A hybrid recommendation algorithm based on user nearest neighbor model.

In the realm of e-commerce, personalized recommendations are a crucial component in enhancing user experience and optimizing sales efficiency. To address the inherent sparsity challenge prevalent in collaborative filtering algorithms within personalized recommendation systems, we propose a novel hybrid e-commerce recommendation algorithm based on the User-Nearest-Neighbor model. By integrating the user nearest neighbor model with other recommendation algorithms, this approach effectively mitigates data sparsity and facilitates a more nuanced understanding of the user-product relationship, consequently elevating recommendation quality and enhancing user experience. Taking into account considerations such as data scale and recommendation performance, we conducted experiments utilizing the Spark distributed platform. Empirical findings demonstrate the superiority of our hybrid algorithm over standalone collaborative filtering algorithms across various recommendation indicators.

Pharmacological Inhibition or Silencing of TREM1 Restrains HCC Cell Metastasis by Inactivating TLR/PI3K/AKT Signaling.

Hepatocellular carcinoma (HCC), a widely prevalent malignancy strongly linked to inflammation, remains a significant public health concern. Triggering receptor expressed on myeloid cells 1 (TREM1), a modulator of inflammatory responses identified in recent years, has emerged as a crucial facilitator in cancer progression. Despite its significance, the precise regulatory mechanism of TREM1 in HCC metastasis remains unanswered. In the present investigation, we observed aberrant upregulation of TREM1 in HCC tissues, which was significantly linked to poorer overall survival. Inhibition of TREM1 expression resulted in a significant reduction in HCC Huh-7 and MHCC-97H cell proliferation, invasion, and epithelial-mesenchymal transition (EMT) process. Furthermore, inhibiting TREM1 decreased protein expressions of toll-like receptor 2/4 (TLR2/4) and major myeloid differentiation response gene 88 (MyD88), leading to the inactivation of phosphatidylinositol 3-kinase (PI3K) and protein kinase B (AKT) in HCC cells. Notably, these effects were reversed by treatment with TLR2-specific agonist (CU-T12-9), indicating a potential crosstalk between TREM1 and TLR2/4. Mechanistic studies revealed a direct interaction between TREM1 and both TLR2 and TLR4. In vivo studies demonstrated that inhibition of TREM1 suppressed the growth of HCC cells in the orthotopic implant model and its metastatic potential in the experimental lung metastasis model. Overall, our findings underscore the role of TREM1 inhibition in regulating EMT and metastasis of HCC cells by inactivating the TLR/PI3K/AKT signaling pathway, thereby providing deeper mechanistic insights into how TREM1 regulates metastasis during HCC progression.

Bedside ultrasound-assisted puncture and drainage under local anesthesia: A novel approach for early post-operative space-occupying tumor bed cysts of glioma resection.

OBJECTIVES: To investigate the causes of space-occupying tumor bed cysts formed early after glioma resection by measuring the osmotic pressure gradient between cystic fluid, serum, and cerebrospinal fluid (CSF) and propose a new method of bedside ultrasound-assisted puncture and drainage (UAP&D) under local anesthesia for treatment. METHODS: Bedside UAP&D under local anesthesia was performed through a burr hole on the skull flap.Following a successful puncture, cystic fluid was collected, while blood and CSF were obtained through vein and lumbar puncture, respectively. The osmotic pressure of all fluids collected was measured. The appearance, biochemical composition, and results of microbial culture of cystic fluid and CSF were analyzed. Within 24 h after UAP&D, a CT examination and Glasgow coma scale (GCS) were assessed. RESULTS: The osmotic pressure of cystic fluid was higher than that of serum and CSF. White blood cell count and protein concentration were higher in the cystic fluid compared to the CSF. Conversely, the concentration of chloride ions and glucose were lower. CT scan confirmed the correct placement of the cysts' drainage tube and that the cysts' volume decreased significantly with continued drainage. Accompanied by a reduction in the volume of cysts, there were significant improvements in GCS score within 24 h after UAP&D. All drainage tubes were removed within 2-5 days, and no puncture tract hemorrhage or infection was observed. CONCLUSION: The osmotic pressure gradient between cystic fluid, serum, and CSF caused the formation of early post-operative space-occupying tumor bed cysts for glioma. UAP&D aligns with the concept that micro-invasive neurosurgery is an effective treatment method for such cysts.

PRM1201 effectively inhibits colorectal cancer metastasis via shaping gut microbiota and short- chain fatty acids.

BACKGROUND: PRM1201 is a traditional medicine with beneficial effects against colorectal cancer (CRC) metastasis. However, the underlying mechanism of this action remains to be determined. HYPOTHESIS: Remodeling microbiota and short-chain fatty acids (SCFAs) metabolism might be a potential mechanism to explain the anti-metastatic action of PRM1201, as this gut-microbiota dependent effect involves downregulation of histone deacetylation and EMT. METHODS: To investigate this possibility, clinical specimens were sequenced and the correlation between the anti-metastatic efficacy of PRM1201 and the restoration of SCFA-producing bacteria was studied. To obtain solid causal evidence, a mouse metastasis model was established to detect the influence of PRM1201 on cancer metastasis. Specifically, 16S amplicon sequencing, ultra-high performance liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS) analysis, and bacterial manipulation were used to examine the gut microbiota-driven anti-metastatic action of PRM1201. RESULTS: Clinical data showed that PRM1201 increased both the number of SCFA-producing bacteria and generation of SCFAs in the feces of CRC patients. A positive correlation between the anti-metastatic efficacy of PRM1201 and the restoration of SCFAs observed. The animal experiments demonstrated that PRM1201 effectively blocked CRC metastasis in a dose-dependent manner. PRM1201 treatment modulated the composition of gut microbiota, and promoted the proliferation of beneficial SCFAs producers such as Akkermansia, Lachnospiraceae_NK4A136_group and Blautia, while simultaneously reducing the abundance of pathogenic bacteria like Escherichia-Shigella. In addition, PRM1201 led to augmentation of SCFAs content. Further results indicated that the anti-cancer metastatic mechanism of PRM1201 was linked to inhibition of histone deacetylation and suppression of epithelial-to-mesenchymal transition (EMT) in metastatic lesions. Microbiota depletion treatment and fecal microbiota transplantation (FMT) underscored the microbiota-dependent nature of this phenomenon. Moreover, this anti-colorectal cancer metastatic effect and mechanism of total SCFAs and single SCFA were also confirmed. CONCLUSION: In summary, PRM1201 exerts its anti-metastatic effects by modulating SCFA-producing bacteria and enhancing the production of SCFAs. Furthermore, the prebiotic-like actions of PRM1201, along with the PRM1201-treated bacteria, function as inhibitors of histone deacetylases (DHACs) thereby effectively suppressing EMT events.

Single-cell analysis of a progressive Rosai-Dorfman disease affecting the cerebral parenchyma: a case report.

Neurologic Rosai-Dorfman disease (RDD) is a rare type of non-Langerhans cell histiocytosis that affects the central nervous system. Most neurologic RDDs grow like meningiomas, have clear boundaries, and can be completely resected. However, a few RDDs are invasive and aggressive, and no effective treatment options are available because the molecular mechanisms involved remain unknown. Here, we report a case of deadly and glucocorticoid-resistant neurologic RDD and explore its possible pathogenic mechanisms via single-cell RNA sequencing. First, we identified two distinct but evolutionarily related histiocyte subpopulations (the C1Q+ and SPP1+ histiocytes) that accumulated in the biopsy sample. The expression of genes in the KRAS signaling pathway was upregulated, indicating gain-of-function of KRAS mutations. The C1Q+ and SPP1+ histiocytes were highly differentiated and arrested in the G1 phase, excluding the idea that RDD is a lympho-histio-proliferative disorder. Second, although C1Q+ histiocytes were the primary RDD cell type, SPP1+ histiocytes highly expressed several severe inflammation-related and invasive factors, such as WNT5A, IL-6, and MMP12, suggesting that SPP1+ histiocytes plays a central role in driving the progression of this disease. Third, oligodendrocytes were found to be the prominent cell type that initiates RDD via MIF and may resist glucocorticoid treatment via the MDK and PTN signaling pathways. In summary, in this case, we report a rare presentation of neurologic RDD and provided new insight into the pathogenic mechanisms of progressive neurologic RDD. This study will also offer evidence for developing precision therapies targeting this complex disease.

Simulation and calibration of radiation monitoring of nuclear power plant containment sump waste liquid.

Waste liquid stored in the containment sumps of nuclear power plants may contain a variety of radionuclides. Real-time monitoring of containment sump waste liquid can ensure that accidents, such as leakage of cooling water, can be avoided. This paper presents the design of a radioactive monitoring system for waste liquid in a containment sump. The detector and the lead-shield in the measurement unit are optimized through Monte Carlo simulations. Experimental verification showed that the background count rate of the measurement chamber in the system was 418.3 cps, and the detection limit of the detection system was 3.01 Bq/L. Distinct gamma-ray characteristic peaks were also observable, demonstrating the system's ability to identify radioactive nuclides in the waste.

A Fast-Charge Graphite Anode with a Li-Ion-Conductive, Electron/Solvent-Repelling Interface.

Graphite has been serving as the key anode material of rechargeable Li-ion batteries, yet is difficultly charged within a quarter hour while maintaining stable electrochemistry. In addition to a defective edge structure that prevents fast Li-ion entry, the high-rate performance of graphite could be hampered by co-intercalation and parasitic reduction of solvent molecules at anode/electrolyte interface. Conventional surface modification by pitch-derived carbon barely isolates the solvent and electrons, and usually lead to inadequate rate capability to meet practical fast-charge requirements. Here we show that, by applying a MoOx-MoNx layer onto graphite surface, the interface allows fast Li-ion diffusion yet blocks solvent access and electron leakage. By regulating interfacial mass and charge transfer, the modified graphite anode delivers a reversible capacity of 340.3 mAh g-1 after 4000 cycles at 6 C, showing promises in building 10-min-rechargeable batteries with a long operation life.

Chinese expert consensus on imaging diagnosis of drug-resistant pulmonary tuberculosis.

Tuberculosis (TB) remains one of the major infectious diseases in the world with a high incidence rate. Drug-resistant tuberculosis (DR-TB) is a key and difficult challenge in the prevention and treatment of TB. Early, rapid, and accurate diagnosis of DR-TB is essential for selecting appropriate and personalized treatment and is an important means of reducing disease transmission and mortality. In recent years, imaging diagnosis of DR-TB has developed rapidly, but there is a lack of consistent understanding. To this end, the Infectious Disease Imaging Group, Infectious Disease Branch, Chinese Research Hospital Association; Infectious Diseases Group of Chinese Medical Association of Radiology; Digital Health Committee of China Association for the Promotion of Science and Technology Industrialization, and other organizations, formed a group of TB experts across China. The conglomerate then considered the Chinese and international diagnosis and treatment status of DR-TB, China's clinical practice, and evidence-based medicine on the methodological requirements of guidelines and standards. After repeated discussion, the expert consensus of imaging diagnosis of DR-PB was proposed. This consensus includes clinical diagnosis and classification of DR-TB, selection of etiology and imaging examination [mainly X-ray and computed tomography (CT)], imaging manifestations, diagnosis, and differential diagnosis. This expert consensus is expected to improve the understanding of the imaging changes of DR-TB, as a starting point for timely detection of suspected DR-TB patients, and can effectively improve the efficiency of clinical diagnosis and achieve the purpose of early diagnosis and treatment of DR-TB.

Prolonged myelin deficits contribute to neuron loss and functional impairments after ischaemic stroke.

Ischaemic stroke causes neuron loss and long-term functional deficits. Unfortunately, effective approaches to preserving neurons and promoting functional recovery remain unavailable. Oligodendrocytes, the myelinating cells in the CNS, are susceptible to oxygen and nutrition deprivation and undergo degeneration after ischaemic stroke. Technically, new oligodendrocytes and myelin can be generated by the differentiation of oligodendrocyte precursor cells (OPCs). However, myelin dynamics and their functional significance after ischaemic stroke remain poorly understood. Here, we report numerous denuded axons accompanied by decreased neuron density in sections from ischaemic stroke lesions in human brain, suggesting that neuron loss correlates with myelin deficits in these lesions. To investigate the longitudinal changes in myelin dynamics after stroke, we labelled and traced pre-existing and newly-formed myelin, respectively, using cell-specific genetic approaches. Our results indicated massive oligodendrocyte death and myelin loss 2 weeks after stroke in the transient middle cerebral artery occlusion (tMCAO) mouse model. In contrast, myelin regeneration remained insufficient 4 and 8 weeks post-stroke. Notably, neuronal loss and functional impairments worsened in aged brains, and new myelin generation was diminished. To analyse the causal relationship between remyelination and neuron survival, we manipulated myelinogenesis by conditional deletion of Olig2 (a positive regulator) or muscarinic receptor 1 (M1R, a negative regulator) in OPCs. Deleting Olig2 inhibited remyelination, reducing neuron survival and functional recovery after tMCAO. Conversely, enhancing remyelination by M1R conditional knockout or treatment with the pro-myelination drug clemastine after tMCAO preserved white matter integrity and neuronal survival, accelerating functional recovery. Together, our findings demonstrate that enhancing myelinogenesis is a promising strategy to preserve neurons and promote functional recovery after ischaemic stroke.

Models for evaluating glioblastoma invasion along white matter tracts.

White matter tracts (WMs) are one of the main invasion paths of glioblastoma multiforme (GBM). The lack of ideal research models hinders our understanding of the details and mechanisms of GBM invasion along WMs. To date, many potential in vitro models have been reported; nerve fiber culture models and nanomaterial models are biocompatible, and the former have electrically active neurons. Brain slice culture models, organoid models, and microfluidic chip models can simulate the real brain and tumor microenvironment (TME), which contains a variety of cell types. These models are closer to the real in vivo environment and are helpful for further studying not only invasion along WMs by GBM, but also perineural invasion and brain metastasis by solid tumors.

Prolonged sleep deprivation induces a cytokine-storm-like syndrome in mammals.

Most animals require sleep, and sleep loss induces serious pathophysiological consequences, including death. Previous experimental approaches for investigating sleep impacts in mice have been unable to persistently deprive animals of both rapid eye movement sleep (REMS) and non-rapid eye movement sleep (NREMS). Here, we report a "curling prevention by water" paradigm wherein mice remain awake 96% of the time. After 4 days of exposure, mice exhibit severe inflammation, and approximately 80% die. Sleep deprivation increases levels of prostaglandin D2 (PGD2) in the brain, and we found that elevated PGD2 efflux across the blood-brain-barrier-mediated by ATP-binding cassette subfamily C4 transporter-induces both accumulation of circulating neutrophils and a cytokine-storm-like syndrome. Experimental disruption of the PGD2/DP1 axis dramatically reduced sleep-deprivation-induced inflammation. Thus, our study reveals that sleep-related changes in PGD2 in the central nervous system drive profound pathological consequences in the peripheral immune system.

Electrochemical ammonia synthesis under ambient conditions using TM-embedded porphine-fused sheets as single-atom catalysts.

In this research, we systematically investigated the reaction mechanism and electrocatalytic properties of transition metal anchored two-dimensional (2D) porphine-fused sheets (TM-Por) as novel single-atom catalysts (SACs) for the electrochemical nitrogen reduction reaction (eNRR) under ambient conditions. Using high-throughput screening and first-principles calculations based on the density functional theory (DFT) method, three eNRR catalyst candidates, i.e. Mo-Por, Tc-Por, and Nb-Por, were screened out, with the eNRR onset potentials on them being -0.36, -0.53, and -0.74 V, respectively. Furthermore, these catalyst candidates all have good stability and selectivity. Analyzing the band structures found that these catalyst candidates all are metallic, which is needed for good electrocatalysts. Ab initio molecular dynamics (AIMD) simulations show that these catalyst candidates have good stability at 500 K. It is hoped that our work will open up new possibilities for the experimental synthesis of electrochemical ammonia catalysts.

HOXD-AS2-STAT3 feedback loop attenuates sensitivity to temozolomide in glioblastoma.

AIMS: Glioblastoma multiforme (GBM) is the deadliest glioma and its resistance to temozolomide (TMZ) remains intractable. Long non-coding RNAs (lncRNAs) play crucial roles in that and this study aimed to investigate underlying mechanism of HOXD-AS2-affected temozolomide sensitivity in glioblastoma. METHODS: We analyzed and validated the aberrant HOXD-AS2 expression in glioma specimens. Then we explored the function of HOXD-AS2 in vivo and in vitro and a clinical case was also reviewed to examine our findings. We further performed mechanistic experiments to investigate the mechanism of HOXD-AS2 in regulating TMZ sensitivity. RESULTS: Elevated HOXD-AS2 expression promoted progression and negatively correlated with prognosis of glioma; HOXD-AS2 attenuated temozolomide sensitivity in vitro and in vivo; The clinical case also showed that lower HOXD-AS2 sensitized glioblastoma to temozolomide; STAT3-induced HOXD-AS2 could interact with IGF2BP2 protein to form a complex and sequentially upregulate STAT3 signaling, thus forming a positive feedback loop regulating TMZ sensitivity in glioblastoma. CONCLUSION: Our study elucidated the crucial role of the HOXD-AS2-STAT3 positive feedback loop in regulating TMZ sensitivity, suggesting that this could be provided as a potential therapeutic candidate of glioblastoma.

Effectiveness and safety analysis of Danggui Shaoyao Powder for the treatment of non-alcoholic fatty liver disease: study protocol for a randomized, double-blind, placebo-controlled clinical trial.

BACKGROUND: The incidence of non-alcoholic fatty liver disease (NAFLD) has been on the rise in recent years, and there are no effective drugs to treat NAFLD; therefore, effective prevention and treatment of NAFLD have become a new challenge. Danggui Shaoyao Powder (DGSY) is a classic prescription commonly used in clinical practice and has been shown to reduce hepatic steatosis in patients with NAFLD. In addition, previous studies have shown that DGSY can alleviate hepatic steatosis and inflammation in NAFLD mice. Although clinical practice and basic studies have shown that DGSY is effective in NAFLD, high levels of clinical evidence are lacking. Therefore, a standardized RCT study protocol is required to evaluate its clinical efficacy and safety. METHODS AND ANALYSIS: This study will be a randomized, double-blind, placebo-controlled, and single-center trial. According to the random number table, NAFLD participants will be randomly divided into the DGSY or placebo group for 24 weeks. The follow-up period will be 6 weeks after drug withdrawal. The primary outcome is the relative change in MRI-proton density fat fraction (MRI-PDFF) from baseline to 24 weeks. Absolute changes in serum alanine aminotransferase (ALT), liver stiffness measurement (LSM), body mass index (BMI), blood lipid, blood glucose, and insulin resistance index will be selected as secondary outcomes to comprehensively evaluate the clinical efficacy of DGSY in the treatment of NAFLD. The safety of DGSY will be evaluated by renal function, routine blood and urine tests, and electrocardiogram. DISCUSSION: This study will provide evidence-based medical corroboration for the clinical application of DGSY and promote the development and application of this classic prescription. TRIAL REGISTRATION: http://www.chictr.org.cn . TRIAL NUMBER: ChiCTR2000029144. Registered on 15 Jan 2020.

GCK exonic mutations induce abnormal biochemical activities and result in GCK-MODY.

Objective: Glucokinase-maturity-onset diabetes of the young (GCK-MODY; MODY2) is a rare genetic disorder caused by mutations in the glucokinase (GCK) gene. It is often under- or misdiagnosed in clinical practice, but correct diagnosis can be facilitated by genetic testing. In this study, we examined the genes of three patients diagnosed with GCK-MODY and tested their biochemical properties, such as protein stability and half-life, to explore the function of the mutant proteins and identify the pathogenic mechanism of GCK-MODY. Methods: Three patients with increased blood glucose levels were diagnosed with MODY2 according to the diagnostic guidelines of GCK-MODY proposed by the International Society for Pediatric and Adolescent Diabetes (ISPAD) in 2018. Next-generation sequencing (whole exome detection) was performed to detect gene mutations. The GCK gene and its mutations were introduced into the pCDNA3.0 and pGEX-4T-1 vectors. Following protein purification, enzyme activity assay, and protein immunoblotting, the enzyme activity of GCK was determined, along with the ubiquitination level of the mutant GCK protein. Results: Genetic testing revealed three mutations in the GCK gene of the three patients, including c.574C>T (p.R192W), c.758G>A (p.C253Y), and c.794G>A (p.G265D). The biochemical characteristics of the protein encoded by wild-type GCK and mutant GCK were different, compared to wild-type GCK, the enzyme activity encoded by the mutant GCK was reduced, suggesting thermal instability of the mutant GST-GCK. The protein stability and expression levels of the mutant GCK were reduced, and the enzyme activity of GCK was negatively correlated with the levels of fasting blood glucose and HbA1c. In addition, ubiquitination of the mutant GCK protein was higher than that of the wild-type, suggesting a higher degradation rate of mutant GCK than WT-GCK. Conclusion: GCK mutations lead to changes in the biochemical characteristics of its encoded proteins. The enzyme activities, protein expression, and protein stability of GCK may be reduced in patients with GCK gene mutations, which further causes glucose metabolism disorders and induces MODY2.

Neutralizing IL-8 potentiates immune checkpoint blockade efficacy for glioma.

Malignant gliomas are largely refractory to immune checkpoint blockade (ICB) therapy. To explore the underlying immune regulators, we examine the microenvironment in glioma and find that tumor-infiltrating T cells are mainly confined to the perivascular cuffs and express high levels of CCR5, CXCR3, and programmed cell death protein 1 (PD-1). Combined analysis of T cell clustering with T cell receptor (TCR) clone expansion shows that potential tumor-killing T cells are mainly categorized into pre-exhausted/exhausted and effector CD8+ T subsets, as well as cytotoxic CD4+ T subsets. Notably, a distinct subpopulation of CD4+ T cells exhibits innate-like features with preferential interleukin-8 (IL-8) expression. With IL-8-humanized mouse strain, we demonstrate that IL-8-producing CD4+ T, myeloid, and tumor cells orchestrate myeloid-derived suppressor cell infiltration and angiogenesis, which results in enhanced tumor growth but reduced ICB efficacy. Antibody-mediated IL-8 blockade or the inhibition of its receptor, CXCR1/2, unleashes anti-PD-1-mediated antitumor immunity. Our findings thus highlight IL-8 as a combinational immunotherapy target for glioma.

Case Report: An Intracranial Aspergillus Infection with Cyst Formation.

Intracranial fungal infection is a rare condition that often requires surgical intervention. In this study, we present a case of intracranial fungal infection with a space-occupying effect and a long medical history of five years. We comprehensively evaluated the medical history, symptoms, imaging manifestations, and pathological examinations of the patient to confirm this rare case of fungal infection with cyst formation. Moreover, we reviewed the literature on intracranial fungal infection, hoping to draw awareness and attention to this rare disease.

Clinical and Computed Tomography Features Associated with Multidrug-Resistant Pulmonary Tuberculosis: A Retrospective Study in China.

Purpose: To explore the value of integrating clinical and computed tomography (CT) features to predict multidrug-resistant pulmonary tuberculosis (MDR-PTB). Patients and Methods: The study included 212 patients with MDR-PTB and 180 patients with drug-sensitive pulmonary tuberculosis (DS-PTB) who referred to our institute in China between January 2016 and March 2021. The clinical and CT characteristics were analyzed and compared between both groups. Multivariable logistic regression analysis was performed to identify independent factors that can be used to predict MDR-PTB. Furthermore, 115 patients admitted to another center from January 2019 to January 2022 were included as external validation cohort. Results: For clinical characteristics, five parameters were significantly different between the two groups (all P < 0.05). With regard to CT features, nine parameters were significantly different between the two groups (all P < 0.05). Multivariable logistic regression analysis using the aforementioned differential features showed that male sex, retreated history, longer duration of previous anti-TB treatment, lower CD4+ T lymphocyte count, thick-walled cavity, centrilobular micronodules and tree-in-bud sign, bronchial stenosis, pleural and pericardial thickening were the most effective variations associated with MDR-PTB with an area under the curve (AUC) of 0.849 and accuracy of 78.6%. Furthermore, the external validation cohort that contains 115 patients obtained an AUC of 0.933 and accuracy of 81.7%. Conclusion: MDR-PTB and DS-PTB have different clinical and imaging characteristics. A combined model incorporating these differential features can promptly diagnose MDR-PTB and develop subsequent therapeutic strategies.

How anthropogenic factors influence the dissolved oxygen in surface water over three decades in eastern China?

The aquatic environment, linked to the sustainable development of human existence and ecological environment, is influenced comprehensively by anthropogenic and natural activities. In light of the continuously low concentration of dissolved oxygen (DO) in surface water in plain river networks and the phenomenon of delay in the improvement of surface water quality, this research aims to introduce a method that may be utilized in identifying the critical driving forces of DO in surface water and their lagging characteristics, which will contribute to the assessment and adjustment of water quality drivers and/or policies. The research analyzes a typical small watershed in a river network region of the Yangtze River Delta plain as the study area, collecting 35-year (1986-2020) data on several water quality parameters, decades of anthropogenic activities, and two natural factors. The time series methods of vector autoregressive model, Granger causality tests, forecast error variance decompositions, and impulse response functions (hereinafter referred to as VAR+), which are rarely applied in related research, were employed in this study and proved helpful for screening out pivotal drivers and capturing the lagging responses of DO level to driving forces at each lagged time. Results show that there exists a fluctuating drop in DO level in surface water from 1986 to 2008 and a steady climb from 2008 to 2020, with the lowest DO level being present in 2008. The impulsive perturbations of phosphate fertilizer consumption (PFC), motor vessel number, and precipitation minimally increase DO concentration, while the impulsive perturbation of gross domestic product (GDP) causes the sharpest drop in DO level. With these perturbations, the driving force of PFC persists for approximately seven years, and the driving forces of water temperature, permanent population, and GDP persist for only five years. Future research could be conducted with spatial hysteresis, selection of lag order and variable quantity within the model, as well as intermediate variables between drivers and DO level for exploring driving pathways and mechanisms.

Forecasting oil consumption with attention-based IndRNN optimized by adaptive differential evolution.

Accurate prediction of oil consumption plays a dominant role in oil supply chain management. However, because of the effects of the coronavirus disease 2019 (COVID-19) pandemic, oil consumption has exhibited an uncertain and volatile trend, which leads to a huge challenge to accurate predictions. The rapid development of the Internet provides countless online information (e.g., online news) that can benefit predict oil consumption. This study adopts a novel news-based oil consumption prediction methodology-convolutional neural network (CNN) to fetch online news information automatically, thereby illustrating the contribution of text features for oil consumption prediction. This study also proposes a new approach called attention-based JADE-IndRNN that combines adaptive differential evolution (adaptive differential evolution with optional external archive, JADE) with an attention-based independent recurrent neural network (IndRNN) to forecast monthly oil consumption. Experimental results further indicate that the proposed news-based oil consumption prediction methodology improves on the traditional techniques without online oil news significantly, as the news might contain some explanations of the relevant confinement or reopen policies during the COVID-19 period.