Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (387)

Search Parameters:
Keywords = track overlap

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
14 pages, 4462 KiB  
Article
Precise Cruise Control for Fixed-Wing Aircraft Based on Proximal Policy Optimization with Nonlinear Attitude Constraints
by Haotian Wu, Yan Guo, Juliang Cao, Zhiming Xiong and Junda Chen
Aerospace 2025, 12(8), 670; https://doi.org/10.3390/aerospace12080670 - 27 Jul 2025
Viewed by 175
Abstract
In response to the issues of severe pitch oscillation and unstable roll attitude present in existing reinforcement learning-based aircraft cruise control methods during dynamic maneuvers, this paper proposes a precise control method for aircraft cruising based on proximal policy optimization (PPO) with nonlinear [...] Read more.
In response to the issues of severe pitch oscillation and unstable roll attitude present in existing reinforcement learning-based aircraft cruise control methods during dynamic maneuvers, this paper proposes a precise control method for aircraft cruising based on proximal policy optimization (PPO) with nonlinear attitude constraints. This method first introduces a combination of long short-term memory (LSTM) and a fully connected layer (FC) to form the policy network of the PPO method, improving the algorithm’s learning efficiency for sequential data while avoiding feature compression. Secondly, it transforms cruise control into tracking target heading, altitude, and speed, achieving a mapping from motion states to optimal control actions within the policy network, and designs nonlinear constraints as the maximum reward intervals for pitch and roll to mitigate abnormal attitudes during maneuvers. Finally, a JSBSim simulation platform is established to train the network parameters, obtaining the optimal strategy for cruise control and achieving precise end-to-end control of the aircraft. Experimental results show that, compared to the cruise control method without dynamic constraints, the improved method reduces heading deviation by approximately 1.6° during ascent and 4.4° during descent, provides smoother pitch control, decreases steady-state altitude error by more than 1.5 m, and achieves higher accuracy in overlapping with the target trajectory during hexagonal trajectory tracking. Full article
(This article belongs to the Section Aeronautics)
Show Figures

Figure 1

12 pages, 219 KiB  
Article
Eye Movements During Pareidolia: Exploring Biomarkers for Thinking and Perception Problems on the Rorschach
by Mellisa Boyle, Barry Dauphin, Harold H. Greene, Mindee Juve and Ellen Day-Suba
J. Eye Mov. Res. 2025, 18(4), 32; https://doi.org/10.3390/jemr18040032 - 22 Jul 2025
Viewed by 511
Abstract
Eye movements (EMs) offer valuable insights into cognitive and perceptual processes, serving as potential biomarkers for disordered thinking. This study explores the relationship between EM indices and perception and thinking problems in the Rorschach Performance Assessment System (R-PAS). Sixty non-clinical participants underwent eye-tracking [...] Read more.
Eye movements (EMs) offer valuable insights into cognitive and perceptual processes, serving as potential biomarkers for disordered thinking. This study explores the relationship between EM indices and perception and thinking problems in the Rorschach Performance Assessment System (R-PAS). Sixty non-clinical participants underwent eye-tracking while completing the Rorschach test, focusing on variables from the Perception and Thinking Problems Domain (e.g., WSumCog, SevCog, FQo%). The results reveal that increased cognitive disturbances were associated with greater exploratory activity but reduced processing efficiency. Regression analyses highlighted the strong predictive role of cognitive variables (e.g., WSumCog) over perceptual ones (e.g., FQo%). Minimal overlap was observed between performance-based (R-PAS) and self-report measures (BSI), underscoring the need for multi-method approaches. The findings suggest that EM patterns could serve as biomarkers for early detection and intervention, offering a foundation for future research on psychotic-spectrum processes in clinical and non-clinical populations. Full article
Show Figures

Graphical abstract

28 pages, 1358 KiB  
Review
Understanding the Borderline Brain: A Review of Neurobiological Findings in Borderline Personality Disorder (BPD)
by Eleni Giannoulis, Christos Nousis, Ioanna-Jonida Sula, Maria-Evangelia Georgitsi and Ioannis Malogiannis
Biomedicines 2025, 13(7), 1783; https://doi.org/10.3390/biomedicines13071783 - 21 Jul 2025
Viewed by 604
Abstract
Borderline personality disorder (BPD) is a complex and heterogeneous condition characterized by emotional instability, impulsivity, and impaired regulation of interpersonal relationships. This narrative review integrates findings from recent neuroimaging, neurochemical, and treatment studies to identify core neurobiological mechanisms and highlight translational potential. Evidence [...] Read more.
Borderline personality disorder (BPD) is a complex and heterogeneous condition characterized by emotional instability, impulsivity, and impaired regulation of interpersonal relationships. This narrative review integrates findings from recent neuroimaging, neurochemical, and treatment studies to identify core neurobiological mechanisms and highlight translational potential. Evidence from 112 studies published up to 2025 is synthesized, encompassing structural MRI, resting-state and task-based functional MRI, EEG, PET, and emerging machine learning applications. Consistent disruptions are observed across the prefrontal–amygdala circuitry, the default mode network (DMN), and mentalization-related regions. BPD shows a dominant and stable pattern of hyperconnectivity in the precuneus. Transdiagnostic comparisons with PTSD and cocaine use disorder (CUD) suggest partial overlap in DMN dysregulation, though BPD-specific traits emerge in network topology. Machine learning models achieve a classification accuracy of 70–88% and may support the tracking of early treatment responses. Longitudinal fMRI studies indicate that psychodynamic therapy facilitates the progressive normalization of dorsal anterior cingulate cortex (dACC) activity and reductions in alexithymia. We discuss the role of phenotypic heterogeneity (internalizing versus externalizing profiles), the potential of neuromodulation guided by biomarkers, and the need for standardized imaging protocols. Limitations include small sample sizes, a lack of effective connectivity analyses, and minimal multicenter cohort representation. Future research should focus on constructing multimodal biomarker panels that integrate functional connectivity, epigenetics, and computational phenotyping. This review supports the use of a precision psychiatry approach for BPD by aligning neuroscience with scalable clinical tools. Full article
(This article belongs to the Section Neurobiology and Clinical Neuroscience)
Show Figures

Figure 1

22 pages, 22775 KiB  
Article
A Detection Line Counting Method Based on Multi-Target Detection and Tracking for Precision Rearing and High-Quality Breeding of Young Silkworm (Bombyx mori)
by Zhenghao Li, Hao Chang, Mingrui Shang, Zhanhua Song, Fuyang Tian, Fade Li, Guizheng Zhang, Tingju Sun, Yinfa Yan and Mochen Liu
Agriculture 2025, 15(14), 1524; https://doi.org/10.3390/agriculture15141524 - 15 Jul 2025
Viewed by 282
Abstract
The co-rearing model for young silkworms (Bombyx mori) utilizing artificial feed is currently undergoing significant promotion within the sericulture industry in China. Within this model, accurately counting the number of young silkworms serves as a crucial foundation for achieving precision rearing [...] Read more.
The co-rearing model for young silkworms (Bombyx mori) utilizing artificial feed is currently undergoing significant promotion within the sericulture industry in China. Within this model, accurately counting the number of young silkworms serves as a crucial foundation for achieving precision rearing and high-quality breeding. Currently, manual counting remains the prevalent method for enumerating young silkworms, yet it is highly subjective. A dataset of young silkworm bodies has been constructed, and the Young Silkworm Counting (YSC) method has been proposed. This method combines an improved detector, incorporating an optimized multi-scale feature fusion module and the Efficient Multi-Scale Attention Fusion Cross Stage Partial (EMA-CSP) mechanism, with an optimized tracker (based on ByteTrack with improved detection box matching), alongside the implementation of a ‘detection line’ approach. The experimental results demonstrate that the recall, precision, and average precision (AP50:95) of the improved detection algorithm are 87.9%, 91.3% and 72.7%, respectively. Additionally, the enhanced ByteTrack method attains a multiple-object tracking accuracy (MOTA) of 88.3%, an IDF1 of 90.2%, and a higher-order tracking accuracy (HOTA) of 78.1%. Experimental validation demonstrates a counting accuracy exceeding 90%. The present study achieves precise counting of young silkworms in complex environments through an improved detection-tracking method combined with a detection line approach. Full article
(This article belongs to the Section Farm Animal Production)
Show Figures

Figure 1

19 pages, 3187 KiB  
Article
Development of an Automated Crack Detection System for Port Quay Walls Using a Small General-Purpose Drone and Orthophotos
by Daiki Komi, Daisuke Yoshida and Tomohito Kameyama
Sensors 2025, 25(14), 4325; https://doi.org/10.3390/s25144325 - 10 Jul 2025
Viewed by 343
Abstract
Aging port infrastructure demands frequent and reliable inspections, yet the existing automated systems often require expensive industrial drones, posing significant adoption barriers for local governments with limited resources. To address this challenge, this study develops a low-cost, automated crack detection system for port [...] Read more.
Aging port infrastructure demands frequent and reliable inspections, yet the existing automated systems often require expensive industrial drones, posing significant adoption barriers for local governments with limited resources. To address this challenge, this study develops a low-cost, automated crack detection system for port quay walls utilizing orthophotos generated from a small general-purpose drone. The system employs the YOLOR (You Only Learn One Representation) object detection algorithm, enhanced by two novel image processing techniques—overlapping tiling and pseudo-altitude slicing—to overcome the resolution limitations of low-cost cameras. While official guidelines for port facilities designate 3 mm as an inspection threshold, our system is specifically designed to achieve a higher-resolution detection capability for cracks as narrow as 1 mm. This approach ensures reliable detection with a sufficient safety margin and enables the proactive monitoring of crack progression for preventive maintenance. The effectiveness of the proposed image processing techniques was validated, with an F1 score-based analysis revealing key trade-offs between maximizing detection recall and achieving a balanced performance depending on the chosen simulated altitude. Furthermore, evaluation using real-world inspection data demonstrated that the proposed system achieves a detection performance comparable to that of a well-established commercial system, confirming its practical applicability. Crucially, by mapping the detected cracks to real-world coordinates on georeferenced orthophotos, the system provides a foundation for advanced, data-driven asset management, allowing for the quantitative tracking of deterioration over time. These results confirm that the proposed workflow is a practical and sustainable solution for infrastructure monitoring. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

15 pages, 1917 KiB  
Article
Home Range and Habitat Selection of Blue-Eared Pheasants Crossoptilon auritum During Breeding Season in Mountains of Southwest China
by Jinglin Peng, Xiaotong Shang, Fan Fan, Yong Zheng, Lianjun Zhao, Sheng Li, Yang Liu and Li Zhang
Animals 2025, 15(14), 2015; https://doi.org/10.3390/ani15142015 - 8 Jul 2025
Viewed by 281
Abstract
The blue-eared pheasant (Crossoptilon auritum), a Near Threatened (NT) species endemic to China, is primarily distributed across the northeastern region of the Qinghai–Tibetan Plateau. To bridge the fine-scale spatiotemporal gap in blue-eared pheasant behavioral ecology, this study combines satellite telemetry, movement [...] Read more.
The blue-eared pheasant (Crossoptilon auritum), a Near Threatened (NT) species endemic to China, is primarily distributed across the northeastern region of the Qinghai–Tibetan Plateau. To bridge the fine-scale spatiotemporal gap in blue-eared pheasant behavioral ecology, this study combines satellite telemetry, movement modeling, and field-based habitat assessments (vegetation, topography, human disturbance). This multidisciplinary approach reveals detailed patterns of their behavior throughout the breeding season. Using satellite-tracking data from six individuals (five males tracked at 4 h intervals; one female tracked hourly) in Wanglang National Nature Reserve (WLNNR), Sichuan Province during breeding seasons 2018–2019, we quantified their home ranges via Kernel Density Estimation (KDE) and examined the female movement patterns using a Hidden Markov Model (HMM). The results indicated male core (50% KDE: 21.93 ± 16.54 ha) and total (95% KDE: 158.30 ± 109.30 ha) home ranges, with spatial overlap among individuals but no significant temporal variation in home range size. Habitat selection analysis indicated that the blue-eared pheasants favored shrub-dominated areas at higher elevations (steep southeast-facing slopes), regions distant from human disturbance, and with abundant animal trails. We found that their movement patterns differed between sexes: the males exhibited higher daytime activity yet slower movement speeds, while the female remained predominantly near nests, making brief excursions before returning promptly. These results enhance our understanding of the movement ecology of blue-eared pheasants by revealing fine-scale breeding-season behaviors and habitat preferences through satellite-tracking. Such detailed insights provide an essential foundation for developing targeted conservation strategies, particularly regarding effective habitat management and zoning of human activities within the species’ range. Full article
(This article belongs to the Section Birds)
Show Figures

Graphical abstract

18 pages, 4805 KiB  
Article
Re-Usable Workflow for Collecting and Analyzing Open Data of Valenbisi
by Áron Magura, Marianna Zichar and Róbert Tóth
Electronics 2025, 14(13), 2720; https://doi.org/10.3390/electronics14132720 - 5 Jul 2025
Viewed by 392
Abstract
This paper proposes a general workflow for collecting and analyzing open data from Bicycle Sharing Systems (BSSs) that was developed using data from the Valenbisi system, operated in Valencia by the French company JCDecaux; however, the stages of the proposed workflow are service-independent [...] Read more.
This paper proposes a general workflow for collecting and analyzing open data from Bicycle Sharing Systems (BSSs) that was developed using data from the Valenbisi system, operated in Valencia by the French company JCDecaux; however, the stages of the proposed workflow are service-independent and can be applied broadly. Cycling has become an increasingly popular mode of transportation, leading to the emergence of BSSs in modern cities. Parallel to this, Smart City solutions have been implemented using Internet of Things (IoT) technologies, such as embedded sensors and GPS-based communication systems, which have become essential to everyday life. When public transportation services or bicycle sharing systems are used, real-time information about the services is provided to customers, including vehicle tracking based on GPS technology and the availability of bikes via sensors installed at bike rental stations. The bike stations were examined from two different perspectives: first, their daily usage, and second, the types of facilities located in their surroundings. Based on these two approaches, the overlap between the clustering results was analyzed—specifically, the similarity in how stations could be grouped and the correlation between their usage and locations. To enhance the raw data retrieved from the service provider’s official API, the stations were annotated based on OpenStreetMap and Overpass API data. Data visualization was created using Tableau from Salesforce. Based on the results, an agreement of 62% was found between the results of the two different clustering approaches. Full article
Show Figures

Figure 1

19 pages, 2567 KiB  
Article
Automated Video Quality Assessment for the Edinburgh Visual Gait Score (EVGS)
by Rajkumar Arumugam Jeeva, Edward D. Lemaire, Ramiro Olleac, Kevin Cheung, Albert Tu and Natalie Baddour
Methods Protoc. 2025, 8(4), 71; https://doi.org/10.3390/mps8040071 - 3 Jul 2025
Viewed by 242
Abstract
This research addresses critical challenges in clinical gait analysis by developing an automated video quality assessment framework to support Edinburgh Visual Gait Score (EVGS) scoring. The proposed methodology uses the MoveNet Lightning pose estimation model to extract body keypoints from video frames, enabling [...] Read more.
This research addresses critical challenges in clinical gait analysis by developing an automated video quality assessment framework to support Edinburgh Visual Gait Score (EVGS) scoring. The proposed methodology uses the MoveNet Lightning pose estimation model to extract body keypoints from video frames, enabling detection of multiple persons, tracking the person of interest, assessment of plane orientation, identification of overlapping individuals, detection of zoom artifacts, and evaluation of video resolution. These components are integrated into a unified quality classification system using a random forest classifier. The framework achieved high performance across key metrics, with 96% accuracy in detecting multiple persons, 95% in assessing overlaps, and 92% in identifying zoom events, culminating in an overall video quality categorization accuracy of 95%. This performance not only facilitates the automated selection of videos suitable for analysis but also provides specific video improvement suggestions when quality standards are not met. Consequently, the proposed system has the potential to streamline gait analysis workflows, reduce reliance on manual quality checks in clinical practice, and enable automated EVGS scoring by ensuring appropriate video quality as input to the gait scoring system. Full article
(This article belongs to the Section Biomedical Sciences and Physiology)
Show Figures

Figure 1

19 pages, 2267 KiB  
Article
Closed-Loop Aerial Tracking with Dynamic Detection-Tracking Coordination
by Yang Wang, Heqing Huang, Jiahao He, Dongting Han and Zhiwei Zhao
Drones 2025, 9(7), 467; https://doi.org/10.3390/drones9070467 - 30 Jun 2025
Viewed by 341
Abstract
Aerial tracking is an important service for many Unmanned Aerial Vehicle (UAV) applications. Existing work has failed to provide robust solutions when handling target disappearance, viewpoint changes, and tracking drifts in practical scenarios with limited UAV resources. In this paper, we propose a [...] Read more.
Aerial tracking is an important service for many Unmanned Aerial Vehicle (UAV) applications. Existing work has failed to provide robust solutions when handling target disappearance, viewpoint changes, and tracking drifts in practical scenarios with limited UAV resources. In this paper, we propose a closed-loop framework integrating three key components: (1) a lightweight adaptive detection with multi-scale feature extraction, (2) spatiotemporal motion modeling through Kalman-filter-based trajectory prediction, and (3) autonomous decision-making through composite scoring of detection confidence, appearance similarity, and motion consistency. By implementing dynamic detection-tracking coordination with quality-aware feature preservation, our system enables real-time operation through performance-adaptive frequency modulation. Evaluated on VOT-ST2019 and OTB100 benchmarks, the proposed method yields marked improvements over baseline trackers, achieving a 27.94% increase in Expected Average Overlap (EAO) and a 10.39% reduction in failure rates, while sustaining a frame rate of 23–95 FPS on edge hardware. The framework achieves rapid target reacquisition during prolonged occlusion scenarios through optimized protocols, outperforming conventional methods in sustained aerial surveillance tasks. Full article
(This article belongs to the Section Drone Design and Development)
Show Figures

Figure 1

16 pages, 264 KiB  
Review
Heart Rate Variability (HRV) in Patients with Sleep Apnea and COPD: A Comprehensive Analysis
by Andreea Zabara-Antal, Radu Crisan-Dabija, Raluca-Ioana Arcana, Oana Elena Melinte, Adriana-Loredana Pintilie, Ionela Alina Grosu-Creanga, Mihai Lucian Zabara and Antigona Trofor
J. Clin. Med. 2025, 14(13), 4630; https://doi.org/10.3390/jcm14134630 - 30 Jun 2025
Viewed by 751
Abstract
Background: Obstructive sleep apnea (OSA) and chronic obstructive pulmonary disease (COPD) are prevalent conditions with overlapping clinical features and shared consequences on autonomic function. Heart rate variability (HRV), a non-invasive biomarker of autonomic nervous system activity, may offer diagnostic, prognostic, and therapeutic insights [...] Read more.
Background: Obstructive sleep apnea (OSA) and chronic obstructive pulmonary disease (COPD) are prevalent conditions with overlapping clinical features and shared consequences on autonomic function. Heart rate variability (HRV), a non-invasive biomarker of autonomic nervous system activity, may offer diagnostic, prognostic, and therapeutic insights in this patient population. Methods: A comprehensive literature review was conducted using PubMed, Google Scholar, and MEDLINE to identify peer-reviewed English-language studies published between January 2015 and December 2024. Studies were included if they evaluated HRV parameters in individuals with OSA, COPD, or overlap syndrome, explored HRV as a marker of disease severity or progression. A total of 239 studies were identified; after screening, 41 met the inclusion criteria. Results: The analysis revealed consistent evidence linking reduced HRV with both OSA and COPD severity. HRV alterations were more pronounced in overlap syndrome, reflecting synergistic autonomic dysfunction. HRV showed potential in differentiating disease stages, predicting cardiovascular risk, and evaluating treatment efficacy, particularly for CPAP therapy in OSA. Short-term HRV was particularly sensitive to autonomic changes, while long-term recordings helped track disease progression. Emerging evidence supports the use of HRV derived from wearable technologies as a viable screening tool for health and wellness. Conclusion: HRV is a valuable, non-invasive tool for assessing autonomic dysfunction in OSA, COPD, and their overlap. It offers significant potential for early diagnosis, disease monitoring, and treatment evaluation. Integrating HRV into clinical practice, could enhance diagnostic efficiency, reduce healthcare burden, and improve outcomes in high-risk respiratory populations. Furthermore, longitudinal studies are warranted to standardise HRV thresholds and validate their use in routine screening protocols. Full article
(This article belongs to the Special Issue Clinical Highlights in Chronic Obstructive Pulmonary Disease (COPD))
20 pages, 4060 KiB  
Article
Tomato Yield Estimation Using an Improved Lightweight YOLO11n Network and an Optimized Region Tracking-Counting Method
by Aichen Wang, Yuanzhi Xu, Dong Hu, Liyuan Zhang, Ao Li, Qingzhen Zhu and Jizhan Liu
Agriculture 2025, 15(13), 1353; https://doi.org/10.3390/agriculture15131353 - 25 Jun 2025
Cited by 1 | Viewed by 385
Abstract
Accurate and effective fruit tracking and counting are crucial for estimating tomato yield. In complex field environments, occlusion and overlap of tomato fruits and leaves often lead to inaccurate counting. To address these issues, this study proposed an improved lightweight YOLO11n network and [...] Read more.
Accurate and effective fruit tracking and counting are crucial for estimating tomato yield. In complex field environments, occlusion and overlap of tomato fruits and leaves often lead to inaccurate counting. To address these issues, this study proposed an improved lightweight YOLO11n network and an optimized region tracking-counting method, which estimates the quantity of tomatoes at different maturity stages. An improved lightweight YOLO11n network was employed for tomato detection and semantic segmentation, which was combined with the C3k2-F, Generalized Intersection over Union (GIoU), and Depthwise Separable Convolution (DSConv) modules. The improved lightweight YOLO11n model is adaptable to edge computing devices, enabling tomato yield estimation while maintaining high detection accuracy. An optimized region tracking-counting method was proposed, combining target tracking and region detection to count the detected fruits. The particle swarm optimization (PSO) algorithm was used to optimize the detection region, thus enhancing the counting accuracy. In terms of network lightweighting, compared to the original, the improved YOLO11n network significantly reduces the number of parameters and Giga Floating-point Operations Per Second (GFLOPs) by 0.22 M and 2.5 G, while achieving detection and segmentation accuracies of 91.3% and 90.5%, respectively. For fruit counting, the results showed that the proposed region tracking-counting method achieved a mean counting error (MCE) of 6.6%, representing a reduction of 5.0% and 2.1% compared to the Bytetrack and cross-line counting methods, respectively. Therefore, the proposed method provided an effective approach for non-contact, accurate, efficient, and real-time intelligent yield estimation for tomatoes. Full article
Show Figures

Figure 1

14 pages, 878 KiB  
Article
Multi-Instance Multi-Scale Graph Attention Neural Net with Label Semantic Embeddings for Instrument Recognition
by Na Bai, Zhaoli Wu and Jian Zhang
Signals 2025, 6(3), 30; https://doi.org/10.3390/signals6030030 - 24 Jun 2025
Viewed by 287
Abstract
Instrument recognition is a crucial aspect of music information retrieval, and in recent years, machine learning-based methods have become the primary approach to addressing this challenge. However, existing models often struggle to accurately identify multiple instruments within music tracks that vary in length [...] Read more.
Instrument recognition is a crucial aspect of music information retrieval, and in recent years, machine learning-based methods have become the primary approach to addressing this challenge. However, existing models often struggle to accurately identify multiple instruments within music tracks that vary in length and quality. One key issue is that the instruments of interest may not appear in every clip of the audio sample, and when they do, they are often unevenly distributed across different sections of the track. Additionally, in polyphonic music, multiple instruments are often played simultaneously, leading to signal overlap. Using the same overlapping audio signals as partial classification features for different instruments will reduce the distinguishability of features between instruments, thereby affecting the performance of instrument recognition. These complexities present significant challenges for current instrument recognition models. Therefore, this paper proposes a multi-instance multi-scale graph attention neural network (MMGAT) with label semantic embeddings for instrument recognition. MMGAT designs an instance correlation graph to model the presence and quantitative timbre similarity of instruments at different positions from the perspective of multi-instance learning. Then, to enhance the distinguishability of signals after the overlap of different instruments and improve classification accuracy, MMGAT learns semantic information from the labels of different instruments as embeddings and incorporates them into the overlapping audio signal features, thereby enhancing the differentiability of audio features for various instruments. MMGAT then designs an instance-based multi-instance multi-scale graph attention neural network to recognize different instruments based on the instance correlation graphs and label semantic embeddings. The effectiveness of MMGAT is validated through experiments and compared to commonly used instrument recognition models. The experimental results demonstrate that MMGAT outperforms existing approaches in instrument recognition tasks. Full article
Show Figures

Figure 1

15 pages, 3542 KiB  
Article
Longitudinal Overlap and Metabolite Analysis in Spectroscopic MRI-Guided Proton Beam Therapy in Pediatric High-Grade Glioma
by Abinand C. Rejimon, Anuradha G. Trivedi, Vicki Huang, Karthik K. Ramesh, Natia Esiashvilli, Eduard Schreibmann, Hyunsuk Shim, Kartik Reddy and Bree R. Eaton
Tomography 2025, 11(6), 71; https://doi.org/10.3390/tomography11060071 - 19 Jun 2025
Viewed by 433
Abstract
Background: Pediatric high-grade glioma (pHGG) is a highly aggressive cancer with unique biology distinct from adult high-grade glioma, limiting the effectiveness of standard treatment protocols derived from adult research. Objective: The purpose of this report is to present preliminary results from an ongoing [...] Read more.
Background: Pediatric high-grade glioma (pHGG) is a highly aggressive cancer with unique biology distinct from adult high-grade glioma, limiting the effectiveness of standard treatment protocols derived from adult research. Objective: The purpose of this report is to present preliminary results from an ongoing pilot study integrating spectroscopic magnetic resonance imaging (sMRI) to guide proton beam therapy and longitudinal imaging analysis in pediatric patients with high-grade glioma (pHGG). Methods: Thirteen pediatric patients under 21 years old with supratentorial WHO grade III-IV glioma underwent baseline and serial whole-brain spectroscopic MRI alongside standard structural MRIs. Radiation targets were defined using T1-weighted contrast enhanced, T2-FLAIR, and Cho/NAA ≥ 2X maps. Longitudinal analyses included voxel-level metabolic change maps and spatial overlap metrics comparing pre-proton therapy and post-. Results: Six patients had sufficient longitudinal data; five received sMRI-guided PBT. Significant positive correlation (R2 = 0.89, p < 0.0001) was observed between T2-FLAIR and Cho/NAA ≥ 2X volumes. Voxel-level difference maps of Cho/NAA and Choline revealed dynamic metabolic changes across follow-up scans. Analyzing Cho/NAA and Cho changes over time allowed differentiation between true progression and pseudoprogression, which conventional MRI alone struggles to achieve. Conclusions: Longitudinal sMRI enhanced metabolic tracking in pHGG, detects early tumor changes, and refines RT targeting beyond structural imaging. This first in-kind study highlights the potential of sMRI biomarkers in tracking treatment effects and emphasizes the complementary roles of metabolic and radiographic metrics in evaluating therapy response in pHGG. Full article
(This article belongs to the Section Cancer Imaging)
Show Figures

Figure 1

26 pages, 11841 KiB  
Article
Automatic Extraction of Road Interchange Networks from Crowdsourced Trajectory Data: A Forward and Reverse Tracking Approach
by Fengwei Jiao, Longgang Xiang and Yuanyuan Deng
ISPRS Int. J. Geo-Inf. 2025, 14(6), 234; https://doi.org/10.3390/ijgi14060234 - 17 Jun 2025
Viewed by 737
Abstract
The generation of road interchange networks benefits various applications, such as vehicle navigation and intelligent transportation systems. Traditional methods often focus on common road structures but fail to fully utilize long-term trajectory continuity and flow information, leading to fragmented results and misidentification of [...] Read more.
The generation of road interchange networks benefits various applications, such as vehicle navigation and intelligent transportation systems. Traditional methods often focus on common road structures but fail to fully utilize long-term trajectory continuity and flow information, leading to fragmented results and misidentification of overlapping roads as intersections. To address these limitations, we propose a forward and reverse tracking method for high-accuracy road interchange network generation. First, raw crowdsourced trajectory data is preprocessed by filtering out non-interchange trajectories and removing abnormal data based on both static and dynamic characteristics of the trajectories. Next, road subgraphs are extracted by identifying potential transition nodes, which are verified using directional and distribution information. Trajectory bifurcation is then performed at these nodes. Finally, a two-stage fusion process combines forward and reverse tracking results to produce a geometrically complete and topologically accurate road interchange network. Experiments using crowdsourced trajectory data from Shenzhen demonstrated highly accurate results, with 95.26% precision in geometric road network alignment and 90.06% accuracy in representing the connectivity of road interchange structures. Compared to existing methods, our approach enhanced accuracy in spatial alignment by 13.3% and improved the correctness of structural connections by 12.1%. The approach demonstrates strong performance across different types of interchanges, including cloverleaf, turbo, and trumpet interchanges. Full article
Show Figures

Figure 1

25 pages, 10815 KiB  
Article
Enhancing Heart Disease Diagnosis Using ECG Signal Reconstruction and Deep Transfer Learning Classification with Optional SVM Integration
by Mostafa Ahmad, Ali Ahmed, Hasan Hashim, Mohammed Farsi and Nader Mahmoud
Diagnostics 2025, 15(12), 1501; https://doi.org/10.3390/diagnostics15121501 - 13 Jun 2025
Viewed by 859
Abstract
Background/Objectives: Accurate and efficient diagnosis of heart disease through electrocardiogram (ECG) analysis remains a critical challenge in clinical practice due to noise interference, morphological variability, and the complexity of overlapping cardiac signals. Methods: This study presents a comprehensive deep learning (DL) framework [...] Read more.
Background/Objectives: Accurate and efficient diagnosis of heart disease through electrocardiogram (ECG) analysis remains a critical challenge in clinical practice due to noise interference, morphological variability, and the complexity of overlapping cardiac signals. Methods: This study presents a comprehensive deep learning (DL) framework that integrates advanced ECG signal segmentation with transfer learning-based classification, aimed at improving diagnostic performance. The proposed ECG segmentation algorithm introduces a distinct and original approach compared to prior research by integrating adaptive preprocessing, histogram-based lead separation, and robust point-tracking techniques into a unified framework. While most earlier studies have addressed ECG image processing using basic filtering, fixed-region cropping, or template matching, our method uniquely focuses on automated and precise reconstruction of individual ECG leads from noisy and overlapping multi-lead images—a challenge often overlooked in previous work. This innovative segmentation strategy significantly enhances signal clarity and enables the extraction of richer and more localized features, boosting the performance of DL classifiers. The dataset utilized in this work of 12 lead-based standard ECG images consists of four primary classes. Results: Experiments conducted using various DL models—such as VGG16, VGG19, ResNet50, InceptionNetV2, and GoogleNet—reveal that segmentation notably enhances model performance in terms of recall, precision, and F1 score. The hybrid VGG19 + SVM model achieved 98.01% and 100% accuracy in multi-class classification, along with average accuracies of 99% and 97.95% in binary classification tasks using the original and reconstructed datasets, respectively. Conclusions: The results highlight the superiority of deep, feature-rich models in handling reconstructed ECG signals and confirm the value of segmentation as a critical preprocessing step. These findings underscore the importance of effective ECG segmentation in DL applications for automated heart disease diagnosis, offering a more reliable and accurate solution. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
Show Figures

Figure 1

Back to TopTop