To a large extent, electricity price prediction is a daunting task because it depends on factors, such as weather, fuel, load and bidding strategies etc. Those features generate a lot of fluctuations ...to electricity price. As a type of RNN, LSTM has a good performance on processing time series data as well as some nonlinear and complex problems. To explore more accurate electricity price forecasting approach, in this paper, a new hybrid model based on wavelet transform and Adam optimized LSTM neural network, denoted as WT-Adam-LSTM, is proposed. After the wavelet transform, nonlinear sequence of electricity price can be decomposed and processed data will have a more stable variance, and the combination of Adam, one of efficient stochastic gradient-based optimizers, and LSTM can capture appropriate behaviors precisely for electricity price. This study presented four cases to verify the performance of the hybrid model, and the dataset from New South Wales of Australia and French were adopted to illustrate the excellence of the hybrid model. The results show that the proposed model can significantly improve the prediction accuracy.
•Long short-term Memory (LSTM) is applied for electricity price forecasting.•Adam is used as optimizer for LSTM.•Pauta criterion and Min-max normalization are used as preprocessing methods for price data.•Wavelet transform is used to decompose the electricity price series into a set of better-performing constitutive series.•Four cases proved that proposed WT-Adam-LSTM outperforms the existing models reported in the literature.
Cerebral small vessel disease (CSVD) is a generic term used for intracranial vascular disorders caused by the structural changes of cerebral microvessels, including the small arteries, arterioles, ...capillaries and venules. CSVD exhibits various neuroimaging features and is associated clinical characteristics. Although CSVD is recognized as the leading cause of vascular cognitive impairment (VCI), the underlying mechanism(s) remains elusive. Growing evidence indicates a significant association between altered neurovascular unit (NVU) functioning and the pathophysiology of evolving CSVD-induced VCI. Therefore, research is required to understand how NVU dysregulation contributes to cognitive impairment due to CSVD. In this review, we describe the link between the neuroimaging focal lesions and cognitive alterations. We also discuss the potential pathological role of NVU dysregulation in the entry of pathogens from the blood into the parenchyma by altering the blood-brain barrier (BBB), affecting the cerebral microvascular and consequently cause VCI. Next, we review the coupling of neural activity with cerebral blood flow to control the microvascular perfusion; and the disrupted clearance of metabolic byproducts with CSF-ISF exchange via perivascular pathways and glymphatic system. Finally, we discussed the possible therapeutic interventions in CSVD.
•CSVD is the common cause of vascular cognitive impairment.•The organelle and cellular injury of NVU components is associated with CSVD neuroimaging markers and cognitive impairment.•NVU dysregulation leads to the dysfunctions of BBB, blood–CSF barrier, CBF and lymphatic drainage system.•Potential therapeutic strategies to target each NVU component involved in CSVD-induced cognitive loss may be developed.
Neuroinflammation and mitochondrial impairment play important roles in the neuropathogenesis of Parkinson's disease (PD). The activation of NLRP3 inflammasome and the accumulation of α-synuclein ...(α-Syn) are strictly correlated to neuroinflammation. Therefore, the regulation of NLRP3 inflammasome activation and α-Syn aggregation might have therapeutic potential. It has been indicated that Dl-3-n-butylphthalide (NBP) produces neuroprotection against some neurological diseases such as ischemic stroke. We here intended to explore whether NBP suppressed NLRP3 inflammasome activation and reduced α-Syn aggregation, thus protecting dopaminergic neurons against neuroinflammation.
In our study, we established a MPTP-induced mouse model and 6-OHDA-induced SH-SY5Y cell model to examine the neuroprotective actions of NBP. We then performed behavioral tests to examine motor dysfunction in MPTP-exposed mice after NBP treatment. Western blotting, immunofluorescence staining, flow cytometry and RT-qPCR were conducted to investigate the expression of NLRP3 inflammasomes, neuroinflammatory cytokines, PARP1, p-α-Syn, and markers of microgliosis and astrogliosis.
The results showed that NBP exerts a neuroprotective effect on experimental PD models.
, NBP ameliorated behavioral impairments and reduced dopaminergic neuron loss in MPTP-induced mice.
, treatment of SH-SY5Y cells with 6-OHDA (100uM,24 h) significantly decreased cell viability, increased intracellular ROS production, and induced apoptosis, while pretreatment with 5uM NBP could alleviated 6-OHDA-induced cytotoxicity, ROS production and cell apoptosis to some extent. Importantly, both
and
, NBP suppressed the activation of the NLRP3 inflammasome and the aggregation of α-Syn, thus inhibited neuroinflammation ameliorated mitochondrial impairments.
In summary, NBP rescued dopaminergic neurons by reducing NLRP3 inflammasome activation and ameliorating mitochondrial impairments and increases in p-α-Syn levels. This current study may provide novel neuroprotective mechanisms of NBP as a potential therapeutic agent.
This study intended to investigate whether retinal nerve fiber layer (RNFL) thickness could become a potential marker in patients with Parkinson's disease with cognitive impairment (PD-CI).
...Fifty-seven PD patients and 45 age-matched healthy controls (HCs) were recruited in our cross-sectional study and completed optical coherence tomography (OCT) evaluations. PD with normal cognition (PD-NC) and cognitive impairment (PD-CI) patients were divided following the 2015 Movement Disorder Society criteria. RNFL thickness was quantified in subfields of the 3.0-mm circle surrounding the optic disk; while a battery of neuropsychiatric assessments was conducted to estimate the Parkinsonism severity. General linear models and one-way ANOVA were adopted to assess RNFL thickness between subgroups with different cognitive statuses; logistic regression analyses were applied to determine the relation between RNFL and PD-CI cases.
Compared with HCs, more thinning of the RNFL was observed in the inferior and temporal sectors in PD patients, especially in the PD-CI group. Inferior RNFL thickness was reduced in PD-CI compared with PD-NC patients. Logistic regression analysis found that inferior RNFL thickness was independently associated with PD-CI cases (odds ratio = 0.923,
= 0.014). Receiver operating characteristic analysis showed that the RNFL-involved combined model provided a high accuracy in screening cognitive deficiency in PD cases (area under the curve = 0.85,
< 0.001).
Reduced RNFL thickness especially in the inferior sector is independently associated with PD-CI patients. Our study present new perspectives into verifying possible indicators for neuropathological processes or disease severity in Parkinsonians with cognitive dysfunction.
: Oxidative stress and inflammation play critical roles in the neuropathogenesis of PD. We aimed to evaluate oxidative stress and inflammation status by measuring serum superoxide dismutase (SOD) ...with lipoprotein cholesterol and high-sensitivity C-reactive protein (hsCRP) respectively in PD patients, and explore their correlation with the disease severity.
: We performed a cross-sectional study that included 204 PD patients and 204 age-matched healthy controls (HCs). Plasma levels of SOD, hsCRP, total cholesterol, high-density lipoprotein cholesterol (HDL-C) and low-density lipoprotein cholesterol (LDL-C) were measured. A series of neuropsychological assessments were performed to rate the severity of PD.
: The plasma levels of SOD (135.7 ± 20.14 vs. 147.2 ± 24.34,
< 0.0001), total cholesterol, HDL-C and LDL-C in PD were significantly lower than those in HCs; the hsCRP level was remarkably increased in PD compared to HC (2.766 ± 3.242 vs. 1.637 ± 1.597,
< 0.0001). The plasma SOD was negatively correlated with the hsCRP, while positively correlated with total cholesterol, HDL-C, and LDL-C in PD patients. The plasma SOD were negatively correlated with H&Y, total UPDRS, UPDRS (I), UPDRS (II), and UPDRS (III) scores, but positively correlated with MoCA and MMSE scores. Besides, hsCRP was negatively correlated with MoCA; while total cholesterol, HDL-C and LDL-C were positively correlated with the MoCA, respectively.
: Our findings suggest that lower SOD along with cholesterol, HDL-C and LDL-C, and higher hsCRP levels might be important markers to assess the PD severity. A better understanding of SOD and hsCRP may yield insights into the pathogenesis of PD.
To characterize the clinical phenotypes associated with the "hot cross bun" sign (HCBs) on MRI and identify correlations between neuroimaging and clinical characteristics.
Firstly, we screened a ...cohort of patients with HCBs from our radiologic information system (RIS) in our center. Secondly, we systematically reviewed published cases on HCBs and classified all these cases according to their etiologies. Finally, we characterized all HCBs cases in detail and classified the disease spectra and their clinical heterogeneity.
: Out of a total of 3,546 patients who were screened, we identified 40 patients with HCBs imaging sign in our cohort; systemic literature review identified 39 cases, which were associated with 14 diseases. In our cohort, inflammation neuromyelitis optica spectrum disorders (NMOSD), multiple sclerosis (MS), and acute disseminated encephalomyelitis (ADEM) and toxicants toxic encephalopathy caused by phenytoin sodium (TEPS) were some of the underlying etiologies. Published cases by systemic literature review were linked to metabolic abnormality, degeneration, neoplasm, infection, and stroke. We demonstrated that the clinical phenotype, neuroimaging characteristics, and HCBs response to therapy varied greatly depending on underlying etiologies.
: This is the first to report HCBs spectra in inflammatory and toxication diseases. Our study and systemic literature review demonstrated that the underpinning disease spectrum may be broader than previously recognized.
To evaluate the correlation between "hot cross bun" sign (HCBs) and disease severity in multiple system atrophy (MSA). We recruited patients with probable and possible MSA with parkinsonism (MSA-P) ...or the cerebellar ataxia (MSA-C) subtypes. Clinical and imaging characteristics were collected and comparison was performed between MSA-C and MSA-P cases. Spearman test was used to evaluate the correlation between HCBs and other variables. Curve estimate and general linear regression was performed to evaluate the relationship between HCBs and the Scale for Assessment and Rating of Ataxia (SARA). Unified Multiple System Atrophy Rating Scale (UMSARS) IV was used to assess the severity of disease. Multinomial ordered logistic regression was used to confirm the increased likelihood of disability for the disease. Eighty-one MSA with HCBs comprising of 50 MSA-C and 31 MSA-P were recruited. We demonstrated that the severity of HCBs showed a positive linear correlation with SARA scores in MSA-C. Multinomial ordered logistic regression test revealed that the increase in the HCBs grade may be associated with an increased likelihood of disability for the disease severity in MSA, especially in those with cerebellar ataxia subtype. We demonstrated that HCBs is a potential imaging marker for the severity of cerebellar ataxia. The increase in the HCBs grade may be associated with an increased likelihood of disability in MSA-C, but not MSA-P cases, suggesting that it may be a useful imaging indicator for disease progression in Chinese patients with MSA-C.
: Hemoglobin is one of the main proteins in erythrocytes. There are significant correlations between low hemoglobin and white matter hyperintensities (WMH) and cognitive impairment. This study ...explored whether erythrocytopenia has predictive value for vascular cognitive impairment (VCI) in patients with WMH.
: We conducted a cross-sectional study of 302 patients, including 62 with cerebral small vessel disease and 240 with stroke. Basic demographic data and fasting blood were collected. First, all patients were divided into normal cognition (NC), mild VCI (mVCI), and severe VCI (sVCI) groups (subgroups later) based on cognitive behavior scores. Second, all patients were divided into mild WMH (mWMH) and severe WMH (sWMH) groups based on Fazekas scores. The differences in blood markers between different groups or subgroups with different cognitive levels were analyzed by univariate analysis. Then, binary logistic regression was used to analyze the diagnostic value of erythrocyte counts for VCI in the sWMH group, and ordinal logistic regression was used to analyze the predictive value of multiple variables for different cognitive levels.
: Univariate analysis showed that erythrocytes, hemoglobin, high-sensitivity C-reactive protein, retinol binding protein and prealbumin were potential blood markers for different cognitive levels in sWMH patients. Among them, erythrocytopenia has good predictive value for the diagnosis of mVCI (AUC = 0.685,
= 0.008) or sVCI (AUC = 0.699,
= 0.003) in patients with sWMH. Multivariate joint analysis showed that erythrocytes were an independent protective factor reducing the occurrence of VCI in patients with sWMH (OR = 0.633,
= 0.045). Even after adjusting for age, there was still a significant difference (
= 0.047).
: Erythrocytes are an independent protective factor for VCI in patients with sWMH. Promoting hematopoietic function may have potential value for prevention of cognitive decline in patients with cerebrovascular disease.
Estimating the remaining useful life (RUL) of equipment is critical for ensuring the safe operation of machinery and reducing maintenance losses. For the existing RUL prediction, the problem of data ...redundancy and initial prediction time dramatically affects the prediction results. Therefore, this paper proposes a long short-term memory network (LSTM) RUL prediction algorithm that is based on multi-layer grid search (MLGS) optimization. This method integrates feature data and optimizes network parameters to ensure accuracy and effectively predict the non-stationary degradation of the bearing. Firstly, this paper uses a data fusion method to extract low dimensional feature vectors of running data, and the multi-feature fusion is performed to obtain the principal component index. Then, the MLGS is used to optimize the network overparameters. The effect of the initial measurement time on prediction results can be reduced, and the calculation speed can be improved. Finally, the IMS data set of NASA is used for verification and comparative testing. The test results show that the proposed RUL prediction algorithm can effectively reduce the influence of the initial prediction time on the prediction accuracy compared with other prediction methods.