Search Results (63)

Recently, studies on driver inattention state recognition as an advanced mobility application technology are being actively conducted to prevent traffic accidents caused by driver drowsiness and distraction. The driver inattention state recognition system is a technology that recognizes drowsiness and distraction by using driver behavior, biosignals, and vehicle data characteristics. Existing driver drowsiness detection systems are wearable accessories that have partial occlusion of facial features and light scattering due to changes in internal and external lighting, which results in momentary image resolution degradation, making it difficult to recognize the driver’s condition. In this paper, we propose a transformer based spatial temporal fusion network (STFTransNet) that fuses multi-modality information for improved driver inattention state recognition in images where the driver’s face is partially occluded by wearing accessories and the instantaneous resolution is degraded due to light scattering from changes in lighting in a driving environment. The proposed STFTransNet consists of (i) a mediapipe face mesh-based facial landmark extraction process for facial feature extraction, (ii) an RCN-based two-stream cross-attention process for learning spatial features of driver face and body action images, (iii) a TCN-based temporal feature extraction process for learning temporal features of extracted features, and (iv) an ensemble of spatial and temporal features and a classification process to recognize the final driver state. As a result of the experiment, the proposed STFTransNet achieved an accuracy of 4.56% better than the existing VBFLLFA model in the NTHU-DDD public DB, 3.48% better than the existing InceptionV3 + HRNN model in the StateFarm public DB, and 3.78% better than the existing VBFLLFA model in the YawDD public DB. The proposed STFTransNet is designed as a two-stream network that can input the driver’s face and action images and solves the degradation in driver inattention state recognition performance due to partial facial feature occlusion and light blur through spatial feature and temporal feature fusion. Full article

This study introduces GaitX, a real-time pedestrian behavior recognition system that leverages only the built-in sensors of a smartphone eliminating the need for external hardware. The system is capable of detecting abnormal walking behavior, such as using a smartphone while walking, regardless of whether the device is handheld or pocketed. GaitX applies multivariate time-series features derived from accelerometer data, using ensemble machine learning models like XGBoost and Random Forest for classification. Experimental validation across 21 subjects demonstrated an average classification accuracy of 92.3%, with notably high precision (97.1%) in identifying distracted walking. In addition to real-time detection, the system explores the link between gait variability and psychological traits by integrating MBTI personality profiling, revealing the potential for emotion-aware mobility analytics. Our findings offer a scalable, cost-effective solution for mobile safety applications and personalized health monitoring. Full article

Fine-grained aircraft classification in remote sensing is a critical task within the field of remote sensing image processing, aiming to precisely distinguish between different types of aircraft in aerial images. Due to the high visual similarity among aircraft targets in remote sensing images, accurately capturing subtle and discriminative features becomes a key technical challenge for fine-grained aircraft classification. In this context, we propose a Normalized Coordinate Attention-Based Counterfactual Classification Network (NCC-Net), which emphasizes the spatial positional information of aircraft targets and effectively captures long-range dependencies, thereby enabling precise localization of various aircraft components. Furthermore, we analyze the proposed network from a causal perspective, encouraging the model to focus on key discriminative features of the aircraft while minimizing distraction from the surrounding environment and background. Experimental results on three benchmark datasets demonstrate the superiority of our method. Specifically, NCC-Net achieves Top-1 classification accuracies of 97.7% on FAIR1M, 95.2% on MTARSI2, and 98.4% on ARSI120, outperforming several state-of-the-art methods. These results highlight the effectiveness and generalizability of our proposed method for fine-grained remote sensing target recognition. Full article

Objectives: Predicting intensive care unit (ICU) admissions during pandemic outbreaks such as COVID-19 can assist clinicians in early intervention and the better allocation of medical resources. Artificial intelligence (AI) tools are promising for this task, but their development can be hindered by the limited availability of training data. This study aims to explore model development strategies in data-limited scenarios, specifically in detecting the need for ICU admission using chest X-rays of COVID-19 patients by leveraging transfer learning and data extension to improve model performance. Methods: We explored convolutional neural networks (CNNs) pre-trained on either natural images or chest X-rays, fine-tuning them on a relatively limited dataset (COVID-19-NY-SBU, n = 899) of lung-segmented X-ray images for ICU admission classification. To further address data scarcity, we introduced a dataset extension strategy that integrates an additional dataset (MIDRC-RICORD-1c, n = 417) with different but clinically relevant labels. Results: The TorchX-SBU-RSNA and ELIXR-SBU-RSNA models, leveraging X-ray-pre-trained models with our training data extension approach, enhanced ICU admission classification performance from a baseline AUC of 0.66 (56% sensitivity and 68% specificity) to AUCs of 0.77–0.78 (58–62% sensitivity and 78–80% specificity). The gradient-weighted class activation mapping (Grad-CAM) analysis demonstrated that the TorchX-SBU-RSNA model focused more precisely on the relevant lung regions and reduced the distractions from non-relevant areas compared to the natural image-pre-trained model without data expansion. Conclusions: This study demonstrates the benefits of medical image-specific pre-training and strategic dataset expansion in enhancing the model performance of imaging AI models. Moreover, this approach demonstrates the potential of using diverse but limited data sources to alleviate the limitations of model development for medical imaging AI. The developed AI models and training strategies may facilitate more effective and efficient patient management and resource allocation in future outbreaks of infectious respiratory diseases. Full article

In the age of technological advancement, brainwave monitoring and attention tracking are critical for individual productivity and organizational efficiency. However, distractions pose significant challenges, making an effective brainwave monitoring and attention system essential. Generative Adversarial Networks (GANs) enhance medical datasets by synthesizing diverse samples. This paper explores their application in improving datasets for indoor positioning and brainwave monitoring-based attention tracking. The goal is to develop an intelligent lighting system that adjusts settings based on users’ brainwave states and positions. GANs enhance brainwave monitoring and positioning datasets, with Principal Component Analysis (PCA) applied for dimensionality reduction. machine learning and deep learning models train on these augmented datasets, enabling dynamic lighting adjustments to optimize user experience. GANs undergo parameter fine-tuning to improve dataset quality. Various classification models, including neural networks (NN), K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Long Short-Term Memory (LSTM), are used for brainwave monitoring, attention, and positioning. Fuzzy logic enhances system stability. The trained models are integrated with hardware components, such as the Raspberry Pi 4, to implement an “Indoor Positioning Deep Learning Brainwave Monitoring and Attention Monitoring System Based on the Grey Wolf Optimizer Algorithm”. Experimental results demonstrate a positioning accuracy of 15 cm and significant improvements in brainwave monitoring and attention tracking. Full article

The emergence of micro-mobility transportation in urban areas has led to a transformative shift in mobility options, yet it has also brought about heightened traffic conflicts and crashes. This research addresses these challenges by pioneering the integration of image-processing techniques with machine learning methodologies to analyze crash diagrams. The study aims to extract latent features from crash data, specifically focusing on understanding the factors influencing injury severity among vehicle and micro-mobility crashes in Michigan’s urban areas. Micro-mobility devices analyzed in this study are bicycles, e-wheelchairs, skateboards, and e-scooters. The AlexNet Convolutional Neural Network (CNN) was utilized to identify various attributes from crash diagrams, enabling the recognition and classification of micro-mobility device collision locations into three categories: roadside, shoulder, and bicycle lane. This study utilized the 2023 Michigan UD-10 crash reports comprising 1174 diverse micro-mobility crash diagrams. Subsequently, the Random Forest classification algorithm was utilized to pinpoint the primary factors and their interactions that affect the severity of micro-mobility injuries. The results suggest that roads with speed limits exceeding 40 mph are the most significant factor in determining the severity of micro-mobility injuries. In addition, micro-mobility rider violations and motorists left-turning maneuvers are associated with more severe crash outcomes. In addition, the findings emphasize the overall effect of many different variables, such as improper lane use, violations, and hazardous actions by micro-mobility users. These factors demonstrate elevated rates of prevalence among younger micro-mobility users and are found to be associated with distracted motorists, elderly motorists, or those who ride during nighttime. Full article

Substantial advancements have been achieved in hyperspectral image (HSI) classification through contemporary deep learning techniques. Nevertheless, the incorporation of an excessive number of irrelevant tokens in large-scale remote sensing data results in inefficient long-range modeling. To overcome this hurdle, this study introduces the Group-Sensitive Selective Perception Transformer (GSAT) framework, which builds upon the Vision Transformer (ViT) to enhance HSI classification outcomes. The innovation of the GSAT architecture is primarily evident in several key aspects. Firstly, the GSAT incorporates a Group-Sensitive Pixel Group Mapping (PGM) module, which organizes pixels into distinct groups. This allows the global self-attention mechanism to function within these groupings, effectively capturing local interdependencies within spectral channels. This grouping tactic not only boosts the model’s spatial awareness but also lessens computational complexity, enhancing overall efficiency. Secondly, the GSAT addresses the detrimental effects of superfluous tokens on model efficacy by introducing the Sensitivity Selection Framework (SSF) module. This module selectively identifies the most pertinent tokens for classification purposes, thereby minimizing distractions from extraneous information and bolstering the model’s representational strength. Furthermore, the SSF refines local representation through multi-scale feature selection, enabling the model to more effectively encapsulate feature data across various scales. Additionally, the GSAT architecture adeptly represents both global and local features of HSI data by merging global self-attention with local feature extraction. This integration strategy not only elevates classification precision but also enhances the model’s versatility in navigating complex scenes, particularly in urban mapping scenarios where it significantly outclasses previous deep learning methods. The advent of the GSAT architecture not only rectifies the inefficiencies of traditional deep learning approaches in processing extensive remote sensing imagery but also markededly enhances the performance of HSI classification tasks through the deployment of group-sensitive and selective perception mechanisms. It presents a novel viewpoint within the domain of hyperspectral image classification and is poised to propel further advancements in the field. Empirical testing on six standard HSI datasets confirms the superior performance of the proposed GSAT method in HSI classification, especially within urban mapping contexts, where it exceeds the capabilities of prior deep learning techniques. In essence, the GSAT architecture markedly refines HSI classification by pioneering group-sensitive pixel group mapping and selective perception mechanisms, heralding a significant breakthrough in hyperspectral image processing. Full article

Background: The rise in work zone crashes due to distracted and aggressive driving calls for improved safety measures. While Truck-Mounted Attenuators (TMAs) have helped reduce crash severity, the increasing number of crashes involving TMAs shows the need for improved warning systems. Methods: This study proposes an AI-enabled vision system to automatically alert drivers on collision courses with TMAs, addressing the limitations of manual alert systems. The system uses multi-task learning (MTL) to detect and classify vehicles, estimate distance zones (danger, warning, and safe), and perform lane and road segmentation. MTL improves efficiency and accuracy, making it ideal for devices with limited resources. Using a Generalized Efficient Layer Aggregation Network (GELAN) backbone, the system enhances stability and performance. Additionally, an alert module triggers alarms based on speed, acceleration, and time to collision. Results: The model achieves a recall of 90.5%, an mAP of 0.792 for vehicle detection, an mIOU of 0.948 for road segmentation, an accuracy of 81.5% for lane segmentation, and 83.8% accuracy for distance classification. Conclusions: The results show the system accurately detects vehicles, classifies distances, and provides real-time alerts, reducing TMA collision risks and enhancing work zone safety. Full article

Distracted driving is a significant threat to road safety, causing numerous accidents every year. Driver distraction detection systems offer a promising solution by alerting the driver to refocus on the primary driving task. Even with increasing vehicle automation, human drivers must remain alert, especially in partially automated vehicles where they may need to take control in critical situations. In this work, an AI-based distraction detection model is developed that focuses on improving classification performance using a long short-term memory (LSTM) network. Unlike traditional approaches that evaluate individual frames independently, the LSTM network captures temporal dependencies across multiple time steps. In addition, this study investigated the integration of vehicle sensor data and an inertial measurement unit (IMU) to further improve detection accuracy. The results show that the recurrent LSTM network significantly improved the average F1 score from 71.3% to 87.0% compared to a traditional vision-based approach using a single image convolutional neural network (CNN). Incorporating sensor data further increased the score to 90.1%. These results highlight the benefits of integrating temporal dependencies and multimodal inputs and demonstrate the potential for more effective driver distraction detection systems that can improve road safety. Full article

One of the factors that threaten traffic safety and cause various traffic problems is distracted drivers. Various studies have been carried out to ensure traffic safety and, accordingly, to reduce traffic accidents. This study aims to determine driver-distraction classes and detect driver violations with deep learning algorithms and decision-making methods. Different driver characteristics are included in the study by using a dataset created from five different countries. Weight classification in the range of 0–1 is used to determine the most important classes using the AHP method, and the most important 9 out of 23 classes are determined. The YOLOv8 algorithm is used to detect driver behaviors and distraction action classes. The YOLOv8 algorithm is examined according to performance-measurement criteria. According to mAP 0.5:0.95, an accuracy rate of 91.17% is obtained. In large datasets, it is seen that a successful result is obtained by using the AHP method, which is used to reduce transaction complexity, and the YOLOv8 algorithm, which is used to detect driver distraction. By detecting driver distraction, it is possible to partially avoid traffic accidents and the negative situations they create. While detecting and preventing driver distraction makes a significant contribution to traffic safety, it also provides a significant improvement in traffic accidents and traffic congestion, increasing transportation efficiency and the sustainability of cities. It also serves sustainable development goals such as energy efficiency and reducing carbon emissions. Full article

Document-level Event Argument Extraction (DEAE) aims to extract structural event knowledge composed of arguments and roles beyond the sentence level. Existing methods mainly focus on designing prompts and using Abstract Meaning Representation (AMR) graph structure as additional features to enrich event argument representation. However, two challenges still remain: (1) the long-range dependency between event trigger and event arguments and (2) the distracting context in the document towards an event that can mislead the argument classification. To address these issues, we propose a novel document-level event argument extraction model named AMR Parser and Sparse Representation (APSR). Specifically, APSR sets inter- and intra-sentential encoders to capture the contextual information in different scopes. Especially, in the intra-sentential encoder, APSR designs three types of sparse event argument attention mechanisms to extract the long-range dependency. Then, APSR constructs AMR semantic graphs, which capture the interactions among concepts well. Finally, APSR fuses the inter- and intra-sentential representations and predicts what role a candidate span plays. Experimental results on the RAMS and WikiEvents datasets demonstrate that APSR achieves a superior performance compared with competitive baselines in terms of F1 by $1.27\%$ and $3.12\%$, respectively. Full article

The vision transformer (ViT) has demonstrated performance comparable to that of convolutional neural networks (CNN) in the hyperspectral image classification domain. This is achieved by transforming images into sequence data and mining global spectral-spatial information to establish remote dependencies. Nevertheless, both the ViT and CNNs have their own limitations. For instance, a CNN is constrained by the extent of its receptive field, which prevents it from fully exploiting global spatial-spectral features. Conversely, the ViT is prone to excessive distraction during the feature extraction process. To be able to overcome the problem of insufficient feature information extraction caused using by a single paradigm, this paper proposes an MLP-mixer and a graph convolutional enhanced transformer (MGCET), whose network consists of a spatial-spectral extraction block (SSEB), an MLP-mixer, and a graph convolutional enhanced transformer (GCET). First, spatial-spectral features are extracted using SSEB, and then local spatial-spectral features are fused with global spatial-spectral features by the MLP-mixer. Finally, graph convolution is embedded in multi-head self-attention (MHSA) to mine spatial relationships and similarity between pixels, which further improves the modeling capability of the model. Correlation experiments were conducted on four different HSI datasets. The MGEET algorithm achieved overall accuracies (OAs) of 95.45%, 97.57%, 98.05%, and 98.52% on these datasets. Full article

This paper introduces a comprehensive framework for the detection of behaviors indicative of reduced concentration levels among motor vehicle operators, leveraging multimodal image data. By integrating dedicated deep learning models, our approach systematically analyzes RGB images, depth maps, and thermal imagery to identify driver drowsiness and distraction signs. Our novel contribution includes utilizing state-of-the-art convolutional neural networks (CNNs) and bidirectional long short-term memory (Bi-LSTM) networks for effective feature extraction and classification across diverse distraction scenarios. Additionally, we explore various data fusion techniques, demonstrating their impact on improving detection accuracy. The significance of this work lies in its potential to enhance road safety by providing more reliable and efficient tools for the real-time monitoring of driver attentiveness, thereby reducing the risk of accidents caused by distraction and fatigue. The proposed methods are thoroughly evaluated using a multimodal benchmark dataset, with results showing their substantial capabilities leading to the development of safety-enhancing technologies for vehicular environments. The primary challenge addressed in this study is the detection of driver states not relying on the lighting conditions. Our solution employs multimodal data integration, encompassing RGB, thermal, and depth images, to ensure robust and accurate monitoring regardless of external lighting variations Full article

To reduce safety accidents caused by distracted driving and address issues such as low recognition accuracy and deployment difficulties in current algorithms for distracted behavior detection, this paper proposes an algorithm that utilizes an improved KNN for classifying driver posture features to predict distracted driving behavior. Firstly, the number of channels in the Lightweight OpenPose network is pruned to predict and output the coordinates of key points in the upper body of the driver. Secondly, based on the principles of ergonomics, driving behavior features are modeled, and a set of five-dimensional feature values are obtained through geometric calculations. Finally, considering the relationship between the distance between samples and the number of samples, this paper proposes an adjustable distance-weighted KNN algorithm (ADW-KNN), which is used for classification and prediction. The experimental results show that the proposed algorithm achieved a recognition rate of 94.04% for distracted driving behavior on the public dataset SFD3, with a speed of up to 50FPS, superior to mainstream deep learning algorithms in terms of accuracy and speed. The superiority of ADW-KNN was further verified through experiments on other public datasets. Full article

Objectives: The study aims to assess and classify complications in patients treated for maxillary transverse deficiency using surgically assisted rapid maxillary/palatal expansion (SARME/SARPE) under general anesthesia. The classification of the complications aimed to assess the difficulty of their treatment as well as estimate its real cost. Methods: The retrospective study covered 185 patients who underwent surgery for a skeletal deformity in the form of maxillary constriction or in which maxillary constriction was one of its components treated by a team of maxillofacial surgeons at one center (97 females and 88 males, aged 15 to 47 years, mean age 26.1 years). Complications were divided into two groups: early complications (up to 3 weeks after surgery) and late complications (>3 weeks after surgery). In relation to the occurrence of complications, we analyzed the demographic characteristics of the group, type of skeletal deformity (class I, II, III), presence of open bite and asymmetry, surgical technique, type and size of appliance used for maxillary expansion, as well as the duration of surgery. Results: In the study group, complications were found in 18 patients (9.73%). Early complications were found in nine patients, while late complications were also found in nine patients. Early complications include no possibility of distraction, palatal mucosa necrosis, perforation of the maxillary alveolar process caused by the distractor and asymmetric distraction. Late complications include maxillary incisor root resorption, no bone formation in the distraction gap, and maxillary incisor necrosis. None of the patients required prolonged hospitalization and only one required reoperation. Conclusions: Complications were found in 18 patients (9.73%). All challenges were classified as minor difficulties since they did not suppress the final outcome of the treatment of skeletal malocclusion. However, the complications that did occur required additional corrective measures. Surgically assisted rapid maxillary expansion, when performed properly and in correlation with the correct orthodontic treatment protocol, is an effective and predictable technique for treating maxillary constriction. Full article