Performance on adsorption of toluene by ionic liquid-modified AC in high-humidity exhaust gas.

Volatile organic compounds (VOCs) frequently pose a threat to the biosphere, impacting ecosystems, flora, fauna, and the surrounding environment. Industrial emissions of VOCs often include the presence of water vapor, which, in turn, diminishes the adsorption capacity and efficacy of adsorbents. This occurs due to the competitive adsorption of water vapor, which competes with target pollutants for adsorption sites on the adsorbent material. In this study, hydrophobic activated carbons (BMIMPF6-AC (L), BMIMPF6-AC (g), and BMIMPF6-AC-H) were successfully prepared using 1-butyl-3-methylimidazolium hexafluorophosphate (BMIMPF6) to adsorb toluene under humidity environment. The adsorption performance and mechanism of the resulting ionic liquid-modified activated carbon for toluene in a high-humidity environment were evaluated to explore the potential application of ionic liquids as hydrophobic modifiers. The results indicated that BMIMPF6-AC-H exhibited superior hydrophobicity. The toluene adsorption capacity of BMIMPF6-AC-H was 1.53 times higher than that of original activated carbon, while the adsorption capacity for water vapor was only 37.30% of it at 27 °C and 77% RH. The Y-N model well-fitted the dynamic adsorption experiments. To elucidate the microscopic mechanism of hydrophobic modification, the Independent Gradient Model (IGM) method was employed to characterize the intermolecular interactions between BMIMPF6 and toluene. Overall, this study introduces a new modifier for hydrophobic modification of activated carbon, which could enhance the efficiency of activated carbon in treating industrial VOCs.

Endoscopic closure of large gastric defects with a novel through-the-scope closing device in a porcine model (with videos).

BACKGROUND AND AIM: After endoscopic full-thickness resection (EFTR), defects require a reliable and sustained closure. We present a novel, through-the-scope "bow-tie" (TTS-BT) closing device enabling direct defect closure without scope withdrawal. This preclinical study aimed to evaluate the feasibility and safety of this device for large defect closure after EFTR in a porcine model. METHODS: Exposed EFTR was performed for virtual lesions > 2 cm in the stomach of twelve pigs. Subsequently, TTS-BT closing devices were used for defect closure. Conventional metal clips were used to close any remaining defects. Gastroscopy was performed for 8 weeks to examine the wound sites and the pigs were subsequently sacrificed. After sacrificing the pigs, the wound healing was histologically verified by hematoxylin-eosin (HE) staining. The primary outcome was a successful closure rate, while the secondary outcomes were complete healing rate, closure time, and incidence of adverse events. RESULTS: The median long and short diameters of perforations were 4.0 (3.0-6.0) cm and 3.0 (2.0-4.0) cm, respectively. Defect closure using novel TTS-BT closure devices and conventional metal clips was successfully performed in all pigs. Complete healing was achieved in the defects of 12 pigs. The median closure time was 13 (9-38) minutes. No serious adverse events occurred during the 8-week follow-up. CONCLUSIONS: The novel TTS-BT closure device is feasible and safe for closing large gastric perforations and could be a promising tool for clinical practice.

Synthesis, in vitro antitumor evaluation and structure activity relationship of heptacoordinated amino-bis(Phenolato) Ti(IV) complexes stabilized by 2,6-dipicolinic acid.

Eighteen novel Ti(IV) complexes stabilized by different chelating amino-bis(phenolato) (ONNO, ONON, ONOO) ligands and 2,6-dipicolinic acid as a second chelator were synthesized with isolated yields ranging from 79 to 93%. Complexes were characterized by 1H and 13C-NMR spectroscopy, as well as by HRMS and X-Ray diffraction analysis. The good to excellent aqueous stability of these Ti(IV) complexes can be modulated by the substitutions on the 2-position of the phenolato ligands. Most of the synthesized Ti(IV) complexes demonstrated potent inhibitory activity against Hela S3 and Hep G2 tumor cells. Among them, the naphthalenyl based Salan type 2j, 2-picolylamine based [ONON] type 2n and N-(2-hydroxyethyl) based [ONOO] type 2p demonstrated up to 40 folds enhanced cytotoxicity compared to cisplatin together with a significantly reduced activity against healthy AML12 cells. The three Ti(IV) complexes exhibited fast cellular uptake by Hela S3 cells and induced almost exclusively apoptosis. 2j could trigger higher level of ROS generation than 2p and 2n.

Gases and gas-releasing materials for the treatment of chronic diabetic wounds.

Chronic non-healing wounds are a common consequence of skin ulceration in diabetic patients, with severe cases such as diabetic foot even leading to amputations. The interplay between pathological factors like hypoxia-ischemia, chronic inflammation, bacterial infection, impaired angiogenesis, and accumulation of advanced glycosylation end products (AGEs), resulting from the dysregulation of the immune microenvironment caused by hyperglycemia, establishes an unending cycle that hampers wound healing. However, there remains a dearth of sufficient and effective approaches to break this vicious cycle within the complex immune microenvironment. Consequently, numerous scholars have directed their research efforts towards addressing chronic diabetic wound repair. In recent years, gases including Oxygen (O2), Nitric oxide (NO), Hydrogen (H2), Hydrogen sulfide (H2S), Ozone (O3), Carbon monoxide (CO) and Nitrous oxide (N2O), along with gas-releasing materials associated with them have emerged as promising therapeutic solutions due to their ability to regulate angiogenesis, intracellular oxygenation levels, exhibit antibacterial and anti-inflammatory effects while effectively minimizing drug residue-induced damage and circumventing drug resistance issues. In this review, we discuss the latest advances in the mechanisms of action and treatment of these gases and related gas-releasing materials in diabetic wound repair. We hope that this review can provide different ideas for the future design and application of gas therapy for chronic diabetic wounds.

Next-generation anti-PD-L1/IL-15 immunocytokine elicits superior antitumor immunity in cold tumors with minimal toxicity.

The clinical applications of immunocytokines are severely restricted by dose-limiting toxicities. To address this challenge, here we propose a next-generation immunocytokine concept involving the design of LH05, a tumor-conditional anti-PD-L1/interleukin-15 (IL-15) prodrug. LH05 innovatively masks IL-15 with steric hindrance, mitigating the "cytokine sink" effect of IL-15 and reducing systemic toxicities associated with wild-type anti-PD-L1/IL-15. Moreover, upon specific proteolytic cleavage within the tumor microenvironment, LH05 releases an active IL-15 superagonist, exerting potent antitumor effects. Mechanistically, the antitumor efficacy of LH05 depends on the increased infiltration of CD8+ T and natural killer cells by stimulating the chemokines CXCL9 and CXCL10, thereby converting cold tumors into hot tumors. Additionally, the tumor-conditional anti-PD-L1/IL-15 can synergize with an oncolytic virus or checkpoint blockade in advanced and metastatic tumor models. Our findings provide a compelling proof of concept for the development of next-generation immunocytokines, contributing significantly to current knowledge and strategies of immunotherapy.

BRD4L cooperates with MYC to block local tumor invasion via suppression of S100A10.

Targeted therapy based on BRD4 and MYC shows promise due to their well-researched oncogenic functions in cancer, but their tumor-suppressive roles are less understood. In this study, we employ a systematic approach to delete exons that encode the low-complexity domain (LCD) of BRD4L in cells by using CRISPR-Cas9. In particular, the deletion of exon 14 (BRD4-E14) results in cellular morphological changes towards spindle-shaped and loosely packed. BRD4-E14 deficient cells show increased cell migration and reduced cell adhesion. The expression of S100A10 was significantly increased in cells lacking E14. BRD4L binds with MYC via the E14-encoded region of the LCD to inhibit the expression of S100A10. In cancer tissues, there is a positive correlation between BRD4 and MYC, while both of these proteins are negatively associated with S100A10 expression. Finally, knocking out the BRD4-E14 region or MYC promotes tumor growth in vivo. Together, these data support a tumor-suppressive role of BRD4L and MYC in some contexts. This discovery emphasizes the significance of a discreetly design and precise patient recruitment in clinical trials that testing cancer therapy based BRD4 and MYC.

Competitive-like binding between carbon black and CTNNB1 to ΔNp63 interpreting the abnormal respiratory epithelial repair after injury.

Airway epithelium is extraordinary vulnerable to damage owning to continuous environment exposure. Subsequent repair is therefore essential to restore the homeostasis of respiratory system. Disruptions in respiratory epithelial repair caused by nanoparticles exposure have been linked to various human diseases, yet implications in repair process remain incompletely elucidated. This study aims to elucidate the key stage in epithelial repair disturbed by carbon black (CB) nanoparticles, highlighting the pivotal role of ΔNp63 in mediating the epithelium repair. A competitive-like binding between CB and beta-catenin 1 (CTNNB1) to ΔNp63 is proposed to elaborate the underlying toxicity mechanism. Specifically, CB exhibits a remarkable inhibitory effect on cell proliferation, leading to aberrant airway epithelial repair, as validated in air-liquid culture. ΔNp63 drives efficient epithelial proliferation during CB exposure, and CTNNB1 was identified as a target of ΔNp63 by bioinformatics analysis. Further molecular dynamics simulation reveals that oxygen-containing functional groups on CB disrupt the native interaction of CTNNB1 with ΔNp63 through competitive-like binding pattern. This process modulates CTNNB1 expression, ultimately restraining proliferation during respiratory epithelial repair. Overall, the current study elucidates that the diminished interaction between CTNNB1 and ΔNp63 impedes respiratory epithelial repair in response to CB exposure, thereby enriching the public health risk assessment on CB-related respiratory diseases.

Defoliation, trampling and nutrient return differentially influence grassland productivity by modulating trait-dependent plant community composition: insights from a simulated grazing experiment.

Ungulate grazing involves multiple components, including defoliation, dung and urine return, and trampling, which supply offsetting or synergistic effects on plant community composition and productivity (ANPP), but these effects have not been fully studied. Plant functional traits may reflect the response of plants to disturbance and their impact on ecosystem functions. Species turnover and intraspecific trait variation (ITV) are important drivers of community trait composition. We conducted a simulated grazing experiment in a steppe grassland in northern China to examine the effects of defoliation, dung and urine return, and trampling on community-weighted mean (CWM), functional diversity (FD) and ANPP, and to disentangle the roles of species turnover and ITV in driving these changes. We found that defoliation had a dominant effect on CWMs and FDs of all four traits through species turnover and ITV, respectively, resulting in a convergence of traits towards as more resource-acquisitive strategy. Dung-urine return resulted in more resource-acquisitive community traits mainly through ITV, whereas there were no significant effects on FDs except for leaf C/N. Trampling increased CWM of leaf dry matter content primarily driven by ITV, and had no significant effect on FDs. Furthermore, our simulated grazing positively affected ANPP, primarily due to nutrient additions from dung and urine, and ITV largely explained the variation in ANPP. These findings highlight the multifaceted effects of grazing components on community structure and ANPP, and the significance of ITV in shaping grassland plant communities and productivity.

Comparative efficacy and safety of JAK inhibitors in the treatment of moderate-to-severe alopecia areata: a systematic review and network meta-analysis.

We performed a Bayesian network meta-analysis to indirectly compare the relative efficacy and safety of the latest JAK inhibitors for moderate-to-severe alopecia areata (AA). 13 trials totaling 3,613 patients were included. Two low-dose groups of oral formulations (ritlecitinib 10mg and ivarmacitinib 2mg) and two topical formulations (delgocitinib ointment and ruxolitinib cream) appeared to be relatively ineffective against moderate-to-severe AA. Ranking analysis suggested that brepocitinib 30mg has the best relative effect in reducing the SALT score (sucra = 0.9831), and demonstrated comparable efficacy to deuruxolitinib 12mg (sucra = 0.9245), followed by deuruxolitinib 8mg (sucra = 0.7736). Regarding the SALT50 response, brepocitinib 30mg ranked highest (sucra = 0.9567), followed by ritlecitinib 50mg (sucra = 0.8689) and deuruxolitinib 12mg (sucra = 0.7690). For achieving the SALT75 response, deuruxolitinib 12mg had the highest probability (sucra = 0.9761), followed by deuruxolitinib 8mg (sucra = 0.8678) and brepocitinib 30mg (sucra = 0.8448). Deuruxolitinib 12mg might be the most effective therapy for patients with severe AA (sucra = 0.9395), followed by ritlecitinib 50mg (sucra = 0.8753) and deuruxolitinib 8mg (sucra = 0.8070). Deuruxolitinib 12mg/8mg demonstrated notable efficacy for moderate-to-severe AA, and is expected to be a new treatment option for AA. It was worth noting that deuruxolitinib exhibit a greater likelihood of causing adverse events in comparison to other JAK inhibitors. Ritlecitinib 50mg seemed to exhibit fewer adverse effects in the high-dose groups of oral JAK inhibitors and might be an optimal choice to balance safety and efficacy. The majority of JAK inhibitors exhibited acceptable short-term safety profiles. To enhance the applicability and accuracy of our research, further head-to-head trials with longer follow-up periods are needed. Systematic Review Registration: identifier [CRD42022368012].

Research progress on the pharmacological activity, biosynthetic pathways, and biosynthesis of crocins.

Crocins are water-soluble apocarotenoids isolated from the flowers of crocus and gardenia. They exhibit various pharmacological effects, including neuroprotection, anti-inflammatory properties, hepatorenal protection, and anticancer activity. They are often used as coloring and seasoning agents. Due to the limited content of crocins in plants and the high cost of chemical synthesis, the supply of crocins is insufficient to meet current demand. The biosynthetic pathways for crocins have been elucidated to date, which allows the heterologous production of these valuable compounds in microorganisms by fermentation. This review article provides a comprehensive overview of the chemistry, pharmacological activity, biosynthetic pathways, and heterologous production of crocins, aiming to lay the foundation for the large-scale production of these valuable natural products by using engineered microbial cell factories.

Building and Validation of an Acute Event Prediction Model for Severe Mental Disorders.

Background: The global incidence of acute events in psychiatric patients is intensifying, and models to successfully predict acute events have attracted much attention. Objective: To explore the influence factors of acute incident severe mental disorders (SMDs) and the application of Rstudio statistical software, and build and verify a nomogram prediction model. Methods: SMDs were taken as research objects. The questionnaire survey method was adopted to collect data. Patients with acute event independent factors were screened. R software multivariable Logistic regression model was constructed and a nomogram was drawn. Results: A total of 342 patients with SMDs were hospitalized, and the number of patients who encountered acute events was 64, which accounted for 18.70% of all patients. Statistical significances were found in many aspects (all P ˂ 0.05). Such aspects included Medication adherence, disease diagnosis, marital status, caregivers, social support and the hospitalization environment (odds ratio (OR) = 4.08, 11.62, 12.06, 10.52, 0.04 and 0.61, respectively) were independent risk factors for the acute events of patients with SMDs. The prediction model was modeled, and the AUC was 0.77 and 0.80. The calibration curve shows that the model has good calibration. The clinical decision curve shows that the model has a good clinical effect. Conclusion: The constructed risk prediction model shows good prediction effectiveness in the acute events of patients with SMDs, which is helpful for the early detection of clinical mental health staff at high risk of acute events.

Translation and validation of the Chinese self-report version of Spinal Cord Independence Measure (SCIM-SR): Rasch psychometric analysis and online application.

Spinal Cord Independence Measure (SCIM) was an important functional outcome measure specifically designed for spinal cord injury (SCI) patients, with the self-reported version of SCIM (SCIM-SR) published in 2013. This study aims to translate the SCIM-SR into Chinese, and to investigate the validity of Chinese SCIM-SR among SCI patients. This Chinese version of SCIM-SR was translated into Chinese in a standardized approach, and then filled out by a sample of patients with SCI (n = 205) within 3 days after admission. Validity of Chinese SCIM-SR was then analyzed using Rasch analysis and principal component analysis. The subscale Selfcare and subscale Mobility showed good fit to the Rasch model, with no significance found in Chi-square test results for item-trait interaction, using Bonferroni adjustment for the significant level (χ2 =18.125, P = 0.111; χ2 =33.629, P = 0.006). Mean fit residual for items and persons of each subscale were within ± 2.5. The model fit of the subscale of Respiration and Sphincter Management was not satisfactory even after deleting one item and merging two items with local dependence. However, Kaiser-Meyer-Olkin test was > 0.50 in total score and all the subscales of Chinese SCIM-SR, and P < 0.05 in the Bartlett's test. There was no differential item functioning for gender, time post injury, age, and etiology in any of the three subscales. An online version of Chinese SCIM-SR was also developed. It is concluded that the SCIM-SR in Chinese is valid for application in individuals with SCI. SCIM-SR is considered as an important tool for self-reporting functional status from SCI individuals' perspective.

A nomogram to predict the risk of acute ischemic stroke in patients with maintenance hemodialysis: a retrospective cohort study.

OBJECTIVE: Acute ischemic stroke (AIS) stands as a leading cause of death and disability globally. This study aimed to investigate the risk factors linked with AIS in patients undergoing maintenance hemodialysis (MHD) and to create and validate nomogram models. METHODS: We examined the medical records of 314 patients with stage 5 chronic kidney disease (CKD5) undergoing MHD, who sought neurology outpatient department consultation for suspected AIS symptoms between January 2018 and December 2023. These 314 patients were randomly divided into the training cohort (n=222) and validation cohort (n=92). The Least Absolute Shrinkage Selection Operator (LASSO) regression model was employed for optimal feature selection in the AIS risk model. Subsequently, multivariable logistic regression analysis was used to construct a predictive model incorporating the features selected through LASSO. This predictive model's performance was assessed using the C-index and the area under the receiver operating characteristic curve (AUC). Additionally, calibration and clinical utility were evaluated through calibration plots and decision curve analysis (DCA). The model's internal validation was conducted using the validation cohort. Resaults: Predictors integrated into the prediction nomogram encompassed cardiovascular disease (CVD) (Odds Ratio [OR] 7.95, 95% confidence interval [CI] 2.400-29.979), smoking (OR 5.7, 95% CI 1.661-21.955), dialysis time (OR 5.91, 95% CI 5.866-29.979), low-density lipoprotein (LDL) (OR 2.99, 95% CI 0.751-13.007), and fibrin degradation products (FDP) (OR 5.47, 95% CI 1.563-23.162). The model exhibited robust discrimination, with a C-index of 0.877 and 0.915 in the internal training and validation cohorts, respectively. The AUC for the training set was 0.857, and a similar AUC of 0.905 was achieved in the validation cohort. Decision curve analysis (DCA) demonstrated a positive net benefit within a threshold risk range of 2 to 96%. CONCLUSION: The proposed nomogram effectively identifies MHD patients at high risk of AIS at an early stage. This model holds the potential to aid clinicians in making preventive recommendations.

Ethical and regulatory challenges of large language models in medicine.

With the rapid growth of interest in and use of large language models (LLMs) across various industries, we are facing some crucial and profound ethical concerns, especially in the medical field. The unique technical architecture and purported emergent abilities of LLMs differentiate them substantially from other artificial intelligence (AI) models and natural language processing techniques used, necessitating a nuanced understanding of LLM ethics. In this Viewpoint, we highlight ethical concerns stemming from the perspectives of users, developers, and regulators, notably focusing on data privacy and rights of use, data provenance, intellectual property contamination, and broad applications and plasticity of LLMs. A comprehensive framework and mitigating strategies will be imperative for the responsible integration of LLMs into medical practice, ensuring alignment with ethical principles and safeguarding against potential societal risks.

Producing high-quantity and high-quality recombinant adeno-associated virus by low-cis triple transfection.

Recombinant adeno-associated virus (rAAV)-based gene therapy is entering clinical and commercial stages at an unprecedented pace. Triple transfection of HEK293 cells is currently the most widely used platform for rAAV manufacturing. Here, we develop low-cis triple transfection that decreases transgene plasmid use by 10- to 100-fold and overcomes several major limitations associated with standard triple transfection. This new method improves packaging of yield-inhibiting transgenes by up to 10-fold, and generates rAAV batches with reduced plasmid backbone contamination that otherwise cannot be eliminated in downstream processing. When tested in mice and compared with rAAV produced by standard triple transfection, low-cis rAAV shows comparable or superior potency and results in diminished plasmid backbone DNA and RNA persistence in tissue. Mechanistically, low-cis triple transfection relies on the extensive replication of transgene cassette (i.e., inverted terminal repeat-flanked vector DNA) in HEK293 cells during production phase. This cost-effective method can be easily implemented and is widely applicable to producing rAAV of high quantity, purity, and potency.

The effectiveness of virtual reality technology in student nurse education: A systematic review and meta-analysis.

AIM: The purpose of this study was to analyze the effectiveness of virtual reality technology in nursing education. BACKGROUND: Virtual reality technology is regarded as one of the advanced and significant instructional tools in contemporary education. However, its effectiveness in nursing education remains a subject of debate, and there is currently limited comprehensive research discussing the impact of varying degrees of virtual technology on the educational effectiveness of nursing students. DESIGN: Systematic review and meta-analysis. METHODS: The present systematic review and meta-analysis were applied according to the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) statement. The PubMed, Embase, CINAHL, ProQuest, Cochrane Library, Web of Science, and Scopus were searched for relevant articles in the English language. The methodologies of the studies evaluated were assessed using Cochrane Risk of Bias2 (ROB 2) tool and Joanna Briggs Institute (JBI) assessment tool. We took the learning satisfaction, knowledge, and skill performance of nursing students as the primary outcomes, and nursing students' self-efficacy, learning motivation, cognitive load, clinical reasoning, and communication ability were assessment as secondary outcomes. The meta-analysis was performed using R 4.3.2 software according to PRISMA guidelines. Heterogeneity was assessed by I2 and P statistics. Standardized mean difference (SMD) and 95 % confidence intervals (CIs) were used as effective indicators. RESULTS: Twenty-six studies were reviewed, which involved 1815 nursing students. The results showed that virtual reality teaching, especially immersive virtual reality, was effective in improving nursing students' learning satisfaction (SMD: 0.82, 95%CI: 0.53-1.11, P < 0.001), knowledge (SMD: 0.56, 95%CI: 0.34-0.77, P < 0.001), skill performance (SMD: 1.13, 95 % CI: 0.68-1.57, P < 0.001), and self-efficacy (SMD: 0.64, 95%CI: 0.21,1.07, P < 0.001) compared to traditional teaching methods. However, the effects of virtual reality technology on nursing students' motivation, cognitive load, clinical reasoning, and communication ability were not significant and require further research. CONCLUSIONS: The results of this study show that virtual reality technology has a positive impact on nursing students. Nonetheless, it is crucial not to underestimate the effectiveness of traditional education methods, and future research could analyze the impact of different populations on nursing education while improving virtual reality technology, to more comprehensively explore how to improve the quality of nursing education. Moreover, it is imperative to emphasize the integration of virtual education interventions with real-world experiences promptly. This integration is essential for bridging the gap between the virtual learning environment and real-life scenarios effectively. REGISTRATION NUMBER: CRD42023420497 (https://www.crd.york.ac.uk/PROSPERO/#recordDetails).

Lanthanide-based nanomaterials for temperature sensing in the near-infrared spectral region: illuminating progress and challenges.

Being first proposed as a method to overcome limitations associated with conventional contact thermometers, luminescence thermometry has been extensively studied over the past two decades as a sensitive and fast approach to remote and minimally invasive thermal sensing. Herein, lanthanide (Ln)-doped nanoparticles (Ln-NPs) have been identified as particularly promising candidates, given their outstanding optical properties. Known primarily for their upconversion emission, Ln-NPs have also been recognized for their ability to be excited with and emit in the near-infrared (NIR) regions matching the NIR transparency windows. This sparked the emergence of the development of NIR-NIR Ln-NPs for a wide range of temperature-sensing applications. The shift to longer excitation and emission wavelengths resulted in increased efforts being put into developing nanothermometers for biomedical applications, however most research is still preclinical. This mini-review outlines and addresses the challenges that limit the reliability and implementation of luminescent nanothermometers to real-life applications. Through a critical look into the recent developments from the past 4 years, we highlight attempts to overcome some of the limitations associated with excitation wavelength, thermal sensitivity, calibration, as well as light-matter interactions. Strategies range from use of longer excitation wavelengths, brighter emitters through strategic core/multi-shell architectures, exploitation of host phonons, and a shift from double- to single-band ratiometric as well as lifetime-based approaches to innovative methods based on computation and machine learning. To conclude, we offer a perspective on remaining gaps and where efforts should be focused towards more robust nanothermometers allowing a shift to real-life, e.g., in vivo, applications.

Oriented feature pyramid network for small and dense wheat heads detection and counting.

Wheat head detection and counting using deep learning techniques has gained considerable attention in precision agriculture applications such as wheat growth monitoring, yield estimation, and resource allocation. However, the accurate detection of small and dense wheat heads remains challenging due to the inherent variations in their size, orientation, appearance, aspect ratios, density, and the complexity of imaging conditions. To address these challenges, we propose a novel approach called the Oriented Feature Pyramid Network (OFPN) that focuses on detecting rotated wheat heads by utilizing oriented bounding boxes. In order to facilitate the development and evaluation of our proposed method, we introduce a novel dataset named the Rotated Global Wheat Head Dataset (RGWHD). This dataset is constructed by manually annotating images from the Global Wheat Head Detection (GWHD) dataset with oriented bounding boxes. Furthermore, we incorporate a Path-aggregation and Balanced Feature Pyramid Network into our architecture to effectively extract both semantic and positional information from the input images. This is achieved by leveraging feature fusion techniques at multiple scales, enhancing the detection capabilities for small wheat heads. To improve the localization and detection accuracy of dense and overlapping wheat heads, we employ the Soft-NMS algorithm to filter the proposed bounding boxes. Experimental results indicate the superior performance of the OFPN model, achieving a remarkable mean average precision of 85.77% in oriented wheat head detection, surpassing six other state-of-the-art models. Moreover, we observe a substantial improvement in the accuracy of wheat head counting, with an accuracy of 93.97%. This represents an increase of 3.12% compared to the Faster R-CNN method. Both qualitative and quantitative results demonstrate the effectiveness of the proposed OFPN model in accurately localizing and counting wheat heads within various challenging scenarios.

Neural Q-learning for discrete-time nonlinear zero-sum games with adjustable convergence rate.

In this paper, an adjustable Q-learning scheme is developed to solve the discrete-time nonlinear zero-sum game problem, which can accelerate the convergence rate of the iterative Q-function sequence. First, the monotonicity and convergence of the iterative Q-function sequence are analyzed under some conditions. Moreover, by employing neural networks, the model-free tracking control problem can be overcome for zero-sum games. Second, two practical algorithms are designed to guarantee the convergence with accelerated learning. In one algorithm, an adjustable acceleration phase is added to the iteration process of Q-learning, which can be adaptively terminated with convergence guarantee. In another algorithm, a novel acceleration function is developed, which can adjust the relaxation factor to ensure the convergence. Finally, through a simulation example with the practical physical background, the fantastic performance of the developed algorithm is demonstrated with neural networks.