PLoS ONEPub Date : 2025-05-27eCollection Date: 2025-01-01DOI: 10.1371/journal.pone.0321059
Yuan Du, Ning Li, Manbin Yang, She Shan, Hui Dou, Yongzhi Chen, Xinyuan Liu
{"title":"Temperature dependence of adhesive friction properties of rubber asphalt mortar and its mechanism of action.","authors":"Yuan Du, Ning Li, Manbin Yang, She Shan, Hui Dou, Yongzhi Chen, Xinyuan Liu","doi":"10.1371/journal.pone.0321059","DOIUrl":"https://doi.org/10.1371/journal.pone.0321059","url":null,"abstract":"<p><p>The tire-road contact friction system has been widely studied. However, the traditional theoretical model of pavement anti-sliding does not pay attention to the influence of temperature on the tire-road interface friction system. The purpose of this paper is to simulate the adhesive friction process of rubber asphalt mortar under different temperature and different phase conditions by molecular dynamics simulation, so as to explain the adhesive friction mechanism of rubber asphalt mortar. In this study, the molecular model of rubber asphalt mortar with rubber powder content of 0%, 10%, 20% and 30% was first constructed by Materials Studio software. Secondly, the molecular dynamics simulation was carried out by COMPASS II force field, and the glass transition temperature, bulk modulus and Young's modulus of the molecular model of rubber asphalt mortar were calculated. Then, the variation characteristics of the friction coefficient index of the rubber-asphalt mortar-aggregate three-layer friction pair model with temperature were simulated, and the simulation results of elastic modulus and adhesion work were comprehensively analyzed. The results showed that the glass transition temperature of the molecular model of rubber asphalt mortar is between -20°C and 0°C, and the bulk modulus and Young's modulus of rubber asphalt mortar show an upward trend with the increase of rubber powder content and temperature. The friction coefficient of the rubber-asphalt mortar-aggregate three-layer friction pair model increases with the increase of temperature and rubber powder content. The results of Young's modulus and adhesion work simulation show that as the temperature increases, the phase state of the rubber asphalt mortar changes, and the adhesion increases, resulting in an increase in the friction coefficient of the rubber asphalt mortar. In addition, the simulated and predicted values of the friction coefficient of the rubber-asphalt mortar-aggregate three-layer friction pair model with temperature change are well fitted, and the maximum difference is 0.32.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0321059"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144161420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PLoS ONEPub Date : 2025-05-27eCollection Date: 2025-01-01DOI: 10.1371/journal.pone.0322953
Lei Song, Ji Wang, Shibo Wang, Zongxiao Yang, Jianxin Su
{"title":"Numerical study on performance of a vertical axis wind rotor with S-shaped blades.","authors":"Lei Song, Ji Wang, Shibo Wang, Zongxiao Yang, Jianxin Su","doi":"10.1371/journal.pone.0322953","DOIUrl":"https://doi.org/10.1371/journal.pone.0322953","url":null,"abstract":"<p><p>Traditional Savonius wind rotor has simple structure and can operate in any wind direction. However, its aerodynamic efficiency is lower than other types. A novel S-shaped wind rotor with three blades is proposed in order to improve the aerodynamic performance. The blade of the rotor is composed of two opposing convex circular arcs and its shape likes an 'S'. The flow characteristics of the rotor are studied and analyzed by computational fluid dynamics (CFD) numerical simulation method. The steady and transient performances are studied using SST k-ω model and sliding mesh method, and are compared with that of traditional Savonius rotors. The results show that the average static torque coefficient of the rotor is 0.291, which is higher than the 0.222 of the Savonius rotor. The static vibration amplitude of the rotor is 0.375, which is lower than 0.709 of the Savonius rotor. The maximum power coefficient of the rotor is 0.228, which is also higher than the 0.226 of the Savonius rotor. The dynamic vibration amplitude of the novel rotor is 0.183, which is lower than the 0.492 of the Savonius rotor. The flow field analyses show that structure of the S-shaped blades can smooth the flow field and reduce the blocking effect in the overlap area. The study indicates that the proposed navel rotor can not only overcome the problems of sharp change in the internal flow field of traditional Savonius rotors, but also provide better operating stability and higher wind energy utilization.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0322953"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144161424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PLoS ONEPub Date : 2025-05-27eCollection Date: 2025-01-01DOI: 10.1371/journal.pone.0322920
Dan Liu, Cheng Long Yu, Rui Feng, Shi Ping Yin
{"title":"Spatiotemporal dynamics and influencing factors of soil heterotrophic respiration in northeast China.","authors":"Dan Liu, Cheng Long Yu, Rui Feng, Shi Ping Yin","doi":"10.1371/journal.pone.0322920","DOIUrl":"https://doi.org/10.1371/journal.pone.0322920","url":null,"abstract":"<p><p>Soil heterotrophic respiration (Rh) represents a primary pathway of carbon release from soil. Using meteorological data, DEM, soil organic carbon density, and other data, we simulated the Rh in Northeast China from 2001 to 2020 using the GSMSR model. We then analyzed its spatialtemporal distribution pattern and examined its spatial-temporal aggregation, differentiation characteristics, and influencing factors at the national level, employing methods such as standard deviation ellipse (a statistical method that describes the spread and direction of data points in space), cold-hot spot analysis, and geographically weighted regression. The results showed that: (1) From 2001 to 2020, the annual mean Rh of the terrestrial ecosystem in Northeast China ranged from 24.22 kgC/ha/year to 25.02 kgC/ha/year, with a very significant increasing trend at the rate of 0.04 kgC/ha/year. The total amount of carbon release from soil heterotrophic respiration ranged from 4.76 × 1011 to 5.02 × 1011 kilograms per year (kg/year), representing the annual carbon flux in the study region. And it had a significant increasing trend at the rate of 5.75 × 108 kg/year. (2) From the spatial differentiation and spatial clustering pattern, Rh was dominated by a northeast-southwest direction, its spatial distribution center was close to the northeast geographical center, and it had no obvious contraction or expansion trend on the whole. (3) In the northern and northeastern regions of the study area, vegetation cover directly influences local soil respiration rates. In most areas of the north, east, and south, per capita Gross Domestic Product directly affects soil respiration rates. It might provide a reference for the estimation of soil carbon loss and ecosystem carbon sink in this region.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0322920"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144161434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PLoS ONEPub Date : 2025-05-27eCollection Date: 2025-01-01DOI: 10.1371/journal.pone.0321270
Zhe Li
{"title":"Swim-Rep fusion net: A new backbone with Faster Recurrent Criss Cross Polarized Attention.","authors":"Zhe Li","doi":"10.1371/journal.pone.0321270","DOIUrl":"https://doi.org/10.1371/journal.pone.0321270","url":null,"abstract":"<p><p>Deep learning techniques are widely used in the field of medicine and image classification. In past studies, SwimTransformer and RepVGG are very efficient and classical deep learning models. Multi-scale feature fusion and attention mechanisms are effective means to enhance the performance of deep learning models. In this paper, we introduce a novel Swim-Rep fusion network, along with a new multi-scale feature fusion module called multi-scale strip pooling fusion module(MPF) and a new attention module called Faster Recurrent Criss Cross Polarized Attention (FRCPA), both of which excel at extracting multi-dimensional cross-attention and fine-grained features. Our fully supervised model achieved an impressive accuracy of 99.82% on the MIT-BIH database, outperforming the ViT model classifier by 0.12%. Additionally, our semi-supervised model demonstrated strong performance, achieving 98.4% accuracy on the validation set. Experimental results on the remote sensing image classification dataset RSSCN7 demonstrate that our new base model achieves a classification accuracy of 92.5%, which is 8.57% better than the classification performance of swim-transformer-base and 12.9% better than that of RepVGG-base, and increasing the depth of the module yields superior performance.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0321270"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144161448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PLoS ONEPub Date : 2025-05-27eCollection Date: 2025-01-01DOI: 10.1371/journal.pone.0325023
Mykyta Peka, Viktor Balatsky
{"title":"Binding of transmissible gastroenteritis virus and porcine respiratory coronavirus to human and porcine aminopeptidase N receptors as an indicator of cross-species transmission.","authors":"Mykyta Peka, Viktor Balatsky","doi":"10.1371/journal.pone.0325023","DOIUrl":"https://doi.org/10.1371/journal.pone.0325023","url":null,"abstract":"<p><p>Coronaviruses have the ability to overcome interspecies barriers and adapt to new hosts, posing significant epidemic risks in cases of zoonotic transmission to humans. A critical factor in this process is the interaction between coronavirus spike proteins and host cell surface receptors, which plays an important role in infection and disease progression. This study focused on two representatives of coronaviruses: transmissible gastroenteritis virus (TGEV) and its mutant, porcine respiratory coronavirus (PRCV), both of which naturally cause disease in pigs. A phylogenetic analysis of previously identified strains of these viruses was performed, and the conservation of receptor-binding domain (RBD) sequences within their spike proteins was evaluated. In silico modeling was performed for complexes of the RBDs from 16 virus strains with porcine aminopeptidase N (APN), as well as for putative complexes with the human APN receptor. The binding free energy of these modeled complexes was evaluated, along with the impact of more than 500 theoretical mutations in the RBD. The computational results suggest that the TGEV 133 strain exhibits the highest affinity for both porcine and human receptors, with only two additional mutations required to further enhance this affinity. Molecular dynamics simulations were conducted for porcine and human APN complexes with known TGEV strains (Purdue and 133) as well as a theoretical mutated strain. These simulations reveal differences in the dynamic behavior of complexes with porcine and human receptors and support the hypothesis that mutagenesis at a few key amino acid residues in the RBD could enable TGEV to achieve affinity for human APN comparable to that of its natural host receptor. The findings underscore a theoretical risk of zoonotic transmission of these coronaviruses to humans, emphasizing the importance of further monitoring these pathogens.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0325023"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144160600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Genome-wide association studies and transcriptome analysis reveal novel genes associated with freezing tolerance in rapeseed (Brassica napus L.).","authors":"Guoqiang Zheng, Zigang Liu, Lixi Jiang, Qi Yang, Jiaping Wei, Zefeng Wu, Junmei Cui, Xiaoyun Dong, Xiaodong Cao, Xuezhen Yang, Ying Wang, Yongjie Gong, Ermei Sa, Xiaoxia Wang","doi":"10.1371/journal.pone.0322547","DOIUrl":"https://doi.org/10.1371/journal.pone.0322547","url":null,"abstract":"<p><p>Freezing stress is the main obstacle affecting the geographical distribution, growth, development, quality, and productivity of rapeseed (Brassica napus) in northern China. However, there is a little knowledge of rapeseed freezing tolerance mechanism. Here, 289 core germplasms collected from 36 countries were used to identify SNPs associated with freezing tolerance. We used RNA-seq data to narrow down the candidate genes identified by genome-wide association studies. The frequency distributions of phenotypic values and best linear unbiased estimates (BLUE) values for each trait conform to normal or approximately normal distributions, with good repeatability across various locations. The results showed that 594, 513, 7, and 45 SNPs were significantly associated with malondialdehyde, peroxidase, soluble protein, and relative electrolyte leakage, respectively. Based on these significantly associated SNPs, we identified 4,998 associated genes. Crossover analysis indicated that 73 genes were overlapped between GWAS and RNA-seq datasets, and 13 candidate genes involved in transmission and perception of freeze stress signals, lipid metabolism, reactive oxygen species (ROS) homeostasis, antifreeze proteins synthesis, and other metabolic processes. These results reveal novel genes associated with freezing tolerance in rapeseed, and provide a basis for further research and improvement of freezing tolerance in rapeseed.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0322547"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144160817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PLoS ONEPub Date : 2025-05-27eCollection Date: 2025-01-01DOI: 10.1371/journal.pone.0318039
Antonio Rodríguez-Fernández, Joan Lobo-Prat, Mariona Tolrà-Campanyà, Florentina Pérez-Cañabate, Josep M Font-Llagunes, Lluis Guirao-Cano
{"title":"Randomized, crossover clinical trial on the safety, feasibility, and usability of the ABLE exoskeleton: A comparative study with knee-ankle-foot orthoses.","authors":"Antonio Rodríguez-Fernández, Joan Lobo-Prat, Mariona Tolrà-Campanyà, Florentina Pérez-Cañabate, Josep M Font-Llagunes, Lluis Guirao-Cano","doi":"10.1371/journal.pone.0318039","DOIUrl":"https://doi.org/10.1371/journal.pone.0318039","url":null,"abstract":"<p><p>Wearable exoskeletons are emerging as a new tool for gait training. However, comparisons between exoskeletons and conventional orthoses in terms of safety and feasibility are scarce. This study assessed the safety, feasibility, usability, and learning process of using the ABLE Exoskeleton in people with spinal cord injury (SCI) while comparing it with knee-ankle-foot orthoses (KAFOs). In this randomized, crossover clinical trial, 10 patients with chronic complete SCI (T4-T12) conducted a 10-session training and assessment protocol with each device: KAFOs and the ABLE Exoskeleton. Outcomes on safety (adverse events), and feasibility and usability (level of assistance, donning/doffing, therapy activities) were recorded for both devices. Evaluation sessions included standard clinical tests (Timed Up and Go, 10-Meter Walk Test, and 6-Minute Walk Test) to assess gait performance. The therapy metrics (number of steps, distance, gait speed, and standing and walking time) were recorded at each session for the robotic device. Participants quickly learned how to use the ABLE Exoskeleton, showing improvements in all therapy metrics (p<0.05) and the 6-Minute Walk Test (p<0.05). Participants reported less adverse events with the robotic device than KAFOs (17 and 31, respectively). Total donning and doffing time was 43 s faster with the robotic device using comparable levels of assistance. The time to complete the therapy activities was very similar between devices. Overall, participants needed 1 to 4 training sessions to perform essential therapy activities (sit/stand transitions, walking 10 meters, turning around) with both devices using minimum assistance or less. The results of this study show that it is feasible and safe for people with motor complete paraplegia due to SCI (T4-T12) to use the ABLE Exoskeleton for gait training in a rehabilitation hospital setting. The ABLE Exoskeleton proved to be as practical and easy to use as conventional orthoses, with fewer AEs reported when using the exoskeleton versus the KAFOs.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0318039"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144161066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PLoS ONEPub Date : 2025-05-27eCollection Date: 2025-01-01DOI: 10.1371/journal.pone.0325024
Zhanrong Li, Jiajie Han, Chao Jiang, Haosheng Su
{"title":"Region sampling NeRF-SLAM based on Kolmogorov-Arnold network.","authors":"Zhanrong Li, Jiajie Han, Chao Jiang, Haosheng Su","doi":"10.1371/journal.pone.0325024","DOIUrl":"https://doi.org/10.1371/journal.pone.0325024","url":null,"abstract":"<p><p>Currently, NeRF-based SLAM is rapidly developing in reconstructing and bitwise estimating indoor scenes. Compared with traditional SLAM, the advantage of the NeRF-based approach is that the error returns to the pixel itself, the optimization process is WYSIWYG, and it can also be differentiated for map representation. Still, it is limited by its MLP-based implicit representation to scale to larger and more complex environments. Inspired by the quadtree in ORB-SLAM2 and the recently proposed Kolmogorov-Arnold network, our approach replaces the MLP with a KAN network based on Gaussian functions, combines quadtree-based regional pixel sampling and random sampling, delineates the scene by voxels, and supports dynamic scaling to realize a high-fidelity reconstruction of large scenes for a SLAM system. Exposure compensation and VIT loss are also introduced to alleviate the necessity of NeRF on dense coverage, which significantly improves the ability to reconstruct sparse outdoor view environments stable. Experiments on three different types of datasets show that our approach reduces the trajectory error accuracy of indoor datasets from centimeter-level to millimeter-level compared to existing NeRF-based SLAM and achieves stable reconstruction in complex outdoor environments, considering the performance while ensuring efficiency.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0325024"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144161077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PLoS ONEPub Date : 2025-05-27eCollection Date: 2025-01-01DOI: 10.1371/journal.pone.0325308
Adil A Mahmoud, Ali Awadallah Saeed, Asim Ahmed Elnour, Osama, Nasreldin E M, Vineetha Menon, Semira Abdi Beshir, Sami Fatehi Abdalla, Abuelnor Mohammed, Mohamed Baraka, Fahad T Alsulami, Yousef Saeed Alqarni, Nadia Al Mazrouei, Khalid Awad Al-Kubaisi, Israa Yousif El Khidir, Kishore Ganana, Abdulla Al Amoodi
{"title":"Correction: A cross-sectional study on the assessment of adherence to cardiovascular medications in Sudan heart center.","authors":"Adil A Mahmoud, Ali Awadallah Saeed, Asim Ahmed Elnour, Osama, Nasreldin E M, Vineetha Menon, Semira Abdi Beshir, Sami Fatehi Abdalla, Abuelnor Mohammed, Mohamed Baraka, Fahad T Alsulami, Yousef Saeed Alqarni, Nadia Al Mazrouei, Khalid Awad Al-Kubaisi, Israa Yousif El Khidir, Kishore Ganana, Abdulla Al Amoodi","doi":"10.1371/journal.pone.0325308","DOIUrl":"https://doi.org/10.1371/journal.pone.0325308","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.1371/journal.pone.0315672.].</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0325308"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144161096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PLoS ONEPub Date : 2025-05-27eCollection Date: 2025-01-01DOI: 10.1371/journal.pone.0324595
Muhammad Rehan Naeem, Rashid Amin, Muhammad Farhan, Faisal S Alsubaei, Eesa Alsolami, Muhammad D Zakaria
{"title":"Cyber security Enhancements with reinforcement learning: A zero-day vulnerabilityu identification perspective.","authors":"Muhammad Rehan Naeem, Rashid Amin, Muhammad Farhan, Faisal S Alsubaei, Eesa Alsolami, Muhammad D Zakaria","doi":"10.1371/journal.pone.0324595","DOIUrl":"https://doi.org/10.1371/journal.pone.0324595","url":null,"abstract":"<p><p>A zero-day vulnerability is a critical security weakness of software or hardware that has not yet been found and, for that reason, neither the vendor nor the users are informed about it. These vulnerabilities may be taken advantage of by malicious people to execute cyber-attacks leading to severe effects on organizations and individuals. Given that nobody knows and is aware of these weaknesses, it becomes challenging to detect and prevent them. For the real-time zero-day vulnerabilities detection, we bring out a novel reinforcement learning (RL) methodology with the help of Deep Q-Networks (DQN). It works by learning the vulnerabilities without any prior knowledge of vulnerabilities, and it is evaluated using rigorous statistical metrics. Traditional methods are surpassed by this one that is able to adjust to changing threats and cope with intricate state spaces while providing scalability to cybersecurity personnel. In this paper, we introduce a new methodology that uses reinforcement learning for zero-day vulnerability detection. Zero-day vulnerabilities are security weaknesses that have never been exposed or published and are considered highly dangerous for systems and networks. Our method exploits reinforcement learning, a sub-type of machine learning which trains agents to make decisions and take actions to maximize an approximation of some underlying cumulative reward signal and discover patterns and features within data related to zero-day discovery. Training of the agent could allow for real-time detection and classification of zero-day vulnerabilities. Our approach will have the potential as a powerful tool of detection and defense against zero-day vulnerabilities and probably brings significant benefits to security experts and researchers in the field of cyber-security. The new method of discovering vulnerabilities that this approach provides has many comparative advantages over the previous approaches. It is applicable to systems with complex behaviour, such as the ones presented throughout this thesis, and can respond to new security threats in real time. Moreover, it does not require any knowledge about vulnerability itself. Because of that, it will discover hidden weak points. In the present paper, we analyzed the statistical evaluation of forecasted values for several parameters in a reinforcement learning environment. We have taken 1000 episodes for training the model and a further 1000 episodes for forecasting using the trained model. We used statistical measures in the evaluation, which showed that the Alpha value was at 0.10, thereby indicating good accuracy in the forecast. Beta was at 0.00, meaning no bias within the forecast. Gamma was also at 0.00, resulting in a very high level of precision within the forecast. MASE was 3.91 and SMAPE was 1.59, meaning that a very minimal percentage error existed within the forecast. The MAE value was at 6.34, while the RMSE was 10.22, meaning a relatively low average difference with","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 5","pages":"e0324595"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144161223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}