Search

The identification of individuals based on their walking patterns, also known as gait recognition, has garnered considerable interest as a biometric trait. The use of gait patterns for gender classification has emerged as a significant research domain with diverse applications across multiple fields. The present investigation centers on the classification of gender based on gait utilizing data from Ultra-wide band radar. A total of 181 participants were included in the study, and data was gathered using Ultra-wide band radar technology. This study investigates various preprocessing techniques, feature extraction methods, and dimensionality reduction approaches to efficiently process Ultra-wide band radar data. The data quality is improved through the utilization of a two-pulse canceller and discrete wavelet transform. The hybrid feature dataset is generated through the creation of gray-level co-occurrence matrices and subsequent extraction of statistical features. Principal Component Analysis is utilized for dimensionality reduction, and prediction probabilities are incorporated as features for classification optimization. The present study employs k-fold cross-validation to train and assess machine learning classifiers, Decision Tree, Random Forest, Support Vector Machine, Logistic Regression, Multi-Layer Perceptron, K-Nearest Neighbors, and Extra Tree Classifier. The Multilayer Perceptron exhibits superior performance, achieving an accuracy of 0.936. The Support Vector Machine and k-Nearest Neighbors classifiers closely trail behind, both achieving an accuracy of 0.934. This research is of the utmost importance due to its capacity to offer solutions to crucial problems in multiple domains. The findings indicate that the utilization of UWB radar data for gait-based gender classification holds promise in diverse domains, including biometrics, surveillance, and healthcare. The present study makes a valuable contribution to the progress of gender classification systems that rely on gait patterns. [ABSTRACT FROM AUTHOR]

Using satellite-based SAR (Synthetic Aperture Radar) imagery to detect and track ships is a formidable challenge. However, accurate analysis is hampered by inherent difficulties such as obscured edges, multiple targets, varying dimensions and complex backgrounds. These factors contribute to a poor signal-to-noise ratio. Various artificial intelligence models have been developed to improve these problems, especially with YOLO-based models. To overcome the above challenges and achieve robust performance, this study presents a model called SwinYOLOv7, a novel fusion of the YOLOv7 framework with the Features Pyramid Network and the Swin Transformer using ground-breaking anchor-free detection algorithms. This innovative method aims to increase the accuracy of vessel detection while reducing the impact of background clutter. The proposed model improved by YOLOv7 examined three different datasets in detail: SRSDD-v1.0, HRSID, and SSDD to optimize the performance of the model. The training process was consistently verified using superior recall, precision, and F1-score values, which can be easily compared with previous studies. The results show that the model using the Swin Transformer attention mechanism and using an image size of 640×640 achieves the highest accuracy of 96.59%. Alternative attention mechanisms, including the Squeeze-and-Excitation Network (SEnet), the Convolutional Block Attention Module (CBAM), Channel Attention (CA) and Efficient Channel Attention (ECA), deliver poorer accuracy rates. The combination of YOLOv7 and Swin Transformer yielded encouraging results that enabled the proposed model to outperform the current benchmarking models. Therefore, the proposed model provides a compelling solution to ensure accurate vessel identification in complex search and rescue scenarios. [Display omitted] • A new version of YOLOv7 model was developed based on Swin Transformer. • Different data sources were used for training and testing new model for ship detection. • The performance of new model was compared with other 18 older models. • The new YOLOv7 model boosts the detection performance better than previous ones. • Model using 640×640 image size achieved the highest accuracy of 96.59%. [ABSTRACT FROM AUTHOR]

The increasing prevalence of low probability of intercept (LPI) radars in electronic warfare (EW) systems highlights the need to effectively recognize phase-coded radar waveforms intercepted at radar warning receivers (RWRs) from various threat emitters. The complexities of the electromagnetic (EM) spectrum necessitate the implementation of an automatic modulation recognition system (AMRS) within the RWR. However, a major challenge is accurately identifying phase-coded waveforms with high accuracy at low signal-to-noise ratios (SNRs). This research addresses the challenge by exploring three artificial intelligence (AI)-driven AMRS architectures for identifying phase-coded waveforms using short-time Fourier transform (STFT): vision transformer (ViT), vicinity vision transformer (VViT), and deep convolutional neural network (DCNN). Unlike recent methods focusing on amplitude spectra, our research delves into the phase spectra for the feature extraction of phase-coded waveforms. We leverage phase-based features extracted from intercepted phase-coded waveforms to classify six types of phase-coded signals using these AMRS architectures across SNR levels ranging from −16 dB to 8 dB. The simulation experiments show that these methods are effective at an SNR of −16 dB, with VViT and ViT achieving recognition accuracies of 93% and 92.7%, respectively. Both outperform the DCNN, which achieves an RA of 89% at the same SNR. This approach promises to enhance situational awareness and decision-making in EW operations by improving phase-coded radar waveform recognition and enabling appropriate countermeasure deployment. [ABSTRACT FROM AUTHOR]

Existing lightweight artificial intelligence models for interpreting tunnel lining Ground Penetrating Radar (GPR) data often suffer from inadequate accuracy and robustness owing to noise interference caused by in-tunnel infrastructure. This study introduces an optimised method, named MTGPR, for the automatic detection of voids and cavities in tunnel linings based on GPR radargrams. The proposed model offers strengthened feature extraction and fusion owing to the use of CAPW-YOLO, a hybrid model aimed at enhancing accuracy in the presence of infrastructure interference. To address the shortage of high-quality training samples, an augmented dataset was generated by refining synthetic radargrams. Ablation experiments showcased that the proposed scheme attained an accuracy of 88.5% and a precision of 84.0%. In comparison to the baseline model, the proposed method exhibited a 46.9% increase in recognition speed and a 10.2% reduction in weight parameter quantity. Consequently, the proposed method advances identification accuracy whilst preserving lightweight and high-speed. • The optimised, lightweight deep-learning MTGPR method is presented. • The method detects subway tunnel lining voids and cavities using radargrams • Ablation experiments showed that this method yielded accuracy/precision: 88.5/84.0%. • MTGPR achieves enhanced performance in highly interfering noisy environments. [ABSTRACT FROM AUTHOR]

This study presents the development of a novel automated system, Rapid Analysis and Detection of At-risk students with Artificial intelligence-based Response (RADAR), that utilizes explainable artificial intelligence (XAI) to identify students who are at risk of falling behind or dropping out of school. The system integrates various features, including learners' personality, previous academic performance, current academic concepts progress, and soft skills. Machine learning algorithms are utilized to analyze the combination of data and identify patterns that predict a student's likelihood of falling behind. The proposed RADAR system employs a multi-modal approach, considering the learner's features. The system is trained on a dataset of students from a school district, where the data is collected and preprocessed accordingly. The feature selection algorithm is applied to identify the most relevant features that can accurately predict students at-risk of falling behind or dropping out. The pilot study establishes the framework of the system and examines the implementation implications. The results of this study indicate that the RADAR system achieves high accuracy in identifying at-risk students. Furthermore, the system effectively employs the identified features to predict students' performance in a continuous manner, enabling advisors, administrators, and students to take proactive measures to maintain high academic progress levels. The system is designed to provide an automated and continuous monitoring of the students' performance, and to notify the relevant parties in case of any deviations. The proposed system represents an innovative approach to using XAI for the detection and support of at-risk students, enabling educators to take timely actions. The results of this study demonstrate the potential of the RADAR system to improve the support and guidance provided to at-risk students, and to ultimately improve their academic outcomes. [ABSTRACT FROM AUTHOR]

This research assessed the efficacy of deep segmentation in identifying and measuring natural karst depressions in the Bambuí Group's carbonate rocks in Western Bahia, Brazil. The investigation used five Global Digital Elevation Models (DEMs) with 30-m resolution: Advanced Spaceborne Thermal Emission and Reflection Radiometer - Global Digital Elevation Model version 3 (ASTER-GDEM v3), Advanced Land Observing Satellite World 3D – 30 m version 3.2 (AW3D30 v3.2), Copernicus 30 m global DEM (GLO-30), NASA Digital Elevation Model version 1 (NASADEM v1), and Shuttle Radar Topography Mission version 3 (SRTM v3). The karst feature detection analysis compared five semantic segmentation architectures: Feature Pyramid Networks (FPN), LinkNet, UNet, UNet++, DVL3+, using an EfficientNet-B7 backbone, one instance segmentation model (Mask-RCNN), and a semantic-to-instance conversion method. This comparison considers different datasets, including one, two, or eleven variables (DEM, DEM-based sink depth, and nine terrain attributes). Besides, we performed a combinatorial analysis of the DEMs to evaluate the improvement in karst feature detection. The methodology involved the generation of geomorphometric attributes, sample labeling from Sentinel-2 and Operational Land Imager-Landsat 8 datasets, training-validation-testing steps with 128 × 128 samples, reconstruction of large images for semantic and instance segmentation, and accuracy analysis. The findings revealed that GLO-30 and AW3D30 data were the most accurate, while ASTER GDEM performed poorly in both segmentation forms. Among the semantic models, FPN showed the highest accuracy. The 11-variable models preferentially outperformed those with fewer in both types of segmentation. The approach of semantic-to-instance conversion with Geographic Information System tools favored individualizing karst depressions and obtaining efficient quantification, consisting of an easy alternative to achieve instance segmentation. Reconstruction of large remote sensing images through sliding windows considering the specifics of instance and semantic segmentation demonstrated that smaller stride enhances object coverage and reduces the risk of losing crucial information, effectively improving the predictions. The combinatorial analysis for semantic and instance segmentation indicates that models incorporating more DEMs (4- and 5-DEM models) and variables achieve generally higher accuracy. The best result in semantic segmentation was combining the five DEM datasets using 11 variables, reaching an F-score of 85.06 and IoU of 74.00. In instance segmentation, the best result for the bounding box was the model that integrates AW3D30, GLO-30, NASADEM, and SRTM with eleven variables reaching Average Precision (AP) of 45.64, AP50 of 88.40 and AP75 of 39.38, while the best result for the segmentation mask was the model that integrates the five models with eleven variables with AP of 42.61, AP50 of 86.79 and AP75 of 35.43. These results demonstrate that integrating a wide range of DEM data, even the lowest performing ones, improves model generalization and accuracy in segmentation, leveraging strengths and mitigating individual weaknesses. Future work could explore high-resolution DEMs and the integration of various deep-learning methods. [Display omitted] • First deep segmentation investigation for karst depression detection in Brazil. • Copernicus Digital Elevation Model with 30-m resolution achieved superior accuracy. • Feature Pyramid Network was more accurate model in detecting karst depressions. • Combining digital elevation model with morphometric attributes improves accuracy. • Successful quantification using semantic-to-instance segmentation conversion. [ABSTRACT FROM AUTHOR]

Line-line (LL) faults in photovoltaic (PV) arrays lead to a reduction in the output power and service life of PV systems, and if not detected and eliminated in time, may cause catastrophic fire hazards. The severity of LL faults could have an adverse effect on the performance of protection devices and depends on two main factors: 1) the number of modules involved in the fault, and 2) the resistivity of the fault path. In this study, first, LL faults are classified using a support vector machine (SVM) and then the main process of LL faults resistance (R f) estimation is carried out to determine the accurate severity of the fault. Conventionally, to measure the resistivity of the fault path, it is inevitable to employ multiple additional current and voltage sensors, which does not seem economically convenient and practical. Therefore, in this study, artificial intelligence (AI) has been utilized to estimate the fault resistance thus eliminating all the additional sensors. To this end, a regression-based dense neural network (R-DNN) is proposed and fine-tuned to predict the R f in a continuous interval of 0–24 Ω. Also, to provide the proposed model with a more organized thus simpler interpretation of the initial dataset, novel tangential features are constructed using five predefined points on the PV array current-voltage (I–V) characteristic curve. The experimental results show that the model is perfectly capable of diagnosing the LL faults and estimating the fault resistance values under various conditions. Finally, a comparison is carried out between the final R-DNN model and several regression-based machine learning algorithms which shows that the proposed R-DNN outperforms the other algorithms in terms of accuracy and execution time. [ABSTRACT FROM AUTHOR]

Seasonal snow-derived water is a critical component of the water supply in the mountains and downstream regions, and the accurate characterization of available water in the form of snow-water-equivalent (SWE), peak SWE, and snowmelt onset are essential inputs for water management efforts. Arising from recent advancements in artificial intelligence (AI) and machine learning (ML), we introduce a large-scale ML SWE model leveraging publicly available data sources and open-source software. The model demonstrates the application of a limited feature space in a relatively simple ML architecture without the need for process-based formulations to effectively estimate spatially continuous SWE at a daily temporal resolution. Beginning with in situ SWE measurements (i.e., SNOTEL), lidar-derived terrain features, and temporal variables, we employ localized feature engineering and optimization via gradient-boosting decision trees to identify regionally unique drivers of snowpack dynamics and use the optimal features to train regionally independent artificial neural networks to estimate regional SWE at a 1 km spatial resolution. The model results yield respectable skill in reconstructed 1 km gridded SWE magnitudes in a hindcast simulation of the 2019 water year that is independent of the training and testing data. Comparing model estimates to over 6200 observations, the model demonstrates a weighted RMSE of 15.4 cm, Kling-Gupta Efficiency metric of 0.86, and a percent bias of 0.71% across 23 snow-influenced regions in the western U.S. The model simulation produces peak SWE estimates within 10 cm for twenty of the twenty-three regions, demonstrating capability in effectively capturing regional snow accumulation processes. The demonstration of low-error ML workflows capable of providing near-real-time, spatially continuous SWE estimates at a high spatial resolution provides proof-of-concept and a foundation to effectively update snow state variables that drive water supply forecasts in snow-dominated regions. • A new Machine Learning-based SWE estimation model for the Western United States. • Utilization of open-source tools and up-to-date in-situ observations to estimate SWE. • Reconstructed SWE magnitudes exhibit respectable skill in a hindcast simulation. • Output may serve as a supplemental state-of-snowpack input to hydrologic models. [ABSTRACT FROM AUTHOR]