Search Results (17)

The global burden of diabetes mellitus (DM) continues to escalate, posing significant challenges to healthcare systems worldwide. This study compares machine learning (ML) and deep learning (DL) methods, their hybrids, and ensemble strategies for predicting the health outcomes of diabetic patients. This work aims to find the best solutions that strike a balance between computational efficiency and accurate prediction. The study systematically assessed a range of predictive models, including sophisticated DL techniques and conventional ML algorithms, based on computational efficiency and performance indicators. The study assessed prediction accuracy, processing speed, scalability, resource consumption, and interpretability using publicly accessible diabetes datasets. It methodically evaluates the selected models using key performance indicators (KPIs), training times, and memory usage. AdaBoost had the highest F1-score (0.74) on PIMA-768, while RF excelled on PIMA-2000 (~0.73). An RNN led the 3-class BRFSS survey (0.44), and a feed-forward DNN excelled on the binary BRFSS subset (0.45), while RF also achieved perfect accuracy on the EMR dataset (1.00) confirming that model performance is tightly coupled to each dataset’s scale, feature mix and label structure. The results highlight how lightweight, interpretable ML and DL models work in resource-constrained environments and for real-time health analytics. The study also compares its results with existing prediction models, confirming the benefits of selected ML approaches in enhancing diabetes-related medical outcomes that are substantial for practical implementation, providing a reliable and efficient framework for automated diabetes prediction to support initiative-taking disease management techniques and tailored treatment. The study concludes the essentiality of conducting a thorough assessment and validation of the model using current institutional datasets as this enhances accuracy, security, and confidence in AI-assisted healthcare decision-making. Full article

With the development of UAV technology, the composition of UAVs has become increasingly complex, interconnected, and tightly coupled. Fault features are characterized by weakness, nonlinearity, coupling, and uncertainty. A promising approach is the use of deep learning methods, which can effectively extract useful diagnostic information from weak, coupled, nonlinear data from inputs with background noise. However, due to the diversity of flight environments and missions, the distribution of the obtained sample data varies. The types of fault data and corresponding labels under different conditions are unknown, and it is time-consuming and expensive to label sample data. These challenges reduce the performance of traditional deep learning models in anomaly detection. To overcome these challenges, a novel weighted-transfer domain-adaptation network (WTDAN) method is introduced to realize the online anomaly detection and fault diagnosis of UAV electromagnetic-sensitive flight data. The method is based on unsupervised transfer learning, which can transfer the knowledge learnt from existing datasets to solve problems in the target domain. The method contains three novel multiscale modules: a feature extractor, used to extract multidimensional features from the input; a domain discriminator, used to improve the imbalance of the data distribution between the source domain and the target domain; and a label classifier, used to classify data categories for the target domain. Multilayer domain adaptation is used to reduce the distance between the source domain datasets and the target domain datasets distributions. The WTDAN assigns different weights to the source domain samples in order to weight the different contributions of source samples to solve the problem during the training process. The dataset adopts not only open datasets from the website but also test datasets from experiments to evaluate the transferability of the proposed WTDAN model. The experimental results show that, under the condition of fewer anomalous target data samples, the proposed method had a classification accuracy of up to 90%, which is higher than that of the other compared methods, and performed with superior transferability on the cross-domain datasets. The capability of fault diagnosis can provide a novel method for online anomaly detection and the prognostics and health management (PHM) of UAVs, which, in turn, would improve the reliability, repairability, and safety of UAV systems. Full article

Accurate, continuous, and reliable positioning is critical to achieving autonomous driving. However, in complex urban canyon environments, the vulnerability of stand-alone sensors and non-line-of-sight (NLOS) caused by high buildings, trees, and elevated structures seriously affect positioning results. To address these challenges, a sky-view image segmentation algorithm based on a fully convolutional network (FCN) is proposed for NLOS detection in global navigation satellite systems (GNSSs). Building upon this, a novel NLOS detection and mitigation algorithm (named S−NDM) uses a tightly coupled GNSS, inertial measurement units (IMUs), and a visual feature system called Sky−GVIO with the aim of achieving continuous and accurate positioning in urban canyon environments. Furthermore, the system combines single-point positioning (SPP) with real-time kinematic (RTK) methodologies to bolster its operational versatility and resilience. In urban canyon environments, the positioning performance of the S−NDM algorithm proposed in this paper is evaluated under different tightly coupled SPP−related and RTK−related models. The results exhibit that the Sky−GVIO system achieves meter-level accuracy under the SPP mode and sub-decimeter precision with RTK positioning, surpassing the performance of GNSS/INS/Vision frameworks devoid of S−NDM. Additionally, the sky-view image dataset, inclusive of training and evaluation subsets, has been made publicly accessible for scholarly exploration. Full article

In response to the demand for high-precision point cloud mapping of subway trains in long tunnel degradation scenarios in major urban cities, we propose a map construction method based on LiDAR and inertial measurement sensors. This method comprises a tightly coupled frontend odometry system based on error Kalman filters and backend optimization using factor graphs. In the frontend odometry, inertial calculation results serve as predictions for the filter, and residuals between LiDAR points and local map plane point clouds are used for filter updates. The global pose graph is constructed based on inter-frame odometry and other constraint factors, followed by a smoothing optimization for map building. Multiple experiments in subway tunnel scenarios demonstrate that the proposed method achieves robust trajectory estimation in long tunnel scenes, where classical multi-sensor fusion methods fail due to sensor degradation. The proposed method achieves a trajectory consistency of 0.1 m in tunnel scenes, meeting the accuracy requirements for train arrival, parking, and interval operations. Additionally, in an industrial park scenario, the method is compared with ground truth provided by inertial navigation, showing an accumulated error of less than 0.2%, indicating high precision. Full article

Exposure to repeated mild blast traumatic brain injury (mbTBI) is common in combat soldiers and the training of Special Forces. Evidence suggests that repeated exposure to a mild or subthreshold blast can cause serious and long-lasting impairments, but the mechanisms causing these symptoms are unclear. In this study, we characterise the effects of single and tightly coupled repeated mbTBI in Sprague–Dawley rats exposed to shockwaves generated using a shock tube. The primary outcomes are functional neurologic function (unconsciousness, neuroscore, weight loss, and RotaRod performance) and neuronal density in brain regions associated with sensorimotor function. Exposure to a single shockwave does not result in functional impairments or histologic injury, which is consistent with a mild or subthreshold injury. In contrast, exposure to three tightly coupled shockwaves results in unconsciousness, along with persistent neurologic impairments. Significant neuronal loss following repeated blast was observed in the motor cortex, somatosensory cortex, auditory cortex, and amygdala. Neuronal loss was not accompanied by changes in astrocyte reactivity. Our study identifies specific brain regions particularly sensitive to repeated mbTBI. The reasons for this sensitivity may include exposure to less attenuated shockwaves or proximity to tissue density transitions, and this merits further investigation. Our novel model will be useful in elucidating the mechanisms of sensitisation to injury, the temporal window of sensitivity and the evaluation of new treatments. Full article

The integration of global navigation satellite system (GNSS) precise point positioning (PPP) and inertial navigation system (INS) is widely used in navigation for its robustness and resilience, especially in case of GNSS signal blockage. With GNSS modernization, a variety of PPP models have been developed and studied, which has also led to various PPP/INS integration methods. In this study, we investigated the performance of a real-time GPS/Galileo zero-difference ionosphere-free (IF) PPP/INS integration with the application of uncombined bias products. This uncombined bias correction was independent of PPP modeling on the user side and also enabled carrier phase ambiguity resolution (AR). CNES (Centre National d’Etudes Spatiales) real-time orbit, clock, and uncombined bias products were used. Six positioning modes were evaluated, including PPP, PPP/INS loosely coupled integration (LCI), PPP/INS tightly coupled integration (TCI), and three of these with uncombined bias correction through a train positioning test in an open sky environment and two van positioning tests at a complex road and city center. All of the tests used a tactical-grade inertial measurement unit (IMU). In the train test, we found that ambiguity-float PPP had almost identical performance with LCI and TCI, which reached an accuracy of 8.5, 5.7, and 4.9 cm in the north (N), east (E) and up (U) direction, respectively. After AR, significant improvements on the east error component were achieved, which were 47%, 40%, and 38% for PPP-AR, PPP-AR/INS LCI, and PPP-AR/INS TCI, respectively. In the van tests, frequent signal interruptions due to bridges, vegetation, and city canyons make the IF AR difficult. TCI achieved the highest accuracies, which were 32, 29, and 41 cm for the N/E/U component, respectively, and also effectively eliminated the solution re-convergence in PPP. Full article

In order to accurately locate personnel in underground spaces, positioning equipment is required to be mounted on wearable equipment. But the wearable inertial personnel positioning equipment moves with personnel and the phenomenon of measurement reference wobble (referred to as moving base) is bound to occur, which leads to inertial measurement errors and makes the positioning accuracy degraded. A neural network-assisted binocular visual-inertial personnel positioning method is proposed to address this problem. Using visual-inertial Simultaneous Localization and Mapping to generate ground truth information (including position, velocity, acceleration data, and gyroscope data), a trained neural network is used to regress 6-dimensional inertial measurement data from the IMU data fragment under the moving base, and a position loss function is constructed based on the regressed inertial data to reduce the inertial measurement error. Finally, using vision as the observation quantity, the point feature and inertial measurement data are tightly coupled to optimize the mechanism to improve the personnel positioning accuracy. Through the actual scene experiment, it is verified that the proposed method can improve the positioning accuracy of personnel. The positioning error of the proposed algorithm is 0.50%D, and it is reduced by 92.20% under the moving base. Full article

The ability to continuously and unobtrusively monitor and classify breathing patterns can be very valuable for automated health assessments because respiration is tightly coupled to many physiological processes. Pathophysiological changes in these processes often manifest in altered breathing patterns and can thus be immediately detected. In order to develop a breathing pattern monitoring system, a study was conducted in which volunteer subjects were asked to breathe according to a predefined breathing protocol containing multiple breathing patterns while being recorded with color and thermal cameras. The recordings were used to develop and compare several respiratory signal extraction algorithms. An algorithm for the robust extraction of multiple respiratory features was developed and evaluated, capable of differentiating a wide range of respiratory patterns. These features were used to train a one vs. one multiclass support vector machine, which can distinguish between breathing patterns with an accuracy of $95.79$ %. The recorded dataset was published to enable further improvement of contactless breathing pattern classification, especially for complex breathing patterns. Full article

Atmospheric turbulence-degraded images in typical practical application scenarios are always disturbed by severe additive noise. Severe additive noise corrupts the prior assumptions of most baseline deconvolution methods. Existing methods either ignore the additive noise term during optimization or perform denoising and deblurring completely independently. However, their performances are not high because they do not conform to the prior that multiple degradation factors are tightly coupled. This paper proposes a Noise Suppression-based Restoration Network (NSRN) for turbulence-degraded images, in which the noise suppression module is designed to learn low-rank subspaces from turbulence-degraded images, the attention-based asymmetric U-NET module is designed for blurred-image deconvolution, and the Fine Deep Back-Projection (FDBP) module is used for multi-level feature fusion to reconstruct a sharp image. Furthermore, an improved curriculum learning strategy is proposed, which trains the network gradually to achieve superior performance through a local-to-global, easy-to-difficult learning method. Based on NSRN, we achieve state-of-the-art performance with PSNR of 30.1 dB and SSIM of 0.9 on the simulated dataset and better visual results on the real images. Full article

East-Asia winter cooling and the associated atmospheric and oceanic influences were investigated based on the wintertime daily temperature and circulation fields during 1950–2020. Both the case study on the 2020/2021 cold surge and the large-sample clustering in the recent 71 winters extracted similar circulation signatures for East-Asia cooling, which are featured by the blocking-related anticyclonic circulation in North Eurasia, large-scale mid-to-high-latitude wave trains, decrease in the sea surface temperature (SST) in tropical Pacific, and the sea-ice cover (SIC) reduction in the Barents and Kara Seas (BKS). From the joint clustering of Eurasian circulation and temperature, two circulation modes that have a cooling effect on East Asia account for 41% of winter days. One of the two modes is characterized by the cyclonic circulation over Northeast Asia coupled with a southward-extending negative-phase Arctic Oscillation (AO−), whose cooling effect is mainly concentrated in central Siberia. The other cooling mode, featuring an anticyclonic circulation over the Urals and AO+ in middle-to-high latitudes, has a relatively stronger cooling effect on lower latitudes, including Mongolia and North China. In general, the occurrences of the mode with warming/cooling effect on East Asia show an overall downward/upward trend. The two cooling modes are significantly influenced by the La Niña-type SST anomaly and reduced SIC in BKS through large-scale wave trains, of which the tropical oceanic forcing mainly acts as a climatic background. Furthermore, the polar forcing is more tightly bound to internal atmospheric variability. Therefore, the tropical SST tends to exert impact over a seasonal scale, but the SIC influence is more significant below the intraseasonal scale; moreover, the synergy between the tropical and polar oceanic forcing can increase the East-Asia cooling days by 3–4% and cold extremes by 5%, mainly through enhancing the AO-related circulation mode. Full article

High-precision, low-cost, and wide coverage indoor positioning technology is the key to indoor and outdoor integrated location-based services, and it has broad market prospects and social value. However, achieving sub-meter level positioning accuracy in indoor environments remains a real challenge due to the blockage of indoor Global Navigation Satellite System (GNSS) signals, the complexity of indoor environments, and the unpredictability of user behavior. In this paper, we introduce a multi-module BLE broadcaster (MMBB)-based indoor positioning solution in which a tightly coupled fusion architecture is implemented on a smartphone. The solution integrates ranging measurements from multiple MMBB and the measurements of the accelerometer built into a smartphone. It becomes an instant positioning solution without any training phase by adopting a calibrated linearly segmented path loss model for ranging. We apply the pedestrian walking speed derived by the smartphone accelerometer to constrain an unscented Kalman filter method that is used to estimate the location and speed. The accuracy of the proposed method is 50% at 0.79 m and 95% at 1.6 m at in terms of horizontal error distance. Position update frequency is 10 Hz and the time to first fix is 0.1 s. The system can easily adapt a global coordinator system so that it can seamlessly work together with the GNSS to form an indoor/outdoor positioning solution. Full article

Fault detection and exclusion are essential to ensure the integrity and reliability of the tightly coupled global navigation satellite system (GNSS)/inertial navigation system (INS) integrated navigation system. A fault detection and system reconfiguration scheme based on generative adversarial networks (GAN-FDSR) for tightly coupled systems is proposed in this paper. The chaotic characteristics of pseudo-range data are analyzed, and the raw data are reconstructed in phase space to improve the learning ability of the models for non-linearity. The trained model is used to calculate generation and discrimination scores to construct fault detection functions and detection thresholds while retaining the generated data for subsequent system reconfiguration. The influence of satellites on positioning accuracy of the system under different environments is discussed, and the system reconfiguration scheme is dynamically selected by calculating the relative differential precision of positioning (RDPOP) of the faulty satellites. Simulation experiments are conducted using the field test data to assess fault detection performance and positioning accuracy. The results show that the proposed method greatly improves the detection sensitivity of the system for small-amplitude faults and gradual faults, and effectively reduces the positioning error during faults. Full article

The problem of electro-thermal coupling is widely present in the integrated circuit (IC). The accuracy and efficiency of traditional solution methods, such as the finite element method (FEM), are tightly related to the quality and density of mesh construction. Recently, PINN (physics-informed neural network) was proposed as a method for solving differential equations. This method is mesh free and generalizes the process of solving PDEs regardless of the equations’ structure. Therefore, an experiment is conducted to explore the feasibility of PINN in solving electro-thermal coupling problems, which include the electrokinetic field and steady-state thermal field. We utilize two neural networks in the form of sequential training to approximate the electric field and the thermal field, respectively. The experimental results show that PINN provides good accuracy in solving electro-thermal coupling problems. Full article

The task of pitch estimation is an essential step in many audio signal processing applications. In this paper, we propose a data-driven pitch estimation network, the Dual Attention Network (DA-Net), which processes directly on the time-domain samples of monophonic music. DA-Net includes six Dual Attention Modules (DA-Modules), and each of them includes two kinds of attention: element-wise and channel-wise attention. DA-Net is to perform element attention and channel attention operations on convolution features, which reflects the idea of "symmetry". DA-Modules can model the semantic interdependencies between element-wise and channel-wise features. In the DA-Module, the element-wise attention mechanism is realized by a Convolutional Gated Linear Unit (ConvGLU), and the channel-wise attention mechanism is realized by a Squeeze-and-Excitation (SE) block. We explored three kinds of combination modes (serial mode, parallel mode, and tightly coupled mode) of the element-wise attention and channel-wise attention. Element-wise attention selectively emphasizes useful features by re-weighting the features at all positions. Channel-wise attention can learn to use global information to selectively emphasize the informative feature maps and suppress the less useful ones. Therefore, DA-Net adaptively integrates the local features with their global dependencies. The outputs of DA-Net are fed into a fully connected layer to generate a 360-dimensional vector corresponding to 360 pitches. We trained the proposed network on the iKala and MDB-stem-synth datasets, respectively. According to the experimental results, our proposed dual attention network with tightly coupled mode achieved the best performance. Full article

Airborne target tracking in infrared imagery remains a challenging task. The airborne target usually has a low signal-to-noise ratio and shows different visual patterns. The features adopted in the visual tracking algorithm are usually deep features pre-trained on ImageNet, which are not tightly coupled with the current video domain and therefore might not be optimal for infrared target tracking. To this end, we propose a new approach to learn the domain-specific features, which can be adapted to the current video online without pre-training on a large datasets. Considering that only a few samples of the initial frame can be used for online training, general feature representations are encoded to the network for a better initialization. The feature learning module is flexible and can be integrated into tracking frameworks based on correlation filters to improve the baseline method. Experiments on airborne infrared imagery are conducted to demonstrate the effectiveness of our tracking algorithm. Full article