Search Results (123)

Unmanned aerial vehicles (UAVs) are widely used in surveillance and combat for their efficiency and autonomy, whilst complex, dynamic environments challenge the modeling of inter-agent relations and information transmission. This research proposes a novel UAV tactical choice-making algorithm utilizing graph neural networks to tackle these challenges. The proposed algorithm employs a graph neural network to process the observed state information, the convolved output of which is then fed into a reconstructed critic network incorporating a Laplacian convolution kernel. This research first enhances the accuracy of obtaining unstable state information in hostile environments. The proposed algorithm uses this information to train a more precise critic network. In turn, this improved critic network guides the actor network to make decisions that better meet the needs of the battlefield. Coupled with a policy transfer mechanism, this architecture significantly enhances the decision-making efficiency and environmental adaptability within the multi-agent system. Results from the experiments show that the average effectiveness of the proposed algorithm across the six planned scenarios is 97.4%, surpassing the baseline by 23.4%. In addition, the integration of transfer learning makes the network convergence speed three times faster than that of the baseline algorithm. This algorithm effectively improves the information transmission efficiency between the environment and the UAV and provides strong support for UAV formation combat. Full article

Massive relief supplies inter-regional lateral transshipment (MRSIRLT) can significantly enhance the efficiency of disaster response, meet the needs of affected areas (AAs), and reduce deprivation costs. This paper develops an integrated allocation and intermodality optimization model (AIOM) to address the MRSIRLT challenge. A phased interactive framework incorporating adaptive differential evolution (JADE) and improved adaptive large neighborhood search (IALNS) is designed. Specifically, JADE is employed in the first stage to allocate the volume of massive relief supplies, aiming to minimize deprivation costs, while IALNS optimizes intermodal routing in the second stage to minimize the weighted sum of transportation time and cost. A case study based on a typhoon disaster in the Chinese region of Bohai Rim demonstrates and verifies the effectiveness and applicability of the proposed model and algorithm. The results and sensitivity analysis indicate that reducing loading and unloading times and improving transshipment efficiency can effectively decrease transfer time. Additionally, the weights assigned to total transfer time and costs can be balanced depending on demand satisfaction levels. Full article

Background: Large language models (LLMs) like ChatGPT are increasingly being explored for medical applications. However, their reliability in providing medication advice for patients with complex clinical situations, particularly those with multiple comorbidities, remains uncertain and under-investigated. This study aimed to systematically evaluate the performance, consistency, and safety of ChatGPT in generating medication recommendations for complex cardiovascular disease (CVD) scenarios. Methods: In this simulation-based study (21 January–1 February 2024), ChatGPT 3.5 and 4.0 were prompted 10 times for each of 25 scenarios, representing five common CVDs paired with five major comorbidities. A panel of five cardiologists independently classified each unique drug recommendation as “high priority” or “low priority”. Key metrics included physician approval rates, the proportion of high-priority recommendations, response consistency (Jaccard similarity index), and error pattern analysis. Statistical comparisons were made using Z-tests, chi-square tests, and Wilcoxon Signed-Rank tests. Results: The overall physician approval rate for GPT-4 (86.90%) was modestly but significantly higher than that for GPT-3.5 (85.06%; p = 0.0476) based on aggregated data. However, a more rigorous paired-scenario analysis of high-priority recommendations revealed no statistically significant difference between the models (p = 0.407), indicating the advantage is not systematic. A chi-square test confirmed significant differences in error patterns (p < 0.001); notably, GPT-4 more frequently recommended contraindicated drugs in high-risk scenarios. Inter-model consistency was low (mean Jaccard index = 0.42), showing the models often provide different advice. Conclusions: While demonstrating high overall physician approval rates, current LLMs exhibit inconsistent performance and pose significant safety risks when providing medication advice for complex CVD cases. Their reliability does not yet meet the standards for autonomous clinical application. Future work must focus on leveraging real-world data for validation and developing domain-specific, fine-tuned models to enhance safety and accuracy. Until then, vigilant professional oversight is indispensable. Full article

Traffic congestion constitutes a substantial global issue, adversely impacting economic productivity and quality of life, with associated costs estimated at approximately 2% of GDP in various nations. This systematic review investigates the application of machine learning (ML) in traffic congestion forecasting from 2010 to 2024, adhering to the PRISMA 2020 guidelines. A comprehensive search of three major databases (IEEE Xplore, SpringerLink, and ScienceDirect) yielded 9695 initial records, with 115 studies meeting the inclusion criteria following rigorous screening. Data extraction encompassed methodological approaches, ML techniques, traffic characteristics, and forecasting periods, with quality assessment achieving near-perfect inter-rater reliability (Cohen’s $\kappa$ = 0.89). Deep Neural Networks were the predominant technical approach (47%), with supervised learning being the most prevalent (57%). Classification tasks were the most common (42%), primarily addressing recurrent congestion scenarios (76%) and passenger vehicles (90%). The quality of publications was notably high, with 85% appearing in Q1-ranked journals, demonstrating exponential growth from minimal activity in 2010 to 18 studies in 2022. Significant research gaps persist: reinforcement learning is underutilized (8%), rural road networks are underrepresented (2%), and industry–academia collaboration is limited (3%). Future research should prioritize multimodal transportation systems, real-time adaptation mechanisms, and enhanced practical implementation to advance intelligent transportation systems (ITSs). This review was not registered because it focused on mapping the research landscape rather than intervention effects. Full article

As the primary electronic payload of laser interferometry system for space gravitational wave detection, the core function of the phasemeter is ultra-high precision phase measurement. According to the principle of laser heterodyne interferometry and the requirement of 1 pm ranging accuracy of the phasemeter, the phase measurement noise should reach 2π μrad/Hz^1/2@(0.1 mHz–1 Hz). The heterodyne interference signal first passes through the quadrant photoelectric detector (QPD) to achieve photoelectric conversion, then passes through the analog-to-digital converter (ADC) to achieve analog and digital conversion, and finally passes through the digital phase-locked loop (DPLL) for phase locking. The sampling timing jitter of the heterodyne interference signal caused by the ADC is the main noise affecting the phase measurement performance and must be suppressed. This paper proposes a sampling timing jitter noise suppression system (STJNSS), which can set system parameters for high-frequency signals used for inter-satellite clock noise transmission, the system clock of the phasemeter, and the pilot frequency for suppressing ADC sampling timing jitter noise, meeting the needs of the current major space gravitational wave detection plans. The experimental results after the integration of SJNSS and the phase meter show that the phase measurement noise of the heterodyne interferometer signal reaches 2π μrad/Hz^1/2@(0.1 mHz–1 Hz), which meets the requirements of space gravitational wave missions. Full article

Hypertension and blood pressure variability (BPV) are major risk factors for cardiovascular disease (CVD). Single-channel photoplethysmography (PPG) has emerged as a promising daily blood pressure (BP) monitoring tool. However, estimating BP trends presents challenges due to complex temporal dependencies and continuous fluctuations. Traditional methods often address BP prediction as isolated tasks and focus solely on temporal dependencies within a limited time window, which may fall short of capturing the intricate BP fluctuation patterns implied in varying time spans, particularly amidst constant BP variations. To address this, we propose a novel deep learning model featuring a two-stage architecture and a new input structure called contextual cycles. This model estimates beat-to-beat systolic blood pressure (SBP) trends as a sequence prediction task, transforming the output from a single SBP value into a sequence. In the first stage, parallel ResU Blocks are utilized to extract fine-grained features from each cycle. The generated feature vectors are then processed by Transformer layers with relative position encoding (RPE) to capture inter-cycle interactions and temporal dependencies in the second stage. Our proposed model demonstrates robust performance in beat-to-beat SBP trend estimation, achieving a mean absolute error (MAE) of 3.186 mmHg, a Pearson correlation coefficient applied to sequences (${\mathrm{R}}_{\mathrm{seq}}$) of 0.743, and a variability error (VE) of 1.199 mmHg. It excels in steady and abrupt substantial fluctuation states, outperforming baseline models. The results reveal that our method meets the requirements of the AAMI standard and achieves grade A according to the BHS standard. Overall, our proposed method shows significant potential for reliable daily health monitoring. Full article

To meet the urgent need for high-precision ranging and large-capacity transmission in the current BeiDou-3 inter-satellite link system, this paper proposes a novel two-way measurement method based on Co-frequency Co-time Full Duplex (CCFD) system. This approach effectively addresses the limitations of traditional Time-Division Half-Duplex (TDHD) systems, such as complex link establishment processes, constrained ranging accuracy, and limited transmission efficiency. Based on the spatial configuration of the BeiDou-3 satellite navigation constellation, a dynamic link constraint model is constructed, and a comprehensive link budget analysis is conducted for the entire inter-satellite measurement process. The fundamental principle, system model, and key errors of the two-way measurement in CCFD are derived in detail. Theoretical analysis and experimental simulations demonstrate that the proposed CCFD system is feasible and achieves remarkable ranging accuracy improvements. At a carrier-to-noise ratio of 61.6 dBHz, the system attains 1σ ranging accuracy of 1.9 cm, representing a 51.3% enhancement over the 3.9 cm accuracy of the TDHD system. When operating at 69.3 dBHz, the precision further improves to 0.8 cm, outperforming TDHD’s 2.2 cm by 66.8%. The introduction of CCFD technology can significantly enhance the performance level of the BeiDou-3 satellite navigation system, demonstrating broad application prospects for the future. Full article

Multi-floored grain warehouses are widely used in China due to their efficient space utilization and high storage capacity. This study evaluates the seismic performance of such structures using a Composite Structure of Steel and Concrete (CSSC) system under various grain-loading conditions. A finite element model was developed in OpenSees based on actual loading scenarios, with both pushover and time history analyses conducted. Results show that the EEF condition (E = Empty, F = Full; top–middle–bottom = Empty–Empty–Full) leads to a 35.14% increase in peak base shear compared to the FEE condition (grain on the top floor only). Capacity spectrum analysis indicates that EEF provides higher initial stiffness and lower displacement across all performance points. Time history results reveal that configurations with lighter upper mass (EFF, EEE) are more prone to top-floor acceleration amplification, while FFF and FFE demonstrate more stable responses due to balanced mass distribution. The maximum inter-story drift consistently occurs at the second floor, with FFF and FFE showing the most significant deformation. All drift ratios meet code limits, confirming the safety and applicability of the CSSC system under various storage scenarios. Full article

Background and Objectives: Alzheimer’s disease (AD) is a progressive neurodegenerative condition that significantly affects cognitive, emotional, and functional abilities in older adults. This study aimed to explore how demographic, clinical, and psychological factors influence the progression of cognitive decline in patients diagnosed with AD. Materials and Methods: A total of 101 patients were evaluated retrospectively and followed longitudinally at three different time points, using standardized instruments, including the MMSE, Reisberg’s GDS, clock-drawing test, MADRS, and Hamilton depression scale. Statistical methods included non-parametric tests, mixed-effect modeling, and Bayesian analysis. Results: Most patients were older women from rural areas, predominantly in moderate-to-severe stages of AD. Age showed a significant association with cognitive decline (p < 0.05), and depression—particularly in moderate and severe forms—was strongly linked to lower MMSE scores (p < 0.001). Over 70% of the participants had some degree of depression. The clock-drawing test highlighted visuospatial impairments, consistent with everyday functional loss. Although donepezil and memantine combinations appeared to be more frequently prescribed, no treatment showed a statistically significant advantage, and confidence interval overlaps suggest caution in interpreting differences between therapies. Longitudinal models confirmed a progressive and accelerated decline, with inter-individual variability becoming more pronounced in later stages. Although comorbidities, such as hypertension and diabetes, were frequent, they did not show a statistically significant effect on MMSE scores in this cohort. Conclusions: Age and depression appear to play central roles in the pace of cognitive deterioration in AD. Given the limited efficacy of most current therapies, these findings highlight the need for earlier intervention and a more personalized, integrated approach—combining cognitive care, psychiatric support, and comorbidity management—to better meet the needs of patients with AD. Full article

Traditional intellectual property authentication relies on centralized intermediaries, which makes it difficult to address issues such as forgery, lack of trust, and opaque information. Combined with the characteristics of blockchain, such as decentralization, tampering, and traceability, these challenges can be effectively dealt with. Aiming at the shortcomings of traditional consensus algorithms in intellectual property authentication, such as high communication overhead and low efficiency, the improved PBFT (Practical Byzantine Fault Tolerance) algorithm (MBFT algorithm) is proposed and combined with the distributed database IPFS (Inter Planetary File System) to alleviate the pressure of blockchain data storage and enhance operational efficiency. The algorithm first adopts the evaluation system in the hierarchical mechanism, invokes the Fibonacci series incremental law to update the Score value of the nodes and sort them, and divides the nodes into the classification consensus layer, the consensus confirmation layer, and the supervision layer. Secondly, the Maglev algorithm is used to generate a lookup table and design a classification consensus strategy, which is divided into four consensus groups based on the characteristics of intellectual property categories, namely, the patent authentication consensus group, the trademark authentication consensus group, the copyright authentication consensus group, and the other types of authentication consensus group. Then, the algorithm optimizes the consistency protocol, carries out PBFT consensus once in each of the classification consensus layers and consensus confirmation layers, according to the consensus situation, and realizes the nodes’ dynamic update to ensure the consensus’s accuracy and reliability. The experiments show that the MBFT algorithm performs better in terms of communication complexity and throughput. As the number and size of files increase, the execution time of IPFS progressively lengthens. However, the overall performance still meets the actual demand. Compared with the traditional PBFT, MBFT improves the communication complexity by about 50% or more, the throughput is about 3 times the traditional PBFT, and the scalability and response speed of the system are significantly improved when the number of nodes increases. Full article

Traditional spacecraft orbit determination primarily employs two methodologies: ground station/survey ship-based orbit determination and global navigation satellite system (GNSS)-based orbit determination. The ground tracking measurement system, reliant on multiple tracking stations or ships, presents a less favorable efficiency-to-cost ratio. For high-orbit satellites, GNSS orbit determination is hindered by a limited number of receivable satellites, weak signal strength and suboptimal geometric configurations, thereby failing to meet the demands for the continuous, high-precision orbit measurement of overseas high-orbit satellites. Satellite navigation systems, characterized by global coverage and Ka-band inter-satellite links, offer measurement and communication services to extended users, such as satellites, aircraft, space stations and other spacecraft. With the widespread adoption of navigation satellite systems, particularly in scenarios where ground tracking, telemetry and command (TT&C) stations are out of sight, there is a growing demand among users for Ka-band inter-satellite links for high-precision ranging and orbit determination. This paper introduces an innovative unidirectional orbit-determination technology for extended users, leveraging the navigation Ka-band inter-satellite link. When extended users are constrained by weight and power consumption limitations, preventing the incorporation of high-precision atomic clocks, they utilize their extensive capture capability to conduct distance measurements between navigation satellites. This process involves constructing clock error models, calculating clock error parameters and compensating for these errors, thereby achieving high-precision time–frequency synchronization and bidirectional communication. The technology has enhanced the time and frequency accuracies by three and two orders of magnitude, respectively. Following the establishment of bidirectional communication, unidirectional ranging values are collected daily for one hour. Utilizing these bidirectional ranging values, a mechanical model and state-transfer matrix are established, resulting in orbit-determination calculations with an accuracy of less than 100 m. This approach addresses the challenge of high-precision time–frequency synchronization and orbit determination for users without atomic clocks, utilizing minimal inter-satellite link time slot resources. For the first time in China, extended users can access the navigation inter-satellite link with a minimal allocation of time slot resources, achieving orbit determination at the 100 m level. This advancement significantly enhances the robustness of extended users and provides substantial technical support for various extended users to employ the Ka inter-satellite link for emergency communication and orbit determination. Full article

Background/Objectives: In the burgeoning field of medical imaging and Artificial Intelligence (AI), high-quality annotations for training AI-models are crucial. However, there are still only a few large datasets, as segmentation is time-consuming, experts have limited time. This study investigates how the experience of radiologists affects the quality of annotations. Methods: We randomly collected 53 anonymized chest radiographs. Fifteen readers with varying levels of expertise annotated the anatomical structures of different complexity, pneumonic opacities and central venous catheters (CVC) as examples of pathologies and foreign material. The readers were divided into three groups of five. The groups consisted of medical students (MS), junior professionals (JP) with less than five years of working experience and senior professionals (SP) with more than five years of experience. Each annotation was compared to a gold standard consisting of a consensus annotation of three senior board-certified radiologists. We calculated the Dice coefficient (DSC) and Hausdorff distance (HD) to evaluate annotation quality. Inter- and intrareader variability and time dependencies were investigated using Intraclass Correlation Coefficient (ICC) and Ordinary Least Squares (OLS). Results: Senior professionals generally showed better performance, while medical students had higher variability in their annotations. Significant differences were noted, especially for complex structures (DSC Pneumonic Opacities as mean [standard deviation]: MS: 0.516 [0.246]; SP: 0.631 [0.211]). However, it should be noted that overall deviation and intraclass variance was higher for these structures even for seniors, highlighting the inherent limitations of conventional radiography. Experience showed a positive relationship with annotation quality for VCS and lung but was not a significant factor for other structures. Conclusions: Experience level significantly impacts annotation quality. Senior radiologists provided higher-quality annotations for complex structures, while less experienced readers could still annotate simpler structures with satisfying accuracy. We suggest a mixed-expertise approach, enabling the highly experienced to utilize their knowledge most effectively. With the increase in numbers of examinations, radiology will rely on AI support tools in the future. Therefore, economizing the process of data acquisition and AI-training; for example, by integrating less experienced radiologists, will help to meet the coming challenges. Full article

Terrestrial and satellite communications, tactical data links, positioning, navigation, and timing (PNT), as well as distributed sensing will continue to require precise timing and the ability to synchronize and disseminate time effectively. However, the supply of space-qualified clocks that meet Global Navigation Satellite Systems (GNSS)-level performance standards is limited. As the awareness of potential disruptions to GNSS due to adversarial actions grows, the current reliance on GNSS-level timing appears costly and outdated. This is especially relevant given the benefits of developing robust and stable time scale references in orbit, especially as various alternatives to GNSS are being explored. The onboard realization of clock ensembles is particularly promising for applications such as those providing the on-demand dissemination of a reference time scale for navigation services via a proliferated Low-Earth Orbit (pLEO) constellation. This article investigates potential inter-satellite network architectures for coordinating time and frequency across pLEO platforms. These architectures dynamically allocate radio resources for clock data transport based on the requirements for pLEO time scale formations. Additionally, this work proposes a model-based control system for wireless networked timekeeping systems. It envisions the optimal placement of critical information concerning the implicit ensemble mean (IEM) estimation across a multi-platform clock ensemble, which can offer better stability than relying on any single ensemble member. This approach aims to reduce data traffic flexibly. By making the IEM estimation sensor more intelligent and running it on the anchor platform while also optimizing the steering of remote frequency standards on participating platforms, the networked control system can better predict the future behavior of local reference clocks paired with low-noise oscillators. This system would then send precise IEM estimation information at critical moments to ensure a common pLEO time scale is realized across all participating platforms. Clock steering is essential for establishing these time scales, and the effectiveness of the realization depends on the selected control intervals and steering techniques. To enhance performance reliability beyond what the existing Linear Quadratic Gaussian (LQG) control technique can provide, the minimal-cost-variance (MCV) control theory is proposed for clock steering operations. The steering process enabled by the MCV control technique significantly impacts the overall performance reliability of the time scale, which is generated by the onboard ensemble of compact, lightweight, and low-power clocks. This is achieved by minimizing the variance of the chi-squared random performance of LQG control while maintaining a constraint on its mean. Full article

Acoustic monitoring facilitates the detailed study of herbivore grazing by generating a timeline of sound bursts associated with jaw movements (JMs) that perform bite or chew actions. The unclassified stream of JM events was used here in an observational study to explore the notion of “grazing time”. Working with shepherded goat herds in a wooded landscape, a horn-based acoustic sensor with a vibration-type microphone was deployed on a volunteer animal along each of 12 foraging routes. The software-generated timeline of unclassified JMs contained a total of 334,582 events. After excluding rumination bouts, minutely JM rates showed a broad, non-normal distribution, with an overall mean of 61 JM min⁻¹. The frequency distribution of inter-JM interval values scaled logarithmically, with a peak in the region of 0.43 s representing a baseline interval that generates the unconstrained, more-or-less regular, rhythm of jaw movement (≈140 JM min⁻¹). This rhythm was punctuated by interruptions, for which duration scaled logarithmically, and which were primarily related to the search phase of the intake process. The empirical time accumulation curve shows the contribution of the inter-JM interval to the total foraging time and provides a penetrating profile of how the animal interacted with the foraging environment. The sum total of time along a foraging route spent at a near-potential JM rate was only ≈1 h, whereas sub-potential rates containing intervals as long as ≈30 s accounted for the bulk of the foraging route. The dimensionless behavioral grazing intensity was defined as the product of the number of ingestive JMs performed and the baseline interval, divided by the duration of the foraging route (excluding rumination). Values were mostly <0.5 for the foraging routes examined. This has implications for how animal presence should be translated to grazing pressure and for how long animals need to forage to meet their nutritional requirements. Full article

Aimed at the problem of the difference between intra-class and inter-class pathogenic spores of Wheat Scab image being small and difficult to distinguish, in this paper, we propose a lightweight decoupled Wheat Scab spore detection network based on Yolov7-tiny (GSD-YOLO). Specifically, considering the limitations of the storage space and power consumption of actual field detection equipment, the original detection head is optimized as a decoupled head, and the GSConv lightweight module is embedded to reduce the parameters of the model and the number of calculations required. In addition, we utilize an improved Spore–Copy data augmentation strategy to improve the detection performance and generalization ability of the algorithm to fit the large numbers, morphology, and variety of wheat disease spores in the actual field and to improve the efficiency of constructing a large data set of diverse spores. The experimental results show that the mAP of the proposed algorithm reaches 98.0%, which is 3.9 percentage points higher than that of the original model. At the same time, the detection speed of the algorithm is 114 f/s, and the memory is 13.1 MB, which meets the application requirements of hardware deployment and real-time detection. It can provide some technical support to the prevention and grading of Wheat Scab in actual farmland. Full article