Search Results (41)

For a given timetable in urban rail transit systems, this paper presents a practical energy efficiency optimization problem that carries out adjustments to the timetable, with the goal of energy saving. We propose two strategies to address this challenge, including adjusting the section running time by selecting a speed profile and improving the utilization of regenerative braking energy by adjusting the trains’ departure time. Constraints on the range of adjustment for energy-efficient time elements are constructed for maintaining the stability of elements of the given timetable. An energy efficiency optimization model is then established to minimize the total net energy consumption of the timetable, and a solution algorithm based on a genetic algorithm is proposed. We make small-scale adjustments to trains’ running trajectories to optimize the overlap time of braking and traction conditions among multiple trains. The case of the Guangzhou Metro Line 8 in China is presented to verify the effectiveness and practicality of our method. The results show that the consumption of traction energy is reduced by 0.95% and the use of regenerative braking energy is increased by 8.18%, with an improvement in energy efficiency of 6.78%. This method can achieve relatively significant energy efficiency results while ensuring the stable service quality of the train timetable and can provide support for an energy-efficient train timetable for urban rail transit operation enterprises. Full article

Accurate measurement of running parameters, including the step length (SL), step frequency (SF), and velocity, is essential for optimizing sprint performance. Traditional methods, such as 2D video analysis and inertial measurement units (IMUs), face limitations in precision and practicality. This study introduces and evaluates two methods for estimating running parameters using real-time kinematic global navigation satellite systems (RTK GNSS) with 100 Hz sampling. Method 1 identifies mid-stance phases via vertical position minima, while Method 2 aligns with the initial contact (IC) events through vertical velocity minima. Two collegiate sprinters completed a 400 m sprint under controlled conditions, with RTK GNSS measurements validated against 3D video analysis and IMU data. Both methods estimated the SF, SL, and velocity, but Method 2 demonstrated superior accuracy, achieving a lower RMSE (SF: 0.205 Hz versus 0.291 Hz; SL: 0.143 m versus 0.190 m) and higher correlation with the reference data. Method 2 also exhibited improved performance in curved sections and detected stride asymmetries with higher consistency than Method 1. These findings highlight RTK GNSS, particularly the velocity minima approach, as a robust, drift-free, single-sensor solution for detailed per-step sprint analysis in outdoor conditions. This approach offers a practical alternative to IMU-based methods and enables training optimization and performance evaluation. Full article

Background/Objectives: Physical fitness in youth soccer impacts individual and team performance through the specific demands that must be met on the field. Therefore, this study aimed to characterize and identify youth soccer players with regard to the roles they play on the field. Material and Methods: A cross-sectional study was designed to characterize and identify the physical fitness levels of youth soccer players using previously validated measurement tests. A total of 36 players were evaluated (15 defenders and 24 attackers) using various physical fitness tests: Squat Jump (SJ), Countermovement Jump (CMJ), Single-leg Countermovement Jumps (SLCMJs), COD-Timer 5-0-5, Speed (5, 10, 15, and 20 m), Yo-Yo Intermittent Recovery Test Level I (YYIR1), and Running-Based Anaerobic Sprint Test (RAST). The data were confirmed using the Shapiro–Wilk test. Effect sizes were obtained using the Rank-Biserial coefficient, and, to identify the profiles of attackers and defenders, principal component analysis (PCA) was employed. Results: For the strength variables, attackers obtained better results than defenders in the variable flight time in the SJ (p = 0.03; R-b = −0.33) and contact time (%) in the SLCMJ test (p = 0.04; R-b = −0.33). Meanwhile, defenders achieved better results than attackers in the SLCMJ test for the variable flight time (%) (p = 0.01; R-b = 0.33) and breaking angle (A°) in the Nordic Hamstring (p = 0.01; R-b = 0.33). The results showed differences according to the players’ roles. Three principal components were identified for both attackers and defenders. The PC1 for attackers considered variables of strength, asymmetry, change of direction, and power. PC2 only considered strength and power variables. PC3 considered variables of strength, speed, endurance, and power. For defenders, PC1 considered strength, asymmetry, and power. PC2 analyzed variables of strength, asymmetry, change of direction and power. Finally, PC3 only grouped speed variables. Conclusions: Although youth soccer positions involve offensive and defensive roles, this study reveals differences in certain physical fitness variables. Therefore, it is necessary to tailor training tasks according to the specificity of the playing position, in line with the systems of play used and the predominance of the role that players occupy, whether in defense or attack. Full article

In recent years, advanced footwear technology (AFT) has been shown to improve performance in long-distance road running by altering biomechanics and perceived comfort. This type of footwear is now being marketed for mountain running, although its effects in such races remain unevaluated. This study aimed to examine the impact of AFT on performance, biomechanics, and perceived comfort during a simulated mountain running event. Twelve trained mountain runners participated in a 3-day experiment, with a 7-day recovery between sessions. On the first day, a maximal aerobic speed test assessed the runners’ performance levels. On the second day, participants familiarized themselves with a 5.19 km mountain circuit and comfort scale. On the third day, they completed two time trials on the same circuit, separated by 30 min of passive recovery, using conventional and AFT shoes in a randomized order. Physiological and biomechanical variables were recorded, including body mass, blood lactate, running biomechanics, vertical stiffness, shoe comfort, and rating of perceived exertion (RPE). The findings indicate that AFT does not improve performance or physiological responses during a simulated mountain race, regardless of segment (uphill, downhill, or mixed). However, AFT significantly alters running biomechanics, reducing step frequency and increasing the vertical oscillation of the center of gravity, especially in uphill and downhill sections. While overall comfort remained unchanged, specific differences were observed with AFT. Coaches and practitioners should consider these findings when using AFT in mountain running training or competition. Full article

Background: The cross-sectional area of skeletal muscles at the level of the third lumbar vertebra (L3) measured from computed tomography (CT) images is an established imaging biomarker used to assess patients’ nutritional status. With the increasing prevalence of low-dose CT scans in clinical practice, accurate and automated skeletal muscle segmentation at the L3 level in low-dose CT images has become an issue to address. This study proposed a lightweight algorithm for automated segmentation of skeletal muscles at the L3 level in low-dose CT images. Methods: This study included 57 patients with rectal cancer, with both low-dose plain and contrast-enhanced pelvic CT image series acquired using a radiotherapy CT scanner. A training set of 30 randomly selected patients was used to develop a lightweight segmentation algorithm, and the other 27 patients were used as the test set. A radiologist selected the most representative axial CT image at the L3 level for both the image series for all the patients, and three groups of observers manually annotated the skeletal muscles in the 54 CT images of the test set as the gold standard. The performance of the proposed algorithm was evaluated in terms of the Dice similarity coefficient (DSC), precision, recall, 95th percentile of the Hausdorff distance (HD95), and average surface distance (ASD). The running time of the proposed algorithm was recorded. An open source deep learning-based AutoMATICA algorithm was compared with the proposed algorithm. The inter-observer variations were also used as the reference. Results: The DSC, precision, recall, HD95, ASD, and running time were 93.2 ± 1.9% (mean ± standard deviation), 96.7 ± 2.9%, 90.0 ± 2.9%, 4.8 ± 1.3 mm, 0.8 ± 0.2 mm, and 303 ± 43 ms (on CPU) for the proposed algorithm, and 94.1 ± 4.1%, 92.7 ± 5.5%, 95.7 ± 4.0%, 7.4 ± 5.7 mm, 0.9 ± 0.6 mm, and 448 ± 40 ms (on GPU) for AutoMATICA, respectively. The differences between the proposed algorithm and the inter-observer reference were 4.7%, 1.2%, 7.9%, 3.2 mm, and 0.6 mm, respectively, for the averaged DSC, precision, recall, HD95, and ASD. Conclusion: The proposed algorithm can be used to segment skeletal muscles at the L3 level in either the plain or enhanced low-dose CT images. Full article

Cyclic air braking is a key element for ensuring safe train operation when running on a long and steep downhill railway section. In reality, the cyclic braking performance of a train is affected by its operating environment, speed and air-refilling time. Existing optimization algorithms have the problem of low learning efficiency. To solve this problem, an intelligent control method based on the deep Q-network (DQN) algorithm for heavy-haul trains running on long and steep downhill railway sections is proposed. Firstly, the environment of heavy-haul train operation is designed by considering the line characteristics, speed limits and constraints of the train pipe’s air-refilling time. Secondly, the control process of heavy-haul trains running on long and steep downhill sections is described as the reinforcement learning (RL) of a Markov decision process. By designing the critical elements of RL, a cyclic braking strategy for heavy-haul trains is established based on the reinforcement learning algorithm. Thirdly, the deep neural network and Q-learning are combined to design a neural network for approximating the action value function so that the algorithm can achieve the optimal action value function faster. Finally, simulation experiments are conducted on the actual track data pertaining to the Shuozhou–Huanghua line in China to compare the performance of the Q-learning algorithm against the DQN algorithm. Our findings revealed that the DQN-based intelligent control strategy decreased the air braking distance by 2.1% and enhanced the overall average speed by more than 7%. These experiments unequivocally demonstrate the efficacy and superiority of the DQN-based intelligent control strategy. Full article

This paper presents a solution to address the challenges of unexpected events in the operation of metro trains, which can lead to increased delays and safety risks. An improved Q-learning algorithm is proposed to reschedule train timetables via incorporating train detention and different section running times as actions. To enhance computational efficiency and convergence rate, a simulated annealing dynamic factor is introduced to improve action selection strategies. Additionally, importance sampling is employed to evaluate different policies effectively. A case study of Shenzhen Metro is conducted to demonstrate the effectiveness of the proposed method. The results show that the method achieves convergence, fast computation speed, and real-time adjustment capabilities. Compared to traditional methods such as no adjustment, manual adjustment, and FIFO (First-In-First-Out), the proposed method significantly reduces the average total train delay by 54% and leads to more uniform train headways. The proposed method utilizes a limited number of variables for practical state descriptions, making it well suited for real-world applications. It also exhibits good scalability and transferability to other metro systems. Full article

Efficient and seamless railway operations depend on the systematic and well-coordinated maintenance of both rolling stock and infrastructure. However, track maintenance, or ‘trackwork’, can cause substantial delays if not properly aligned with train schedules. This study comprehensively investigates how trackwork influences train operations in Sweden. It involves an in-depth analysis of an extensive dataset comprising over 225,000 recorded instances of planned trackwork and approximately 32.5 million train passages throughout the year 2017. Multiple logistic and negative binomial regression models showed that train running time delay occurrence is higher in the sections with scheduled trackwork. Trains passing through trackwork are 1.43 times more likely to experience delays compared to trains that do not pass through scheduled trackwork. The likelihood of an opportunity for the train delay recovery passing the section with scheduled trackwork is reduced by 11%. Additionally, the frequency of train delay increase is 16% higher, and delayed recovery is 4% lower in relation to trackwork. With the number of trackwork set to increase over the coming years, these results bring attention to train scheduling and the performance of trackwork. Full article

Using a high-throughput neuroanatomical screen of histological brain sections developed in collaboration with the International Mouse Phenotyping Consortium, we previously reported a list of 198 genes whose inactivation leads to neuroanatomical phenotypes. To achieve this milestone, tens of thousands of hours of manual image segmentation were necessary. The present work involved developing a full pipeline to automate the application of deep learning methods for the automated segmentation of 24 anatomical regions used in the aforementioned screen. The dataset includes 2000 annotated parasagittal slides (24,000 × 14,000 pixels). Our approach consists of three main parts: the conversion of images (.ROI to .PNG), the training of the deep learning approach on the compressed images (512 × 256 and 2048 × 1024 pixels of the deep learning approach) to extract the regions of interest using either the U-Net or Attention U-Net architectures, and finally the transformation of the identified regions (.PNG to .ROI), enabling visualization and editing within the Fiji/ImageJ 1.54 software environment. With an image resolution of 2048 × 1024, the Attention U-Net provided the best results with an overall Dice Similarity Coefficient (DSC) of 0.90 ± 0.01 for all 24 regions. Using one command line, the end-user is now able to pre-analyze images automatically, then runs the existing analytical pipeline made of ImageJ macros to validate the automatically generated regions of interest resulting. Even for regions with low DSC, expert neuroanatomists rarely correct the results. We estimate a time savings of 6 to 10 times. Full article

The purpose of this report is to provide additional analysis and commentary on the men’s 100 m world record of 9.58 s, set by Usain Bolt in the 2009 Berlin World Championships in Athletics. In addition, the entire race underwent a unique kinematic analysis, particularly emphasizing the maximum running velocity and its related factors. It was possible due the application of the new Stuhec software. The data were provided by LAVEG’S advanced laser measurement technology based on positional data with a high spatiotemporal resolution. The maximum velocity phase is the most critical determinant of the final race time. Bolt completed two phases in this world-record 100 m sprint: acceleration and top velocity. The borderline between these phases reached the highest velocity of 12.32 m/s on a 52 m run. He could keep the maximum velocity in five 10 m sections (50–100 m). The occurrence of functional asymmetry—the difference in step length between the left and right legs—was also noticed. Longer steps were taken with the left leg, almost over 80 m. From a practical point of view, new technologies (e.g., software) allow coaches and athletes to analyze the kinematic parameters of sprinting even more precisely and in detail. They must take into account precise changes in the course of maximum speed and the parameters determining it which are step length and frequency. Based on such an analysis, it is possible to modify the training process aimed at increasing the potential, both maximum speed and the supporting factors of strength and power. This must be conditioned by the appropriate selection of training measures shaping the abovementioned motor skills and parameters describing the optimal sprinting technique. Full article

Strong wind–sand flow exerts great potential safety hazards for high-speed train operations. In this paper, we investigate the aerodynamic characteristics of high-speed trains passing through the bridge–road transition section under a wind-blown sand environment. In particular, we adopt the sliding grid method to simulate the changes in aerodynamic pressure on the train surface when the train passes the bridge transition at different speeds and bridge heights. The variation in the aerodynamic lateral force borne by the vehicle body at various times is then obtained. The results reveal that in the wind–sand environment, when a train drives from the bridge to the embankment, the pressure values on both the windward and leeward sides of the train change abruptly, with the most obvious increase in the lateral force of the head car. Moreover, the abrupt change in pressure increases with the speed of the lateral wind–sand flow. The differential pressure force of the train on the embankment is larger where the differential pressure force on both sides of the head train is the largest. When the train is running in the opposite direction, the differential pressure force on both sides of the train decreases. Compared with the lateral wind condition, the lateral force at different positions of the train under the wind–sand condition exceeds that under the non-sand condition. The average increases in the train body are approximately 17.6% (10 m/s), 10.5% (20 m/s) and 9.5% (30 m/s), which will cause passengers to experience an obvious “shaking” phenomenon. Full article

The stiffnesses of embankments and culverts differ in the transition sections of high-speed railways (HSRs) due to their different supporting conditions. The dynamic irregularity caused by the different stiffnesses makes this transition area the weakest part of high-speed railways. Graded crushed stone combined with 5% cement is typically used to fill the subgrade in these transition areas. Thus, three different particle size ratios of crushed stone were matched and tested regarding the construction parameters to explore the most suitable materials to fill the roadbed in a transition section. Then, field dynamic tests were carried out on the culvert–embankment–culvert transition area where trains run at speeds of 5–360 km/h. A time-domain analysis of the test data was performed to obtain the laws of variation that cause the dynamic characteristics to change with the railway line and roadbed layer and the changes induced by a train’s running speed, operating direction, and axle weight. The results indicate that (i) it is feasible to fill transition section roadbeds with well-graded crushed stone combined with 5% cement with optimal water contents; (ii) extreme dynamic responses in some special sections are observed, suggesting the value of taking special measures at the transition section. For example, the sections 14.5 m and 30 m from the 679 culvert and the bed layer should be specially stabilized; (iii) the train’s axle load and driving direction show a great effect on corresponding sections and layers but present a small effect on the sections and layers nearby; and (iv) 260 km/h is a critical speed. Full article

Of past years, wearing masks has turned into a necessity in daily life due to the rampant new coronavirus and the increasing importance people place on health and life safety. However, current mask detection algorithms are difficult to run on low-computing-power hardware platforms and have low accuracy. To resolve this discrepancy, a lightweight mask inspection algorithm ECGYOLO based on improved YOLOv7tiny is proposed. This algorithm uses GhostNet to replace the original convolutional layer with ECG module instead of ELAN module, which greatly improves the inspection efficiency and decreases the parameters of the model. In the meantime, the ECA (efficient channel attention) mechanism is led into the neck section to boost the feature fetch capability of the channel, and Mosaic and Mixup data enhancement techniques are adopted in training to obtain mask images under different viewpoints to improve the comprehensiveness and effectiveness of the model. Experiments show that the mAP (mean average precision) of the algorithm is raised by 4.4% to 92.75%, and the number of arguments is decreased by 1.14 M to 5.06M compared with the original YOLOv7tiny. ECGYOLO is more efficient than other algorithms at present and can meet the real-time and lightweight needs of mask detection. Full article

Over the past few years, several applications have been extensively exploiting the advantages of deep learning, in particular when using convolutional neural networks (CNNs). The intrinsic flexibility of such models makes them widely adopted in a variety of practical applications, from medical to industrial. In this latter scenario, however, using consumer Personal Computer (PC) hardware is not always suitable for the potential harsh conditions of the working environment and the strict timing that industrial applications typically have. Therefore, the design of custom FPGA (Field Programmable Gate Array) solutions for network inference is gaining massive attention from researchers and companies as well. In this paper, we propose a family of network architectures composed of three kinds of custom layers working with integer arithmetic with a customizable precision (down to just two bits). Such layers are designed to be effectively trained on classical GPUs (Graphics Processing Units) and then synthesized to FPGA hardware for real-time inference. The idea is to provide a trainable quantization layer, called Requantizer, acting both as a non-linear activation for neurons and a value rescaler to match the desired bit precision. This way, the training is not only quantization-aware, but also capable of estimating the optimal scaling coefficients to accommodate both the non-linear nature of the activations and the constraints imposed by the limited precision. In the experimental section, we test the performance of this kind of model while working both on classical PC hardware and a case-study implementation of a signal peak detection device running on a real FPGA. We employ TensorFlow Lite for training and comparison, and use Xilinx FPGAs and Vivado for synthesis and implementation. The results show an accuracy of the quantized networks close to the floating point version, without the need for representative data for calibration as in other approaches, and performance that is better than dedicated peak detection algorithms. The FPGA implementation is able to run in real time at a rate of four gigapixels per second with moderate hardware resources, while achieving a sustained efficiency of 0.5 TOPS/W (tera operations per second per watt), in line with custom integrated hardware accelerators. Full article

The potential running or endurance performance difference based on following different general types of diets, such as omnivorous, vegetarian, or vegan, remains questionable. Several underlying modifiable factors of long-distance running performance, especially runner training behaviors and experience, diminish the clarity of results when analyzing dietary subgroups. Based on the cross-sectional design (survey), the NURMI Study Step 2 aimed to investigate a plethora of training behaviors among recreational long-distance running athletes and the relationship of general diet types with best time race performance. The statistical analysis was based on Chi-squared and Wilcoxon tests. The final sample (n = 245) included fit recreational long-distance runners following an omnivorous diet (n = 109), a vegetarian diet (n = 45), or a vegan diet (n = 91). Significant differences were found between the dietary subgroups in body mass index (p = 0.001), sex (p = 0.004), marital status (p = 0.029), and running-related motivations for well-being (p < 0.05) but not in age (p = 0.054). No significant difference was found for best time half-marathon, marathon, and/or ultra-marathon race performance based on diet type (p > 0.05). Whether the vegan diet is associated with enhanced endurance performance remains unclear. Although, the present results are suggestive that 100% plant-based (vegan) nutrition is compatible with distance running performance at the least. Full article