset. Anchor box scale re-clustering of the wood defect dataset was carried out according to the defect features. The spatial pyramid pooling (SPP) network was applied to improve the feature pyramid (FP) network in YOLO V3. The validity and real-time performance of the proposed algorithm were verified by a randomly selected test set. The results show that the overall detection accuracy rate on the wood defect test dataset reaches 93.23% while the detection time for each image is within 13 ms.
Large-scale image indexing and retrieval are pivotal in artificial intelligence, especially within computer vision, for efficiently organizing and accessing extensive image databases. This systematic literature review...
详细信息
Large-scale image indexing and retrieval are pivotal in artificial intelligence, especially within computer vision, for efficiently organizing and accessing extensive image databases. This systematic literature review employs the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology to thoroughly analyze and synthesise the current research landscape in this domain. Through meticulous research and a stringent selection process, this study uncovers significant trends, pioneering methodologies, and ongoing challenges in large-scale image indexing and retrieval. Key findings reveal a growing adoption of deeplearning techniques, the integration of multimodal data to improve retrieval accuracy, and persistent challenges related to scalability and real-timeprocessing. These insights offer a valuable resource for researchers and practitioners striving to enhance the efficiency and effectiveness of image indexing and retrieval systems.
Optical speckle image reconstruction is crucial in fields such as biomedical imaging, optical coherence tomography, and optical remote sensing. However, speckle images often suffer from noise and scattering, leading t...
详细信息
This letter describes autonomous landing of an unmanned aircraft system on a moving platform using vision and deep reinforcement learning. Landing on the moving platform offers several benefits, such as more mission f...
详细信息
This letter describes autonomous landing of an unmanned aircraft system on a moving platform using vision and deep reinforcement learning. Landing on the moving platform offers several benefits, such as more mission flexibility and reduced flight time. In particular, the end-to-end vision approach (i.e., an input to the reinforcement learning is a raw image from the camera) with the deep regularized Q algorithm and custom designed reward is utilized. The custom reward was specifically devised to encourage useful feature extraction from the state space. Additionally, the proposed reinforcement learning algorithm has full 3D velocity control including the vertical channel. The simulation results show that the proposed approach can outperform existing approaches which use high-level extracted features (such as relative position and velocity of the landing pad). The simulation results are then successfully transferred to the real-world experiment by utilizing domain randomization.
Accurate forecasting of solar irradiance is a key tool for optimizing the efficiency and service quality of solar energy systems. In this paper, a novel approach is proposed for multi-step solar irradiation forecastin...
详细信息
Accurate forecasting of solar irradiance is a key tool for optimizing the efficiency and service quality of solar energy systems. In this paper, a novel approach is proposed for multi-step solar irradiation forecasting using deeplearning models optimized for low computational resource environments. Traditional forecasting models often lack accuracy, and modern, deep-learning based models, while accurate, require substantial computational resources, making them impractical for real-time or resource-constrained environments. Our method uniquely combines dimensionality reduction via imageprocessing with an LSTM-based architecture, achieving significant input data reduction by a factor of 4250 while preserving essential sky condition information, resulting in a lightweight neural network architecture that balances prediction accuracy with computational efficiency. The forecasts are generated simultaneously for multiple time steps: 1 minute, 5 minutes, 10 minutes and 20 minutes. Models are evaluated against a custom dataset, spanning across more than 3 years, containing 1 min samples encompassing both all-sky imagery and meteorological measurements. The approach is demonstrated to achieve better forecasting accuracy, namely a forecast skill of 10 % compared to persistence, and a significantly reduced computational overhead compared to benchmark ConvLSTM models. Moreover, utilizing the preprocessed image features reduces input size by a factor of 6 compared to the raw images. Our findings suggest that the proposed models are well-suited for deployment in embedded systems, remote sensors, and other scenarios where computational resources are limited.
In recent years, deeplearning has emerged as the dominant approach for hyperspectral image (HSI) classification. However, deep neural networks require large annotated datasets to generalize well. This limits the appl...
详细信息
In recent years, deeplearning has emerged as the dominant approach for hyperspectral image (HSI) classification. However, deep neural networks require large annotated datasets to generalize well. This limits the applicability of deeplearning for real-world HSI classification problems, as manual labeling of thousands of pixels per scene is costly and time consuming. In this article, we tackle the problem of few-shot HSI classification by leveraging state-of-the-art self-supervised contrastive learning with an improved view-generation approach. Traditionally, contrastive learning algorithms heavily rely on hand-crafted data augmentations tailored for natural imagery to generate positive pairs. However, these augmentations are not directly applicable to HSIs, limiting the potential of self-supervised learning in the hyperspectral domain. To overcome this limitation, we introduce two positive pair-mining strategies for contrastive learning on HSIs. The proposed strategies mitigate the need for high-quality data augmentations, providing an effective solution for few-shot HSI classification. Through extensive experiments, we show that the proposed approach improves accuracy and label efficiency on four popular HSI classification benchmarks. Furthermore, we conduct a thorough analysis of the impact of data augmentation in contrastive learning, highlighting the advantage of our positive pair-mining approach.
This comprehensive review examines the role of artificial intelligence (AI) in enhancing threat detection and cybersecurity, focusing on recent advancements and ongoing challenges in this dynamic field. The ability to...
详细信息
This comprehensive review examines the role of artificial intelligence (AI) in enhancing threat detection and cybersecurity, focusing on recent advancements and ongoing challenges in this dynamic field. The ability to identify and counteract cybersecurity threats including network breaches, adversarial assaults, and zero-day vulnerabilities has significantly increased with the inclusion of AI, especially machine learning and deeplearning techniques. The review underscores the critical role of explainability and resilience in AI models to ensure trustworthiness and reliability in AI-driven security solutions. The studies analyzed span a wide range of sectors, including Industry 5.0, the Internet of Things (IoT), 5G networks, and autonomous vehicles, illustrating AI's adaptability in tackling unique security issues across these domains. Cutting-edge approaches, such as transformer-based models, federated learning, and blockchain integration, are advancing the development of more robust and real-time threat detection systems. However, challenges persist, particularly in managing large-scale data, enabling real-timeprocessing, and ensuring privacy and security. The review concludes that although substantial progress has been achieved, ongoing research and collaboration are vital to fully harness AI's potential in securing digital landscapes.
Adjusting camera exposure in arbitrary lighting conditions is the first step to ensure the functionality of computer vision applications. Poorly adjusted camera exposure often leads to critical failure and performance...
详细信息
ISBN:
(纸本)9798350353013;9798350353006
Adjusting camera exposure in arbitrary lighting conditions is the first step to ensure the functionality of computer vision applications. Poorly adjusted camera exposure often leads to critical failure and performance degradation. Traditional camera exposure control methods require multiple convergence steps and time-consuming processes, making them unsuitable for dynamic lighting conditions. In this paper, we propose a new camera exposure control framework that rapidly controls camera exposure while performing real-timeprocessing by exploiting deep reinforcement learning. The proposed framework consists of four contributions: 1) a simplified training ground to simulate real-world's diverse and dynamic lighting changes, 2) flickering and image attribute-aware reward design, along with lightweight state design for real-timeprocessing, 3) a static-to-dynamic lighting curriculum to gradually improve the agent's exposure-adjusting capability, and 4) domain randomization techniques to alleviate the limitation of the training ground and achieve seamless generalization in the wild. As a result, our proposed method rapidly reaches a desired exposure level within five steps with real-timeprocessing (1ms). Also, the acquired images are well-exposed and show superiority in various computer vision tasks, such as feature extraction and object detection.
暂无评论