International Journal of Intelligent Systems最新文献

We present a novel vector quantization (VQ) module for the two state-of-the-art long-range simultaneous localization and mapping (SLAM) algorithms. The VQ task in SLAM is generally performed using unsupervised methods. We provide an alternative approach trough embedding a semisupervised hyperbolic graph convolutional neural network (HGCN) in the VQ step of the SLAM processes. The SLAM platforms we have utilized for this purpose are fast appearance-based mapping (FABMAP) and oriented fast and rotated short (ORB), both of which rely on extracting the features of the captured images in their loop closure detection (LCD) module. For the first time, we have considered the space formed by these SURF features, robust image descriptors, as a graph, enabling us to apply an HGCN in the VQ section which results in an improved LCD performance. The HGCN vector quantizes the SURF feature space, leading to a bag-of-word (BoW) representation construction of the images. This representation is subsequently used to determine LCD accuracy and recall. Our approaches in this study are referred to as HGCN-FABMAP and HGCN-ORB. The main advantage of using HGCN in the LCD section is that it scales linearly when the features are accumulated. The benchmarking experiments show the superiority of our methods in terms of both trajectory generation accuracy in small-scale paths and LCD accuracy and recall for large-scale problems.

GNSS (global navigation satellite systems) technology enables high-precision single-point positioning (SPP) in open environments. However, the accuracy of GNSS positioning is significantly compromised in complex urban canyons due to signal obstructions and non-line-of-sight propagation errors. To address this challenge, we propose a GNSS displacement estimation algorithm. This method learns nonlinear dependencies between GNSS raw measurements and corresponding position changes, capturing dynamic and layered features in GNSS measurement data for displacement estimation. We introduce a denoising auto-encoder (DAE) to preprocess raw GNSS observations, reducing the impact of noise. The model simultaneously outputs estimated displacement and model confidence. The fusion process dynamically combines positioning results from the SPP algorithm and the D-Tran model, adaptively blending them to achieve accurate and optimal positioning estimation. This approach optimizes the accuracy of estimated positioning results while maintaining confidence in the estimation. Experimental results show a 61% reduction in root mean square error (RMSE) and 100% availability in urban canyon environments compared to traditional single-point positioning techniques.

Flood disasters occur worldwide, and flood risk prediction is conducive to protecting human life and property safety. Influenced by topographic changes and rainfall, the water level fluctuates randomly and violently during the flood, introducing many noises and directly increasing the difficulty of flood prediction. A data-driven flood forecasting method is proposed based on data preprocessing and a two-layer BiLSTM-Attention network to improve forecast accuracy. First, the Variational Mode Decomposition (VMD) is used to decompose the data for reducing noise and produce suitable Intrinsic Mode Functions (IMFs); Then, an optimized two-layer attention-based Bidirectional Long Sshort-Term memory (BiLSTM-Attention) network is constructed to predict each IMF. Finally, two optimization algorithms are used to obtain the optimized parameters of VMD and BiLSTM intelligently, increasing the self-adaptability. The inertia factor of particle swarm optimization is improved and then used to optimize the five hyperparameters of BiLSTM. The proposed model reduces storage errors for smaller training sets and can achieve good performance. Three water level data sets from the Yangtze River in China are used for comparative experiments. Numerical results show that the peak height absolute error is within 2 cm, and the relative error of peak time arrival is within 30%. Compared with LSTM, BiLSTM, CNN-BiLSTM-attention, etc., the proposed model reduces the root mean square error by at least 50% and has advantages for high-risk forecasting when the water level exceeds the defense line and fluctuates prominently.

Despite the rapid growth of machine learning (ML) and its far-reaching applications in various fields such as healthcare, finance, and urban heat management, there are still some unresolved challenges in the field of climate change. Reliable subseasonal forecasts of summer temperatures would be a great benefit to society. Although numerical weather prediction (NWP) models are better at capturing relevant sources of predictability, such as temperatures, land, and sea surface conditions, the subseasonal potential is not fully exploited. One such challenge is accurate subseasonal temperature forecasting using cutting-edge ML technology. This study aims to assess and predict the changes in subseasonal temperature during the summer season (from March to June) in Senegal on 2-weeks time scales. Six ML techniques, including linear regression (LR), decision tree (DT), support vector machine (SVM), artificial neural network (ANN), long short-term memory (LSTM), and gated recurrent units (GRU), are used. The experiments utilize a multivariate approach by incorporating variables of the ERA-5 dataset from 1981 to 2022. The results compared all the performances of the methods to assess their overall effectiveness in forecasting air temperature (t2m) values over 2 weeks. Our analysis demonstrates that the GRU model outperforms the other ML models, achieving a Nash–Sutcliffe efficiency (NSE) score of 74.68% and a mean absolute percentage error (MAPE) of 2.51%. The GRU model effectively captures long-term dependencies and exhibits superior performance in temperature forecasting. Furthermore, a comparison between the observed and predicted values confirms the accuracy of the GRU model in aligning with actual temperature trends. Overall, this study contributes an impactful deep learning model to the field of subseasonal temperature forecasting in West Africa (Senegal), which offers local authorities the capability to anticipate climatic events and enact preventive measures accordingly.

In the present study, the effects of the wing fence on the wing tip vortices and control surfaces located at the tip of the wing in a flying wing aircraft have been investigated using a numerical method. For the size of the fences, the average dimensions extracted from the wing tip vortices at different angles of attack are used. The basic determining parameter is the rolling torque coefficient, which is tried to be shown by employing a parametric study of the flow behavior in different situations of fence placement. These effects on the rolling torque of the aircraft are measured due to the presence of the split drag rudder control system. In this study, the fences were installed at three different heights and three different positions along the length of the wing, which were investigated at angles of attack of 7 to 16 degrees. The next stage of the research is to design the dimensions of the fence using the single-objective optimization method (a method to find the best solution for a problem with a specific goal). The designing of the fences at three points based on the dimensions of the wing tip vortex is carried out with the computational fluid dynamics (CFD) method (CFD is a computational method that uses physical laws to predict the behavior of fluids.). The aim of this research is to achieve the best design that converges to an optimal solution with minimum time and cost (CFD solution is long). However, CFD analysis requires a lot of computational time. To address this challenge, we employed a hybrid learning model comprising the radial basis function (RBF), a type of artificial neural network, and Kriging, a Gaussian process-based interpolation technique. The dataset for training the hybrid model was obtained from numerical solutions of CFD simulations involving a fence placed at various locations on the wing. Additionally, a genetic algorithm was employed as the optimization method in all instances where it was required. Using the power of machine learning techniques helped us identify the optimal placement of the fence to prevent it from being engulfed by the vortex and to optimize the utilization of the split drag system, yielding significant improvements.

The potential of technology to revolutionize healthcare is exemplified by the synergy between artificial intelligence (AI) and early detection of cardiomegaly, demonstrating the power of proactive intervention in cardiovascular health. This paper presents an innovative approach that leverages advanced AI algorithms, specifically deep learning (DL) technology, for the early detection of cardiomegaly. The methodology consists of five key steps, including data collection, image preprocessing, data augmentation, feature extraction, and classification. Utilizing chest X-ray (CXR) images from the National Institutes of Health (NIH), the study applies rigorous image preprocessing operations, including color transformation and normalization. To enhance model generalization, data augmentation is employed, paving the way for two distinct DL models, a convolutional neural network (CNN) developed from scratch and a pretrained residual network with 50 layers (ResNet50), and adapted to the problem domain. Both models are systematically evaluated with five optimizers, revealing the AdaMax optimizer’s superiority for the CNN model and AdaGrad’s efficacy for the modified ResNet50. The proposed CNN with AdaMax achieves an impressive 99.91% accuracy, outperforming recent techniques in precision, recall, and F1 − score. This research underscores the transformative potential of AI in cardiovascular health diagnostics, emphasizing the significance of timely intervention.

Facing the implementation problems such like low growth reward, long training time, and poor stability of the multiagent learning methods when dealing with complex environment and more agents, this paper proposes a fast optimal coordination method for multiagent in complex environment (FOC-MACE). Firstly, the environment exploration strategy is introduced into the policy network based on the MADDPG method for higher growth rewards. Then, the parallel computing technology is adopted in the critic network, in purpose to effectively reduce the training time. These tactics together are beneficial to enhance the stability of multiagent learning. Lastly, the optimal resource allocation is carried out to realize optimal coevolution of the multiagents and further improve the learning ability of the agents’ group. To verify the effectiveness of our proposal, the FOC-MACE is compared with several advanced methods at current stage in the MPE environment. Three different experiments prove that by using our method, the growth reward is increased by up to 37.1%, the training is speed up significantly, and the stability of the method, which represented by standardized variance, is also improved. In addition, this paper validated the fast optimal coordination method for multiagent systems in the context of UAV scenarios, demonstrating the practical performance of the approach. Through comprehensive experiments and scenario validations, the study successfully confirmed the effectiveness of the proposed fast optimal coordination method for multiagent systems in complex environments.

Breast cancer characterization remains a significant and challenging issue in contemporary medicine. Accurately distinguishing between malignant and benign breast lesions is crucial for effective diagnosis and treatment. The anatomical structure of malignant breast ultrasound images is more chaotic than that of benign images due to disease pathologies. However, texture-based analysis alone often fails to identify the extent of chaoticness in malignant breast ultrasound images due to their vague appearance with normal echo patterns, leading to missed diagnoses and increased mortality rates. To address this issue, we proposed an angular feature-based multilevel breast cancer classification framework $$ that aims to improve the accuracy and efficiency of classification. The proposed framework mimics the radiologist interpretation procedure by identifying the chaoticness on the periphery of the breast lesion in a breast ultrasound image (level-1). If the lesion contains an acute angle in any part of the periphery, it can be characterized as malignant or otherwise benign. However, solely relying on level-1 analysis may result in misclassification, especially when benign lesions exhibit echo patterns that resemble malignant ones. To overcome this limitation and to make the proposed system highly sensitive, advanced texture-based analysis (using combined shape, texture, and angular features) is performed (level-2). Finally, the performance of the proposed system is evaluated using a cross-dataset (consisting of 1293 breast ultrasound images) and compared with the different individual feature extraction techniques. Encouragingly, our system demonstrated an accuracy of 96.99% for classifying malignant and benign tumors, which is also validated using statistical analysis. The implications of our research lie in its potential to significantly improve breast cancer diagnosis by providing a reliable, efficient, and sensitive tool for radiologists.

In recent years, remarkable performance improvements have been produced by deep convolutional neural networks (CNN) for single image super-resolution (SISR). Nevertheless, a high proportion of CNN-based SISR models are with quite a few network parameters and high computational complexity for deep or wide architectures. How to more fully utilize deep features to make a balance between model complexity and reconstruction performance is one of the main challenges in this field. To address this problem, on the basis of the well-known information multi-distillation model, a multi-attention feature distillation network termed as MAFDN is developed for lightweight and accurate SISR. Specifically, an effective multi-attention feature distillation block (MAFDB) is designed and used as the basic feature extraction unit in MAFDN. With the help of multi-attention layers including pixel attention, spatial attention, and channel attention, MAFDB uses multiple information distillation branches to learn more discriminative and representative features. Furthermore, MAFDB introduces the depthwise over-parameterized convolutional layer (DO-Conv)-based residual block (OPCRB) to enhance its ability without incurring any parameter and computation increase in the inference stage. The results on commonly used datasets demonstrate that our MAFDN outperforms existing representative lightweight SISR models when taking both reconstruction performance and model complexity into consideration. For example, for ×4 SR on Set5, MAFDN (597K/33.79G) obtains 0.21 dB/0.0037 and 0.10 dB/0.0015 PSNR/SSIM gains over the attention-based SR model AFAN (692K/50.90G) and the feature distillation-based SR model DDistill-SR (675K/32.83G), respectively.