SRSF9 promotes cell proliferation and migration of glioblastoma through enhancing CDK1 expression.

BACKGROUND: Glioblastoma (GBM) is a highly aggressive and prevalent brain tumor that poses significant challenges in treatment. SRSF9, an RNA-binding protein, is essential for cellular processes and implicated in cancer progression. Yet, its function and mechanism in GBM need clarification. METHODS: Bioinformatics analysis was performed to explore differential expression of SRSF9 in GBM and its prognostic relevance to glioma patients. SRSF9 and CDK1 expression in GBM cell lines and patients' tissues were quantified by RT-qPCR, Western blot or immunofluorescence assay. The role of SRSF9 in GBM cell proliferation and migration was assessed by MTT, Transwell and colony formation assays. Additionally, transcriptional regulation of CDK1 by SRSF9 was investigated using ChIP-PCR and dual-luciferase assays. RESULTS: The elevated SRSF9 expression correlates to GBM stages and poor survival of glioma patients. Through gain-of-function and loss-of-function strategies, SRSF9 was demonstrated to promote proliferation and migration of GBM cells. Bioinformatics analysis showed that SRSF9 has an impact on cell growth pathways including cell cycle checkpoints and E2F targets. Mechanistically, SRSF9 appears to bind to the promoter of CDK1 gene and increase its transcription level, thus promoting GBM cell proliferation. CONCLUSIONS: These findings uncover the cellular function of SRSF9 in GBM and highlight its therapeutic potential for GBM.

DeepCBA: a deep learning framework for gene expression prediction in maize based on DNA sequence and chromatin interaction.

Chromatin interactions create spatial proximity between distal regulatory elements and target genes in the genome, which has an important impact on gene expression, transcriptional regulation, and phenotypic traits. To date, several methods have been developed for predicting gene expression. However, existing methods do not take into consideration the impact of chromatin interactions on target gene expression, thus potentially reduces the accuracy of gene expression prediction and mining of important regulatory elements. In this study, a highly accurate deep learning-based gene expression prediction model (DeepCBA) based on maize chromatin interaction data was developed. Compared with existing models, DeepCBA exhibits higher accuracy in expression classification and expression value prediction. The average Pearson correlation coefficients (PCC) for predicting gene expression using gene promoter proximal interactions, proximal-distal interactions, and proximal and distal interactions were 0.818, 0.625, and 0.929, respectively, representing an increase of 0.357, 0.16, and 0.469 over the PCC of traditional methods that only use gene proximal sequences. Some important motifs were identified through DeepCBA and were found to be enriched in open chromatin regions and expression quantitative trait loci (eQTL) and have the molecular characteristic of tissue specificity. Importantly, the experimental results of maize flowering-related gene ZmRap2.7 and tillering-related gene ZmTb1 demonstrate the feasibility of DeepCBA in exploring regulatory elements that affect gene expression. Moreover, the promoter editing and verification of two reported genes (ZmCLE7, ZmVTE4) demonstrated new insights of DeepCBA in precise designing of gene expression and even future intelligent breeding. DeepCBA is available at http://www.deepcba.com/ or http://124.220.197.196/.

U-Shaped Relationship Between Fibrinogen Level and 10-year Mortality in Patients With Acute Coronary Syndrome: Prospective Cohort Study.

This study demonstrated that fibrinogen is an independent risk factor for 10-year mortality in patients with acute coronary syndrome (ACS), with a U-shaped nonlinear relationship observed between the two. These findings underscore the importance of monitoring fibrinogen levels and the consideration of long-term anti-inflammatory treatment in the clinical management of patients with ACS.

Ru-Doped NiFe-MIL-53 with Facilitated Reconstruction and Active Hydrogen Supplement for Enhanced Nitrate Reduction.

The Electrochemical reduction of nitrate to ammonia (NH3) is a process of great significance to energy utilization and environmental protection. However, it suffers from sluggish multielectron/proton-involved steps involving coupling reactions between different reaction intermediates and active hydrogen species (Hads) produced by water decomposition. In this study, a Ru-doped NiFe-MIL-53 (NiFeRu-MIL-53) supported on Ni foam (NF) has been designed for the nitrate reduction reaction (NO3RR). The NiFeRu-MIL-53 exhibits excellent NO3RR activity with a maximum Faradaic efficiency (FE) of 100% at -0.4 V vs. RHE for NH3 and a maximum NH3 yield of 62.39 mg h-1 cm-2 at -0.7 V vs. RHE in alkaline media. This excellent performance for the NO3RR is attributed to a strong synergistic effect between Ru and reconstructed NiFe(OH)2. Additionally, the doped Ru facilitates water dissociation, leading to an appropriate supply of Hads required for N species hydrogenation during NO3RR, thereby further enhancing its performance. Furthermore, in situ Raman analysis reveals that incorporating Ru facilitates the reconstruction of MOFs and promotes the formation of hydroxide active species during the NO3RR process. This work provides a valuable strategy for designing electrocatalysts to improve the efficiency of the reduction of electrochemical nitrate to ammonia.

Topology Reconfiguration of Anion-Pillared Metal-Organic Framework from Flexibility to Rigidity for Enhanced Acetylene Separation.

Flexible metal-organic framework (MOF) adsorbents commonly encounter limitations in removing trace impurities below gate-opening threshold pressures. Topology reconfiguration can fundamentally eliminate intrinsic structural flexibility, yet remains a formidable challenge and is rarely achieved in practical applications. Herein, a solvent-mediated approach is presented to regulate the flexible CuSnF6-dpds-sql (dpds = 4,4''-dipyridyldisulfide) with sql topology into rigid CuSnF6-dpds-cds with cds topology. Notably, the cds topology is unprecedented and first obtained in anion-pillared MOF materials. As a result, rigid CuSnF6-dpds-cds exhibits enhanced C2H2 adsorption capacity of 48.61 cm3 g-1 at 0.01 bar compared to flexible CuSnF6-dpds-sql (21.06 cm3 g-1). The topology transformation also facilitates the adsorption kinetics for C2H2, exhibiting a 6.5-fold enhanced diffusion time constant (D/r2) of 1.71 × 10-3 s-1 on CuSnF6-dpds-cds than that of CuSnF6-dpds-sql (2.64 × 10-4 s-1). Multiple computational simulations reveal the structural transformations and guest-host interactions in both adsorbents. Furthermore, dynamic breakthrough experiments demonstrate that high-purity C2H4 (>99.996%) effluent with a productivity of 93.9 mmol g-1 can be directly collected from C2H2/C2H4 (1/99, v/v) gas-mixture in a single CuSnF6-dpds-cds column.

Universal scaling law for chiral antiferromagnetism.

The chiral antiferromagnetic (AFM) materials, which have been widely investigated due to their rich physics, such as non-zero Berry phase and topology, provide a platform for the development of antiferromagnetic spintronics. Here, we find two distinctive anomalous Hall effect (AHE) contributions in the chiral AFM Mn3Pt, originating from a time-reversal symmetry breaking induced intrinsic mechanism and a skew scattering induced topological AHE due to an out-of-plane spin canting with respect to the Kagome plane. We propose a universal AHE scaling law to explain the AHE resistivity ( ρ A H ) in this chiral magnet, with both a scalar spin chirality (SSC)-induced skew scattering topological AHE term, a s k and non-collinear spin-texture induced intrinsic anomalous Hall term, b i n . We found that a s k and b i n can be effectively modulated by the interfacial electron scattering, exhibiting a linear relation with the inverse film thickness. Moreover, the scaling law can explain the anomalous Hall effect in various chiral magnets and has far-reaching implications for chiral-based spintronics devices.

Semi-supervised bipartite graph construction with active EEG sample selection for emotion recognition.

Electroencephalogram (EEG) signals are derived from the central nervous system and inherently difficult to camouflage, leading to the recent popularity of EEG-based emotion recognition. However, due to the non-stationary nature of EEG, inter-subject variabilities become obstacles for recognition models to well adapt to different subjects. In this paper, we propose a novel approach called semi-supervised bipartite graph construction with active EEG sample selection (SBGASS) for cross-subject emotion recognition, which offers two significant advantages. Firstly, SBGASS adaptively learns a bipartite graph to characterize the underlying relationships between labeled and unlabeled EEG samples, effectively implementing the semantic connection for samples from different subjects. Secondly, we employ active sample selection technique in this paper to reduce the impact of negative samples (outliers or noise in the data) on bipartite graph construction. Drawing from the experimental results with the SEED-IV data set, we have gained the following three insights. (1) SBGASS actively rejects negative labeled samples, which helps mitigate the impact of negative samples when constructing the optimal bipartite graph and improves the model performance. (2) Through the learned optimal bipartite graph in SBGASS, the transferability of labeled EEG samples is quantitatively analyzed, which exhibits a decreasing tendency as the distance between each labeled sample and the corresponding class centroid increases. (3) Besides the improved recognition accuracy, the spatial-frequency patterns in emotion recognition are investigated by the acquired projection matrix.

Two-Dimensional Materials for Highly Efficient and Stable Perovskite Solar Cells.

Perovskite solar cells (PSCs) offer low costs and high power conversion efficiency. However, the lack of long-term stability, primarily stemming from the interfacial defects and the susceptible metal electrodes, hinders their practical application. In the past few years, two-dimensional (2D) materials (e.g., graphene and its derivatives, transitional metal dichalcogenides, MXenes, and black phosphorus) have been identified as a promising solution to solving these problems because of their dangling bond-free surfaces, layer-dependent electronic band structures, tunable functional groups, and inherent compactness. Here, recent progress of 2D material toward efficient and stable PSCs is summarized, including its role as both interface materials and electrodes. We discuss their beneficial effects on perovskite growth, energy level alignment, defect passivation, as well as blocking external stimulus. In particular, the unique properties of 2D materials to form van der Waals heterojunction at the bottom interface are emphasized. Finally, perspectives on the further development of PSCs using 2D materials are provided, such as designing high-quality van der Waals heterojunction, enhancing the uniformity and coverage of 2D nanosheets, and developing new 2D materials-based electrodes.

The tumor-intrinsic role of the m6A reader YTHDF2 in regulating immune evasion.

Tumors evade attacks from the immune system through various mechanisms. Here, we identify a component of tumor immune evasion mediated by YTH domain-containing family protein 2 (YTHDF2), a reader protein that usually destabilizes m6A-modified mRNA. Loss of tumoral YTHDF2 inhibits tumor growth and prolongs survival in immunocompetent tumor models. Mechanistically, tumoral YTHDF2 deficiency promotes the recruitment of macrophages via CX3CL1 and enhances mitochondrial respiration of CD8+ T cells by impairing tumor glycolysis metabolism. Tumoral YTHDF2 deficiency promotes inflammatory macrophage polarization and antigen presentation in the presence of IFN-γ. In addition, IFN-γ induces autophagic degradation of tumoral YTHDF2, thereby sensitizing tumor cells to CD8+ T cell-mediated cytotoxicity. Last, we identified a small molecule compound that preferentially induces YTHDF2 degradation, which shows a potent antitumor effect alone but a better effect when combined with anti-PD-L1 or anti-PD-1 antibodies. Collectively, YTHDF2 appears to be a tumor-intrinsic regulator that orchestrates immune evasion, representing a promising target for enhancing cancer immunotherapy.

Electrocardiogram-based prediction of conduction disturbances after transcatheter aortic valve replacement with convolutional neural network.

Aims: Permanent pacemaker implantation and left bundle branch block are common complications after transcatheter aortic valve replacement (TAVR) and are associated with impaired prognosis. This study aimed to develop an artificial intelligence (AI) model for predicting conduction disturbances after TAVR using pre-procedural 12-lead electrocardiogram (ECG) images. Methods and results: We collected pre-procedural 12-lead ECGs of patients who underwent TAVR at West China Hospital between March 2016 and March 2022. A hold-out testing set comprising 20% of the sample was randomly selected. We developed an AI model using a convolutional neural network, trained it using five-fold cross-validation and tested it on the hold-out testing cohort. We also developed and validated an enhanced model that included additional clinical features. After applying exclusion criteria, we included 1354 ECGs of 718 patients in the study. The AI model predicted conduction disturbances in the hold-out testing cohort with an area under the curve (AUC) of 0.764, accuracy of 0.743, F1 score of 0.752, sensitivity of 0.876, and specificity of 0.624, based solely on pre-procedural ECG images. The performance was better than the Emory score (AUC = 0.704), as well as the logistic (AUC = 0.574) and XGBoost (AUC = 0.520) models built with previously identified high-risk ECG patterns. After adding clinical features, there was an increase in the overall performance with an AUC of 0.779, accuracy of 0.774, F1 score of 0.776, sensitivity of 0.794, and specificity of 0.752. Conclusion: Artificial intelligence-enhanced ECGs may offer better predictive value than traditionally defined high-risk ECG patterns.

Trends in statin use for the primary prevention of atherosclerotic cardiovascular disease among US adults by demographic characteristics, 1999-2020.

PURPOSE: Atherosclerotic cardiovascular disease (ASCVD) is a leading cause of mortality worldwide. Statins, which are effective in preventing ASCVD, are underused, particularly for primary prevention. This study examined trends in statin use for primary ASCVD prevention from 1999 to 2020, focusing on demographic variations. METHODS: Utilizing data from the National Health and Nutrition Examination Survey, the present study includes individuals aged 18 years and older who had a greater than 10% risk of ASCVD over 10 years, and excluded patients with existing ASCVD. Subgroup analyses by demographic categories were performed. We calculated the changes in statin usage and used linear and quadratic tests to assess the linear and nonlinear trends in those changes. RESULTS: A total of 10,037 participants were included. Statin usage increased from 16.16% in 1999 to 36.24% in 2010, and 41.74% in 2020 (quadratic P-value < 0.001). In the 18-44 years age group, statin usage increased from 2.52% in 1999 to 8.14% in 2020 (linear P-value = 0.322), showing no significant linear trend. In the "never-married" group, statin usage increased from 19.16% in 1999 to 30.05% in 2020 (linear P-value = 0.256). CONCLUSION: Statin usage has shown a positive trend among populations requiring primary prevention for ASCVD. Currently, health policies are proving effective. However, the overall statin usage rate remains less than 50%. Additionally, young and never-married individuals should also receive special attention regarding statin usage as primary treatment for ASCVD.

Above-room-temperature chiral skyrmion lattice and Dzyaloshinskii-Moriya interaction in a van der Waals ferromagnet Fe3-xGaTe2.

Skyrmions in existing 2D van der Waals (vdW) materials have primarily been limited to cryogenic temperatures, and the underlying physical mechanism of the Dzyaloshinskii-Moriya interaction (DMI), a crucial ingredient for stabilizing chiral skyrmions, remains inadequately explored. Here, we report the observation of Néel-type skyrmions in a vdW ferromagnet Fe3-xGaTe2 above room temperature. Contrary to previous assumptions of centrosymmetry in Fe3-xGaTe2, the atomic-resolution scanning transmission electron microscopy reveals that the off-centered FeΙΙ atoms break the spatial inversion symmetry, rendering it a polar metal. First-principles calculations further elucidate that the DMI primarily stems from the Te sublayers through the Fert-Lévy mechanism. Remarkably, the chiral skyrmion lattice in Fe3-xGaTe2 can persist up to 330 K at zero magnetic field, demonstrating superior thermal stability compared to other known skyrmion vdW magnets. This work provides valuable insights into skyrmionics and presents promising prospects for 2D material-based skyrmion devices operating beyond room temperature.

The relationship between splenic dose and radiation-induced lymphopenia.

Lymphocytes, which are highly sensitive to radiation, play a crucial role in the body's defense against tumors. Radiation-induced lymphopenia has been associated with poorer outcomes in different cancer types. Despite being the largest secondary lymphoid organ, the spleen has not been officially designated as an organ at risk. This study hypothesizes a connection between spleen irradiation and lymphopenia and seeks to establish evidence-based dosage limits for the spleen. We retrospectively analyzed data from 96 patients with locally advanced gastric cancer who received postoperative chemoradiotherapy (CRT) between May 2010 and May 2017. Complete blood counts were collected before, during and after CRT. We established a model for predicting the minimum absolute lymphocyte count (Min ALC) and to investigate potential associations between spleen dosimetric variables and Min ALC. The median follow-up was 60 months. The 5-year overall survival (OS) and disease-free survival (DFS) were 65.2% and 56.8%, respectively. The median values of pre-treatment ALC, Min ALC and post-treatment ALC were 1.40 × 109, 0.23 × 109 and 0.28 × 109/L, respectively. Regression analysis confirmed that the primary tumor location, number of fractions and spleen V5 were significant predictors of Min ALC during radiation therapy. Changes in ALC (ΔALC) were identified as an independent predictor of both OS and DFS. Spleen V5 is an independent predictor for Min ALC, and the maximum dose of the spleen is associated with an increased risk of severe lymphopenia. Therefore, these doses should be restricted in clinical practice. Additionally, ΔALC can serve as a prognostic indicator for adjuvant radiotherapy in gastric cancer.

Transcriptomic and metabolomic profiles of Pirata subpiraticus in response to copper exposure.

Copper (Cu) contamination represents a persistent and significant form of heavy metal pollution in agricultural ecosystems, posing serious threats to organisms in current society. Spiders serve as crucial biological indicators for assessing the impact of heavy metals-induced toxicity. However, the specific molecular responses of spiders to Cu exposure and the mechanisms involved are not well understood. In our study, the wolf pond spiders, Pirata subpiraticus, were exposed to Cu for 21 d, resulting in a notable decline in survival rates compared with the control (n = 50, p < 0.05). We observed an increased expression of enzymes like glutathione peroxidase and superoxide dismutase (p < 0.05), signaling a strong oxidative stress response crucial for counteracting the harmful effects of reactive oxygen species. This response was corroborated by a rise in malondialdehyde levels (p < 0.05), a marker of lipid peroxidation and oxidative damage. Transcriptomic and metabolomic analyses revealed 2004 differentially expressed genes (DEGs) and 220 metabolites (DEMs). A significant number of these DEGs were involved in the glutathione biosynthetic process and antioxidant activity. A conjoint analysis revealed that under the Cu stress, several important enzymes and metabolites were altered (e.g., cathepsin A, legumain, and lysosomal acid lipase), affecting the activities of key biological processes and components, such as lysosome and insect hormone biosynthesis. Additionally, the protein interaction network analysis showed an up-regulation of processes like the apoptotic process, glutamate synthase activity, and peroxisome, suggesting that spiders activate cellular protective strategies to cope with stress and maintain homeostasis. This study not only deepens our understanding of spider biology in the context of environmental stress but also makes a significant contribution to the field of environmental stress biology.

Correction: Single molecule magnet features in luminescent lanthanide coordination polymers with heptacoordinate Dy/Yb(III) ions as nodes.

Correction for 'Single molecule magnet features in luminescent lanthanide coordination polymers with heptacoordinate Dy/Yb(III) ions as nodes' by Xiang-Tao Dong et al., Dalton Trans., 2023, 52, 12686-12694, https://doi.org/10.1039/D3DT02106H.

Validated numerical unrestrained occupant-seat crash scenarios for high-speed trains integrating experimental, computational, and inverse methods.

OBJECTIVE: Occupant impact safety is critical for train development. This paper proposes a systematic procedure for developing validated numerical occupant crash scenarios for high-speed trains by integrating experimental, computational, and inverse methods. METHODS: As the train interior is the most potentially injury-causing factor, the material properties were acquired by mechanical tests, and constitutive models were calibrated using inverse methods. The validity of the seat material constitutive model was further verified via drop tower tests. Finite element (FE) and multibody (MB) models of train occupant-seat interactions in frontal impact were established in LS-DYNA and MADYMO software, respectively, using the experimentally acquired materials/mechanical characteristics. Three dummy sled crash tests with different folding table and backrest configurations were conducted to validate the numerical occupant-seat models and to further assess occupant injury in train collisions. The occupant impact responses between dummy tests and simulations were quantitatively compared using a correlation and analysis (CORA) objective rating method. RESULTS: Results indicated that the experimentally calibrated numerical seat-occupant models could effectively reproduce the occupant responses in bullet train collisions (CORA scores >80%). Compared with the train seat-occupant MB model, the FE model could simulate the head acceleration with slightly more acceptable fidelity, however, the FE model CORA scores were slightly less than for the MB models. The maximum head acceleration was 30 g but the maximum HIC score was 17.4. When opening the folding table, the occupant's chest injury was not obvious, but the neck-table contact and "chokehold" may potentially be severe and require further assessment. CONCLUSIONS: This study demonstrates the value of experimental data for occupant-seat model interactions in train collisions and provides practical help for train interior safety design and formulation of standards for rolling stock interior passive safety.

Characterization of three lamp genes from largemouth bass (Micropterus salmoides): molecular cloning, expression patterns, and their transcriptional levels in response to fast and refeeding strategy.

Lysosomes-associated membrane proteins (LAMPs), a family of glycosylated proteins and major constituents of the lysosomal membranes, play a dominant role in various cellular processes, including phagocytosis, autophagy and immunity in mammals. However, their roles in aquatic species remain poorly known. In the present study, three lamp genes were cloned and characterized from Micropterus salmoides. Subsequently, their transcriptional levels in response to different nutritional status were investigated. The full-length coding sequences of lamp1, lamp2 and lamp3 were 1251bp, 1224bp and 771bp, encoding 416, 407 and 256 amino acids, respectively. Multiple sequence alignment showed that LAMP1-3 were highly conserved among the different fish species, respectively. 3-D structure prediction, genomic survey, and phylogenetic analysis were further confirmed that these genes are widely existed in vertebrates. The mRNA expression of the three genes was ubiquitously expressed in all selected tissues, including liver, brain, gill, heart, muscle, spleen, kidney, stomach, adipose and intestine, lamp1 shows highly transcript levels in brain and muscle, lamp2 displays highly expression level in heart, muscle and spleen, but lamp3 shows highly transcript level in spleen, liver and kidney. To analyze the function of the three genes under starvation stress in largemouth bass, three experimental treatment groups (fasted group and refeeding group, control group) were established in the current study. The results indicated that the expression of lamp1 was significant induced after starvation, and then returned to normal levels after refeeding in the liver. The expression of lamp2 and lamp3 exhibited the same trend in the liver. In addition, in the spleen and the kidney, the transcript level of lamp1 and lamp2 was remarkably increased in the fasted treatment group and slightly decreased in the refed treatment group, respectively. Collectively, our findings suggest that three lamp genes may have differential function in the immune and energetic organism in largemouth bass, which is helpful in understanding roles of lamps in aquatic species.

Evaporated Nickel Oxide Films with Slow Annealing and Interface Modification for Perovskite Solar Cells.

Electron-beam-evaporated nickel oxide (NiOx) films are known for their high quality, precise control, and suitability for complex structures in perovskite (PVK) solar cells (PSCs). However, untreated NiOx films have inherent challenges, such as surface defects, relatively low intrinsic conductivity, and shallow valence band maximum, which seriously restrict the efficiency and stability of the devices. To address these challenges, we employ a dual coordination optimization strategy. The strategy includes low heating rate annealing of NiOx films and using an aminoguanidine nitrate spin coating process on the surfaces of NiOx films to strategically modify NiOx films itself and the interface of NiOx/PVK. Under the synergistic effect of this dual optimization method, the quality of the films is significantly improved and its p-type characteristics are enhanced. At the same time, the interface defects and energy level alignment of the films are effectively improved, and the charge extraction ability at the interface is improved. The combined treatment significantly improved the efficiency of inverted PSCs, from 17.85% to 20.31%, and enhanced device stability under various conditions. This innovative dual-coordinated optimization strategy provides a clear and effective framework for improving the performance of NiOx films and inverted PSCs.

Study on the impact of COVID-19 pandemic on the mental health of Chinese college students: a cross-sectional analysis.

Background: The COVID-19 pandemic has significantly impacted the mental health of college students, prompting the need for universities to implement measures to mitigate these adverse effects. This study aims to assess the mental health status and mitigation measures of college students, identify the primary factors contributing to their mental health challenges, and provide suggestions for educational institutions to reduce negative psychological impacts. Methods: In February 2023, a questionnaire survey was conducted among 1,445 college students. Statistical analysis was performed on the survey results, and multiple regression models were used to identify significant influencing factors and optimize the model. Results: The study revealed correlations between factors affecting mental health during the pandemic, with interactions observed among some factors. Significant differences in mental health status were found among different groups of college students based on their information-sharing habits through apps and engagement in thesis research. Multiple regression analysis indicated that conducting academic research related to COVID-19 significantly increased the psychological stress of college students during the pandemic (p = 0.043). Among all mitigation measures, playing games demonstrated significant effectiveness in model analysis (p = 0.047). The optimization of the model showed that the multiple regression model considering the interaction of factors was more effective. Conclusion: Our research identifies crucial factors influencing the mental health of college students and investigates the mental health status of various student groups. We recommend that educational institutions adopt proactive strategies and a multifaceted approach to support the mental health of college students and address potential issues that may arise.

Enhancing thermal comfort prediction in high-speed trains through machine learning and physiological signals integration.

Heating, Ventilation, and Air Conditioning (HVAC) systems in high-speed trains (HST) are responsible for consuming approximately 70% of non-operational energy sources, yet they frequently fail to ensure provide adequate thermal comfort for the majority of passengers. Recent advancements in portable wearable sensors have opened up new possibilities for real-time detection of occupant thermal comfort status and timely feedback to the HVAC system. However, since occupant thermal comfort is subjective and cannot be directly measured, it is generally inferred from thermal environment parameters or physiological signals of occupants within the HST compartment. This paper presents a field test conducted to assess the thermal comfort of occupants within HST compartments. Leveraging physiological signals, including skin temperature, galvanic skin reaction, heart rate, and ambient temperature, we propose a Predicted Thermal Comfort (PTC) model for HST cabin occupants and establish an intelligent regulation model for the HVAC system. Nine input factors, comprising physiological signals, individual physiological characteristics, compartment seating, and ambient temperature, were formulated for the PTS model. In order to obtain an efficient and accurate PTC prediction model for HST cabin occupants, we compared the accuracy of different subsets of features trained by Machine Learning (ML) models of Random Forest, Decision Tree, Vector Machine and K-neighbourhood. We divided all the predicted feature values into four subsets, and did hyperparameter optimisation for each ML model. The HST compartment occupant PTC prediction model trained by Random Forest model obtained 90.4% Accuracy (F1 macro = 0.889). Subsequent sensitivity analyses of the best predictive models were then performed using SHapley Additive explanation (SHAP) and data-based sensitivity analysis (DSA) methods. The development of a more accurate and operationally efficient thermal comfort prediction model for HST occupants allows for precise and detailed feedback to the HVAC system. Consequently, the HVAC system can make the most appropriate and effective air supply adjustments, leading to improved satisfaction rates for HST occupant thermal comfort and the avoidance of energy wastage caused by inaccurate and untimely predictive feedback.