Search Results (55)

Mass shootings are forms of loosely defined violent crimes typically involving four or more casualties by firearm and have become increasingly more frequent, and organized and speedy responses from police are necessary to mitigate harm and neutralize the perpetrator. Recent, widely publicized police responses to mass shooting events have been criticized by the media, government, and public. With the advancements in artificial intelligence, specifically single-shot detection (SSD) models, computer programs can detect harmful weapons within efficient time frames. We utilized YOLO (You Only Look Once), an SSD with a Convolutional Neural Network, and used versions 5, 7, 8, 9, 10, and 11 to develop our detection system. For our data, we used a Roboflow dataset that contained almost 17,000 images of real-life handgun scenarios, designed to skew towards positive instances. We trained each model on our dataset and exchanged different hyperparameters, conducting a randomized trial. Finally, we evaluated the performance based on precision metrics. Using a Python-based design, we tested our model’s capabilities for surveillance functions. Our experimental results showed that our best-performing model was YOLOv10s, with an mAP-50 (mean average precision 50) of 98.2% on our dataset. Our model showed potential in edge computing settings. Full article

Objective: This study aims to investigate the effect of shot selection on the muscle coordination characteristics during basketball shooting. Methods: A three-dimensional motion capture system, force platform, and wireless surface electromyography (sEMG) were used to simultaneously collect shooting data from 14 elite basketball players. An inverse mapping model of sEMG signals and spinal α-motor neuron pool activity was developed based on the Debra muscle segment distribution theory. Non-negative matrix factorization (NMF) and K-means clustering were used to extract muscle coordination features. Results: (1) Significant differences in spinal segment activation timing and amplitude were observed between stationary and jump shots at different distances. In close-range stationary shots, the C5-S3 segments showed higher activation during the TP phase and lower activation during the RP phase. For mid-range shots, the C6-S3 segments exhibited greater activation during the TP phase. In long-range shots, the C7-S3 segments showed higher activation during the TP phase, whereas the L3-S3 segments showed lower activation during the RP phase (p < 0.01). (2) The spatiotemporal structure of muscle coordination modules differed significantly between stationary and jump shots. In terms of spatiotemporal structure, the second and third coordination groups showed stronger activation during the RP phase (p < 0.01). Significant differences in muscle activation levels were also observed between the coordination modules within each group in the spatial structure. Conclusion: Shot selection plays a significant role in shaping neuromuscular control strategies during basketball shooting. Targeted training should focus on addressing the athlete’s specific shooting weaknesses. For stationary shots, the emphasis should be on enhancing lower limb stability, while for jump shots, attention should be directed toward improving core stability and upper limb coordination. Full article

In recent years, advances in artificial intelligence, machine vision, and the Internet of Things have significantly impacted sports analytics, particularly basketball, where accurate measurement and analysis of player performance have become increasingly important. This study proposes a real-time goal state recognition system based on inertial measurement unit (IMU) sensors, focusing on four shooting scenarios: rebounds, swishes, other shots, and misses. By installing IMU sensors around the basketball net, the system captures real-time data on acceleration, angular velocity, and angular changes to comprehensively analyze the fluency and success rate of shooting execution, utilizing five deep learning models—convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM), CNN-LSTM, and CNN-LSTM-Attention—to classify shot types. Experimental results indicate that the CNN-LSTM-Attention model outperformed other models with an accuracy of 87.79% in identifying goal states. This result represents a commanding level of real-time goal state recognition, demonstrating the robustness and efficiency of the model in complex sports environments. This high accuracy not only supports the application of the system in skill analysis and sports performance evaluation but also lays a solid foundation for the development of intelligent basketball training equipment, providing an efficient and practical solution for athletes and coaches. Full article

Grapes are rich in bioactive compounds, including phenolics and anthocyanins, which exhibit antioxidant properties and offer potential health benefits. The accumulation of these compounds is influenced by agronomic practices, particularly rootstock selection and training systems. This study evaluated the effects of different rootstocks (‘IAC 766 Campinas’ and ‘106-8 Mgt’) and training systems (low and high vertical shoot positioning) on the polyphenolic composition and antioxidant activity in the skins and pulps of Vitis labrusca and Brazilian hybrid grapes. The analyses included total phenolics, total flavonoids, monomeric anthocyanins, and antioxidant activity (DPPH and FRAP assays), as well as the individual polyphenolic profile in grape skins. The results indicated that both rootstock and training system significantly affected the accumulation of bioactive compounds and antioxidant capacity. Grapes trained on high trellises exhibited higher concentrations of bioactive compounds, while those from low trellises showed an enhanced phenolic composition. Among Vitis labrusca varieties, ‘Bordô’ had the highest bioactive compounds, while ‘Isabel’ stood out for specific phenolic acids. In hybrid cultivars, the ‘106-8 Mgt’ rootstock boosted antioxidant compounds, while ‘IAC 766 Campinas’ enhanced flavonoid, anthocyanin, and phenolic acid levels. Malvidin-3-O-glucoside emerged as the predominant anthocyanin. These findings underscore the importance of optimizing rootstock selection and training systems to enhance the phenolic composition and antioxidant potential of grapes. Full article

Tower bolts play a crucial role as connecting components in wind turbines and are of great interest for health monitoring systems. Non-contact monitoring techniques offer superior efficiency, convenience, and intelligence compared to contact-based methods. However, the precision and robustness of the non-contact monitoring process are significantly impacted by suboptimal lighting conditions within the wind turbine tower. To address this problem, this article proposes an automated detection method for the bolt detachment of wind turbines in low-light scenarios. The approach leverages the deep convolutional generative adversarial network (DCGAN) to expand and augment the small-sample bolt dataset. Transfer learning is then applied to train the Zero-DCE++ low-light enhancement model and the bolt defect detection model, with the experimental verification of the proposed method’s effectiveness. The results reveal that the deep convolutional generative adversarial network can generate realistic bolt images, thereby improving the quantity and quality of the dataset. Additionally, the Zero-DCE++ light enhancement model significantly increases the mean brightness of low-light images, resulting in a decrease in the error rate of defect detection from 31.08% to 2.36%. In addition, the model’s detection performance is affected by shooting angles and distances. Maintaining a shooting distance within 1.6 m and a shooting angle within 20° improves the reliability of the detection results. Full article

This study’s primary goal is to use computer vision and ultra-wideband (UWB) localisation techniques to automatically mark numerals in cow photos. In order to accomplish this, we created a UWB-based cow localisation system that involves installing tags on cow heads and placing several base stations throughout the farm. The system can determine the distance between each base station and the cow using wireless communication technology, which allows it to determine the cow’s current location coordinates. The study employed a neural network to train and optimise the ranging data gathered in the 1–20 m range in order to solve the issue of significant ranging errors in conventional UWB positioning systems. The experimental data indicates that the UWB positioning system’s unoptimized range error has an absolute mean of 0.18 m and a standard deviation of 0.047. However, when using a neural network-trained model, the ranging error is much decreased, with an absolute mean of 0.038 m and a standard deviation of 0.0079. The average root mean square error (RMSE) of the positioning coordinates is decreased to 0.043 m following the positioning computation utilising the optimised range data, greatly increasing the positioning accuracy. This study used the conventional camera shooting method for image acquisition. Following image acquisition, the system extracts the cow’s coordinate information from the image using a perspective transformation method. This allows for accurate cow identification and number labelling when compared to the location coordinates. According to the trial findings, this plan, which integrates computer vision and UWB positioning technologies, achieves high-precision cow labelling and placement in the optimised system and greatly raises the degree of automation and precise management in the farming process. This technology has many potential applications, particularly in the administration and surveillance of big dairy farms, and it offers a strong technical basis for precision farming. Full article

The present study aimed to verify the (1) differences between players’ roles in relation to technical and tactical and time–motion indicators, and the (2) relationships between individual time–motion and technical and tactical indicators for each role in a men’s Italian football Serie A team. A total of 227 performances were analyzed (28 players: 8 forwards, FWs; 11 midfielders, MDs; 9 defenders, DFs). Technical and tactical indicators, such as ball possession (played balls, successful passes, successful playing patterns, lost balls, ball possession time), offensive play (total and successful dribbles, crosses, assists), and shooting (total shots, shots on target) were obtained by means of Panini Digital (DigitalSoccer Project S.r.l). In addition, a time–motion analysis included the total distance, distances covered at intensities of 16.0–19.8 km/h, 19.8–25.2 km/h, and over 25.2 km/h, the average recovery time between metabolic power peaks, and burst occurrence, the latter of which was performed by means of a 18 Hz GPS device (GPexe Pro2 system tool) worn by the players. Results showed role-specific differences: MDs covered more distance, while DFs had better ball possession. MDs and DFs had more successful playing patterns, and MDs and FWs performed more dribbles and shots. Strong correlations (p < 0.01, ρ > 0.8) were found between bursts and assists for FWs, high-intensity running and ball possession for MDs, and distance, dribbling, and shots for DFs. These findings highlight the importance of individual and tailored training programs to optimize role-specific performance demands. Full article

In this study, an action recognition system was developed to identify fundamental basketball movements using a single Inertial Measurement Unit (IMU) sensor embedded in a wearable vest. This study aims to enhance basketball training by providing a high-performance, low-cost solution that minimizes discomfort for athletes. Data were collected from 21 collegiate basketball players, and movements such as dribbling, passing, shooting, layup, and standing still were recorded. The collected IMU data underwent preprocessing and feature extraction, followed by the application of machine learning algorithms including KNN, decision tree, Random Forest, AdaBoost, and XGBoost. Among these, the XGBoost algorithm with a window size of 250 and a 75% overlap yielded the highest accuracy of 96.6%. The system demonstrated superior performance compared to other single-sensor systems, achieving an overall classification accuracy of 96.9%. This research contributes to the field by presenting a new dataset of basketball movements, comparing the effectiveness of various feature extraction and machine learning methods, and offering a scalable, efficient, and accurate action recognition system for basketball. Full article

Archery has increasingly captivated attention in its use for rehabilitation and physical education due to its adaptability for various abilities. However, this repetitive sport carries some injury risk in the shoulder, elbow, and back during the draw and release phases. While research often explores factors affecting shooting performance, limited studies have examined the interplay between gender-specific biomechanics and bow-related variables on lumbar stress and shooting mechanics. This study addresses this gap by leveraging the Xsens MVN Awinda motion capture system and JACK Siemens ergonomic software to analyze full-body movements of archers with different experience levels, bow types, and target placements. Thirteen subjects participated in this investigation, each equipped with standard gear. We analyzed their posture throughout the shooting sequence and the forces acting on their lower back. This innovative approach streamlines data collection and eliminates the need for extensive prototyping. Our findings highlight natural biomechanical adaptations between males and females when using bows of varying draw weights. Males generally exhibited greater consistency and stability, while females showed increased variability, particularly with heavier bows. This research establishes a foundation for ergonomic and reproducible archery techniques, enabling individualized training and performance optimization strategies. Full article

Although the U.S. makes up only 5% of the global population, it accounts for approximately 31% of public mass shootings. Gun violence and mass shootings not only result in loss of life and injury but also inflict lasting psychological trauma, cause property damage, and lead to significant economic losses. We recently developed and published an embedded system prototype for detecting gunshots in an indoor environment. The proposed device can be attached to the walls or ceilings of schools, offices, clubs, places of worship, etc., similar to smoke detectors or night lights, and they can notify the first responders as soon as a gunshot is fired. The proposed system will help to stop the shooter early and the injured people can be taken to the hospital quickly, thus more lives can be saved. In this project, a new custom dataset of blank gunshot sounds is recorded, and a deep learning model using both time and frequency domain features is trained to classify gunshot and non-gunshot sounds with 99% accuracy. The previously developed system suffered from several security and privacy vulnerabilities. In this research, those vulnerabilities are addressed by implementing secure Message Queuing Telemetry Transport (MQTT) communication protocols for IoT systems, better authentication methods, Wi-Fi provisioning without Bluetooth, and over-the-air (OTA) firmware update features. The prototype is implemented in a Raspberry Pi Zero 2W embedded system platform and successfully tested with blank gunshots and possible false alarms. Full article

Firearm shooting performance training rightfully focuses on shooting accuracy; however, additional foci should include decision processing speed and reaction time associated with decision making to avoid reaction-only based shooting responses. While advancements in realistic training environments attempt to mimic “real-world” situations, many remain largely anticipatory or subject to a speed–accuracy trade-off (SAT). The purpose of this brief field trial was to demonstrate the feasibility of a random-action target system (RATS) on participants’ shooting performance (i.e., accuracy, omission, and commission rates) among a convenience sample of six retired police officers and competitive shooters (age range: 45–58 years, mean age = 52.5 ± 5.89). Observational data were gathered from a single-day, three-round trial to test shooting accuracy and shooting errors when shooters were unable to anticipate target appearance location and target exposure speed. In Trial 1, the target exposure time was 0.5 s, which increased to 0.7 s in Trial 2, and decreased back to 0.5 s in Trial 3. Shooting accuracy generally increased, while omission and commission generally decreased, when shooters were presented with targets exposed for longer durations. From Trial 1 to Trial 3 (both trials with 0.5 s target exposures), shooters showed higher median accuracy rates, lower median omission rates, and lower median commission rates. Findings suggest that a non-anticipatory, RATS holds promise for improving shooting performance and offset SAT among shooters with firearm experience. However, additional trials are needed with the RATS to replicate these findings among a larger and more diverse set of participants, who train with the RATS consistently, over longer durations. Full article

This study examines the influence of fatigue and defensive pressure on the kinematic parameters of the three-point jump shot in basketball. Fourteen male collegiate basketball players (age: 21 ± 3 years old, body height: 186.35 ± 7.02 cm, body mass: 82.20 ± 10.99) participated in the study. Each participant performed three-point jump shots under four conditions: without defense, with defense, without defense after a fatigue protocol, and with defense after a fatigue protocol. Kinematic data were collected using the Xsens MVN inertial suit system and the OptoJump Next system. The analysis focused on various parameters including jump height, center of mass, release height, shoulder angle, and segment velocities. The repeated-measures ANOVA was used to observe the differences between each shot condition (fatigue, defense). Results indicated significant changes in the kinematic parameters due to both fatigue and defensive pressure. Fatigue notably changed shooting performance, affecting jump height and release mechanics. The defensive pressure altered shooting technique, leading to quicker ball release and higher release points. These findings highlight the importance of incorporating fatigue and defensive scenarios in training, suggesting that coaches develop more targeted training plans to improve performance under conditions of fatigue and defensive pressure. Full article

In order to promote the accurate recognition and application of visual navigation robots to the environment, this paper carried out research on the road pattern recognition of a vision-guided robot based on improved YOLOv8 on the basis of road pattern calibration and experimental sampling. First, an experimental system for road image shooting was built independently, and 21 different kinds of road pattern image data were obtained by sampling roads with different weather conditions, road materials, and degrees of damage. Second, the road pattern recognition model based on the classical neural network Resnet 18 was constructed for model training and testing, and the initial recognition of road pattern was realized. Third, the YOLOv8 target detection model was introduced to build the road pattern recognition model based on YOLOv8n, and the model was trained and tested, improving road pattern recognition accuracy and recognition response speed by 3.1% and 200%, respectively. Finally, to further improve the accuracy of road pattern recognition, improvement research was carried out on the YOLOv8n road pattern recognition model based on the C2f-ODConv module, the AWD adaptive weight downsampling module, the EMA attention mechanism, and the collaboration of the three modules. Three network architectures, classical CNN (Resnet 18), YOLOv8n, and improved YOLOv8n, were compared. The results show that four different optimization models can further improve the accuracy of road pattern recognition, among which the accuracy of the improved YOLO v8 road pattern recognition model based on multimodule cooperation is the highest, reaching more than 93%. Full article

Scoring targets in shooting sports is a crucial and time-consuming task that relies on manually counting bullet holes. This paper introduces an automatic score detection model using object detection techniques. The study contributes to the field of computer vision by comparing the performance of seven models (belonging to two different architectural setups) and by making the dataset publicly available. Another value-added aspect is the inclusion of three variants of the object detection model, YOLOv8, recently released in 2023 (at the time of writing). Five of the used models are single-shot detectors, while two belong to the two-shot detectors category. The dataset was manually captured from the shooting range and expanded by generating more versatile data using Python code. Before the dataset was trained to develop models, it was resized (640 × 640) and augmented using Roboflow API. The trained models were then assessed on the test dataset, and their performance was compared using matrices like mAP50, mAP50-90, precision, and recall. The results showed that YOLOv8 models can detect multiple objects with good confidence scores. Among these models, YOLOv8m performed the best, with the highest mAP50 value of 96.7%, followed by the performance of YOLOv8s with the mAP50 value of 96.5%. It is suggested that if the system is to be implemented in a real-time environment, YOLOv8s is a better choice since it took significantly less inference time (2.3 ms) than YOLOv8m (5.7 ms) and yet generated a competitive mAP50 of 96.5%. Full article

To investigate the impact of brackish water irrigation on the multidimensional root distribution and root-shoot characteristics of summer maize under different salt-tolerance-training modes, a micro-plot experiment was conducted from June to October in 2022 at the experimental station in Hohai University, China. Freshwater irrigation was used as the control (CK), and different concentrations of brackish water (S0: 0.08 g·L⁻¹, S1: 2.0 g·L⁻¹, S2: 4.0 g·L⁻¹, S3: 6.0 g·L⁻¹) were irrigated at six-leaf stage, ten-leaf stage, and tasseling stage, constituting different salt tolerance training modes, referred to as S_0-2-3, S_0-3-3, S_1-2-3, S_1-3-3, S_2-2-3, and S_2-3-3. The results showed that although their fine root length density (FRLD) increased, the S_0-2-3 and S_0-3-3 treatments reduced the limit of root extension in the horizontal direction, causing the roots to be mainly distributed near the plants. This resulted in decreased leaf area and biomass accumulation, ultimately leading to significant yield reduction. Additionally, the S_2-2-3 and S_2-3-3 treatments stimulated the adaptive mechanism of maize roots, resulting in boosted fine root growth to increase the FRLD and develop into deeper soil layers. However, due to the prolonged exposure to a high level of salinity, their roots below 30 cm depth senesced prematurely, leading to an inhibition in shoot growth and also resulting in yield reduction of 10.99% and 11.75%, compared to CK, respectively. Furthermore, the S_1-2-3 and S_1-3-3 treatments produced more reasonable distributions of FRLD, which did not boost fine root growth but established fewer weak areas (FLRD < 0.66 cm⁻³) in their root systems. Moreover, the S_1-2-3 treatment contributed to increasing leaf development and biomass accumulation, compared to CK, whereas it allowed for minimizing yield reduction. Therefore, our study proposed the S_1-2-3 treatment as the recommended training mode for summer maize while utilizing brackish water resources. Full article