Short-term Correlation Research Articles

A study on the backtesting and correlation of systemic risk in Chinese financial institutions: an empirical analysis based on MES and Delta CoVaR

Effectively measuring the risk level of financial institutions is the key to preventing and defusing systemic risks. This paper uses the unconditional coverage test method to backtest the systemic risk of 35 listed financial institutions in China, and uses the quantile coherence method to construct a quantile frequency domain correlation network to explore the frequency domain mechanism of systemic risk correlation of financial institutions. The study found that: (1) During the financial market crisis, the Delta CoVaR commonly used systemic risk measurement indicators such as MES, CoVaR, and failed to effectively measure the systemic risk of China's financial institutions. (2) Compared with the short-term correlation layer and the medium-term correlation layer, China's financial institutions have obvious extreme risk linkage effects in the long-term correlation layer.(3) In the short-term, medium-term and long-term correlation layers, small and medium-sized financial institutions such as Ningbo Bank, Industrial Securities and Dongfang Energy all have high correlation importance. Relevant departments should pay attention to preventing the risk of "too correlated to fail" of small and medium-sized financial institutions in my country.

COVID-19 PANDEMIC; IMPACT ON NET INTEREST MARGIN OF INDONESIAN BANKING INDUSTRY

The study explores factors affecting Net Interest Margins (NIM) in Indonesia's Core Capital Bank Groups. Using data from Jan 2021 to Mar 2022 and the Error Correction Model, it finds negative short-term correlations between BOPO and LDR with NIM in KBMI 1 and positive long-term correlations with BI Rate. KBMI 2 exhibits negative short-term correlations between inflation and LDR with NIM. KBMI 3 shows negative short-term correlations with Covid-19, LDR, and BOPO with NIM. KBMI 4 experiences negative impacts from BOPO, Covid-19, and LDR on NIM in both short and long terms. The study emphasizes the importance of managing operational costs and credit distribution for NIM stability in the short term and highlights the significant influence of Bank Indonesia's benchmark interest rate policy on NIM in the long term, requiring careful adjustments to prevent excessive fluctuations.

Multiple serial correlations in global air temperature anomaly time series.

Serial correlations within temperature time series serve as indicators of the temporal consistency of climate events. This study delves into the serial correlations embedded in global surface air temperature (SAT) data. Initially, we preprocess the SAT time series to eradicate seasonal patterns and linear trends, resulting in the SAT anomaly time series, which encapsulates the inherent variability of Earth's climate system. Employing diverse statistical techniques, we identify three distinct types of serial correlations: short-term, long-term, and nonlinear. To identify short-term correlations, we utilize the first-order autoregressive model, AR(1), revealing a global pattern that can be partially attributed to atmospheric Rossby waves in extratropical regions and the Eastern Pacific warm pool. For long-term correlations, we adopt the standard detrended fluctuation analysis, finding that the global pattern aligns with long-term climate variability, such as the El Niño-Southern Oscillation (ENSO) over the Eastern Pacific. Furthermore, we apply the horizontal visibility graph (HVG) algorithm to transform the SAT anomaly time series into complex networks. The topological parameters of these networks aptly capture the long-term correlations present in the data. Additionally, we introduce a novel topological parameter, Δσ, to detect nonlinear correlations. The statistical significance of this parameter is rigorously tested using the Monte Carlo method, simulating fractional Brownian motion and fractional Gaussian noise processes with a predefined DFA exponent to estimate confidence intervals. In conclusion, serial correlations are universal in global SAT time series and the presence of these serial correlations should be considered carefully in climate sciences.

Self-supervised multi-object tracking based on metric learning

The current paradigm of joint detection and tracking still requires a large amount of instance-level trajectory annotation, which incurs high annotation costs. Moreover, treating embedding training as a classification problem would lead to difficulties in model fitting. In this paper, we propose a new self-supervised multi-object tracking based on the real-time joint detection and embedding (JDE) framework, which we termed as self-supervised multi-object tracking (SS-MOT). In SS-MOT, the short-term temporal correlations between objects within and across adjacent video frames are both considered as self-supervised constraints, where the distances between different objects are enlarged while the distances between same object of adjacent frames are brought closer. In addition, short trajectories are formed by matching pairs of adjacent frames using a matching algorithm, and these matched pairs are treated as positive samples. The distances between positive samples are then minimized for futher the feature representation of the same object. Therefore, our method can be trained on videos without instance-level annotations. We apply our approach to state-of-the-art JDE models, such as FairMOT, Cstrack, and SiamMOT, and achieve comparable results to these supevised methods on the widely used MOT17 and MOT20 challenges.

Role of Rule of Law in the Renewal Energy Transition in Saudi Arabia: A Review and Analysis

The effectiveness of the rule of law and general institutional quality are critical for encouraging Renewable Energy Consumption (REC), which facilitates the Renewable Energy Transition (RET). This concept is empirically tested in Saudi Arabia, using data spanning 1996–2022. Our findings show that there are substantial long- and short-term correlations within the model, demonstrating a positive association between RET and all evaluated variables of institutional quality. The long-term favorable impact of the rule of law is also remarkable, implying that reforms in legal and regulatory frameworks could result in an instant boost in RET. Similarly, control of corruption, as well as voice and accountability, have positive long- and short-term impacts. However, our data shows that economic growth has no substantial impact on RET. As a result, we urge that the Saudi economy emphasize efforts to improve institutional quality as a means of advancing the Renewable Energy Transition agenda. Strengthening the rule of law, reducing corruption, and increasing voice and accountability procedures can all contribute to the development of renewable energy in Saudi Arabia, propelling the country toward a more sustainable energy future. Received: 14 February 2024 / Accepted: 30 April 2024 / Published: 02 July 2024

DNA-T: Deformable Neighborhood Attention Transformer for Irregular Medical Time Series.

The real-world Electronic Health Records (EHRs) present irregularities due to changes in the patient's health status, resulting in various time intervals between observations and different physiological variables examined at each observation point. There have been recent applications of Transformer-based models in the field of irregular time series. However, the full attention mechanism in Transformer overly focuses on distant information, ignoring the short-term correlations of the condition. Thereby, the model is not able to capture localized changes or short-term fluctuations in patients' conditions. Therefore, we propose a novel end-to-end Deformable Neighborhood Attention Transformer (DNA-T) for irregular medical time series. The DNA-T captures local features by dynamically adjusting the receptive field of attention and aggregating relevant deformable neighborhoods in irregular time series. Specifically, we design a Deformable Neighborhood Attention (DNA) module that enables the network to attend to relevant neighborhoods by drifting the receiving field of neighborhood attention. The DNA enhances the model's sensitivity to local information and representation of local features, thereby capturing the correlation of localized changes in patients' conditions. We conduct extensive experiments to validate the effectiveness of DNA-T, outperforming existing state-of-the-art methods in predicting the mortality risk of patients. Moreover, we visualize an example to validate the effectiveness of the proposed DNA.

Traffic Flow Prediction with Random Walks on Graph and Spatiotemporal Bidirectional Attention Transformer

Traffic flow prediction is crucial in intelligent transportation systems. Considering the severe disruptions caused by traffic accidents or congestion, a time series model is developed for traffic flow prediction based on multiple random walks on graphs (MRWG) and the bidirectional spatiotemporal attention mechanism (BSAM), which can adapt to both normal and exceptional situations. The MRWG mechanism is applied to capture spatial features of urban areas during traffic accidents and congestion, especially the spatial dependencies among neighboring regions. Further, a local position attention module is applied to acquire the spatial correlations between different regions to investigate their impact on the global area, while a local temporal attention module is adopted to extract short-term periodic time correlations from traffic flow data. Finally, a spatiotemporal bidirectional attention module is applied to simultaneously extract both the temporal and spatial correlations of the historical traffic flow data in order to generate the output prediction. Experiments have been conducted on NYCTaxi and NYCBike datasets with abnormal events, and the results indicate that the developed model can efficiently predict traffic flow in abnormal events, especially short-term traffic disruptions, outperforming the baseline methods under both abnormal and normal conditions.

An ARDL estimation is conducted to examine the dynamical connection among energy use and joblessness in Saudi Arabia

The rate of joblessness in Saudi Arabia has been a major worry in the past few years, exhibiting swings because of several economic causes. The nation has the formidable task of accommodating a substantial influx of fresh graduates into the labor market annually, posing an obstacle for government officials to offer sufficient employment prospects. Nevertheless, there has been a lack of comprehensive research on the influence of macroeconomic variables, such as energy consumption, on joblessness. The objective of this study is to examine the influence of several macroeconomic factors, such as foreign and domestic investment, trade liberalization, inflation, urbanization, economic growth, and energy consumption, on the levels of unemployment in Saudi Arabia. The ARDL estimate method was used to assess the yearly data spanning from 1971 to 2022. The findings indicate a varied anticipated influence of the independent and dependent variables over an extended period of time. While there is a short-term negative correlation between energy consumption and rate of joblessness, this relationship does not hold true in the long term. The study culminates with a compilation of policy suggestions.

Power load forecasting based on spatial–temporal fusion graph convolution network

The cyclical behavior of electricity users facilitates the prediction of future electricity loads through the analysis of historical data, in addition to considering the spatial correlation among various electricity units. Building on these observations, this study transforms the power loads generated by regional-level user units into graph signals for a more effective visualization of spatial–temporal electricity consumption patterns. Specifically, the graph-based model harnesses its unique spatial–temporal dependencies to deduce the dynamics of electricity consumption patterns and enhance the precision of electricity generation predictions. Introducing a novel deep learning model, the Spatial-Temporal Fusion Graph Convolutional Network (FSTGRNN), which integrates temporal and spatial correlations for the prediction of electricity load values at future time steps. FSTGRNN is an end-to-end model that, firstly, delineates the spatial and temporal patterns of electric loads by constructing spatial relationship graphs using the FC-LSTM and GC-GRU models designed within the spatial–temporal block (ST-Block). Secondly, the spatial–temporal fusion block (STF-Block) in FSTGRNN, equipped with a gating mechanism, encodes the graph signals to capture both long-term dependencies and short-term correlations. The resulting integrated representation is utilized for the forecasting process. Experimental validation is conducted on two electricity load datasets, and the forecasting results clearly demonstrate the superiority and efficiency of the proposed deep learning system.

Estimating the risk of SARS-CoV-2 infection in New Zealand border arrivals

BackgroundTravel restrictions and border controls were used extensively during the COVID-19 pandemic. However, the processes for making robust evidence-based risk assessments of source countries to inform border control policies was in many cases very limited.MethodsBetween April 2020 and February 2022, all international arrivals to New Zealand were required to spend 14 days in government-managed quarantine facilities and were tested at least twice. The infection rates among arrivals in the years 2020, 2021 and 2022 were respectively 6.3, 9.4 and 90.0 cases per thousand arrivals (487, 1064 and 1496 cases). Test results for all arrivals were linked with travel history, providing a large and comprehensive dataset on the number of SARS-CoV-2-positive and negative travellers from different countries over time. We developed a statistical model to predict the country-level infection risk based on infection rates among recent arrivals and reported cases in the country of origin. The model incorporates a country-level random effect to allow for the differences between the infection risk of the population of each country and that of travellers to New Zealand. A time dependent auto-regressive component of the model allows for short term correlation in infection rates.ResultsA model selection and checking exercise found that the model was robust and reliable for forecasting arrival risk for 2 weeks ahead. We used the model to forecast the number of infected arrivals in future weeks and categorised countries according to their risk level. The model was implemented in R and was used by the New Zealand Ministry of Health to help inform border control policy during 2021.ConclusionsA robust and practical forecasting tool was developed for forecasting infection risk among arriving passengers during a period of controlled borders during the COVID-19 pandemic. The model uses historical infection rates among arrivals and current infection rates in the source country to make separate risk predictions for arrivals from each country.

Exploring the link between CO2 emissions, health expenditure, and economic growth in Türkiye: evidence from the ARDL model

AbstractIn recent times, the literature has seen considerable growth in research at the intersection of CO2 emission, health expenditure, and economic growth. But looking at the literature, it appears that the relationship between health expenditures, CO2 emissions, and economic growth is unclear. To resolve this uncertainty, this study was conducted with different data, countries, and methods. To this end, the present study analyzed the nexus between CO2 emissions, health expenditure, and economic growth in Türkiye from 1975 to 2020 using the Autoregressive Distributed Lagged (ARDL) model developed by Pesaran et al. (J Appl Econ 16(3):289–326, 2001). The study reveals a connection between CO2 emissions, health spending, and economic development in Türkiye over the long term. It also highlights a short-term correlation among these factors. The study indicates that a 1% increase in economic growth results in a 0.553 and 0.297 rise in CO2 emissions in the short and long term, respectively. That is, it suggests that if economic growth in Türkiye doesn’t involve renewable energy, it could negatively affect CO2 emissions both in the short and long term. To address this, substantial efforts are needed to transition to low-carbon technologies like renewable energy and energy efficiency, aiming to reduce emissions and support long-term economic growth. The study further demonstrates that a 1% growth in health expenditure leads to a 0.124% decrease in CO2 emissions over the long term. This implies that Türkiye’s health sector could benefit from utilizing more renewable energy or using fossil fuels more efficiently. Additionally, the study warns that long-term population growth could negatively affect CO2 emissions in Türkiye.

Personalized prediction of speech intelligibility for hearing-impaired listeners using a physiological model of the human ear

Due to the problems of occlusion effect, insufficient high-frequency gain, and acoustic feedback in conventional hearing aids, middle ear implants as a new type of hearing device have become an important compensatory tool for the treatment of patients with moderate to severe hearing loss. However, current speech intelligibility (SI) models are inadequate for predicting SI in hearing-impaired (HI) listeners after middle ear implants implantation. Moreover, the compensatory performance of middle ear implants before implantation remains unknown due to the invasive nature of the surgical procedure. Therefore, this study proposes a novel SI model that can predict the compensatory effects on SI after middle ear implants implantation. The model combines a physiologically nonlinear auditory preprocessing front-end with a short-term correlation analysis back-end. In normal-hearing (NH) listeners, the model accurately predicts speech reception thresholds (SRTs) and masking release under steady-state and fluctuating noise conditions. For HI listeners, the model modifies the parameters of outer hair cells and inner hair cells in the preprocessing front-end to simulate the patient’s audiogram, achieving excellent predictive capability for HI listeners’ test data. Overall, the proposed SI model can be used for the optimal design and algorithm fitting of middle ear implants tailored to patients with varying degrees of hearing loss, offering valuable insights for the clinical treatment of HI listeners.

ANALYSIS OF FACTORS AFFECTING THE DEMAND FOR MONEY IN INDONESIA

Demand for money is defined as people's tendency to save money for various purposes, such as transactions, anticipation, and speculation. Many factors related to economic, social, political and psychological conditions influence the demand for money. This research aims to evaluate the impact of various variables on money demand in Indonesia from 2018 to 2023. This research uses an Error Correction Model (ECM), which can measure short-term and long-term correlations between the variables studied. The money supply (M2) is the dependent variable of this research, and the independent variables are interest rates, inflation and the US dollar exchange rate against the rupiah. The results show that except for inflation, all independent variables influence money demand significantly in the long run. In the short term, only the rupiah exchange rate has a significant influence on the demand for money.

Double Asymmetric Impacts, Dynamic Correlations, and Risk Management Amidst Market Risks: A Comparative Study between the US and China

Extreme shocks, including climate change, economic sanctions, geopolitical conflicts, etc., are significant and complex issues currently confronting the global world. From the US–China perspective, this paper employs the DCC-DAGM model to investigate how diverse market risks asymmetrically affect return volatility, and extract correlations between stock indices and hedging assets. Then, diversified and hedging portfolios, constructed by optimal weight and hedge ratio, are investigated using multiple risk reduction measures. The empirical results highlight that, first, diverse risks exhibit an asymmetric effect on the return volatility in the long term, while in the short term, the US stock market is more sensitive to negative return shocks than the Chinese market. Second, risks impact correlations differently across time horizons and countries. Short-term correlations are stronger than long-term ones for the US market, with the Chinese stock market displaying more stable correlations. Third, the hedging strategy is more effective in reducing volatility and risk for US stocks, while the diversification strategy proves more effective for Chinese stocks. These findings have implications for market participants striving to make their portfolios robust during turbulent times.

Breast Cancer Image Classification based on Adaptive Interpolation Approach Using Clinical Dataset

In the healthcare and bioinformatics disciplines, the categorization of breast cancer has become an emerging paradigm due to the second most common cause of cancer-related mortality in women. A biopsy is a procedure in which tissue has been examined to determine whether or not it is breast cancer through histopathologists that may lead to a mistaken diagnosis. The research is mainly focused on the patient data (884 case reports of patients) is acquired from the American Oncology Institute implemented with preprocessing techniques consists of missing values and those values are recovered with Novel Modified Interpolation (MI) Method. Deep learning networks effectively detect and assess the pattern for annotating histological data based on the labelling, which preserves time, system cost and enhances the system accuracy. This framework addressed feature acquisition and missing analysis strategies based on entropy confidence weight factor. First, the iterative patterns have been treated as a potential diagnostic rule, and the attention-based rule combination formulates the classification issue based on integrating convolutional and recurrent neural networks, and the short-term and long-term spatial correlations between patches. Second, the key part of label construction is carried out with an entropy confidence-weight factor assessment which detects and predict different patterns to construct the rule for classification. Third, optimization of clustering data by assessing missing parameters based on mean square error and the concept of interpolation to reduce data loss by around 20% and enhance the system accuracy. Simulation results show that the proposed system achieves 91.3% accuracy to state-of-art approaches, potentially allied in clinical applications. Modified Interpolation (MI) method recovered missing values with least mean square error and less data loss of 0.0123 and 1.38% respectively. This method also compared with existing Linear Interpolation (LI) method which is able to recover least men square error and data loss of 3.295 and 18.925% respectively. Comparatively the modified interpolation method recovered the missing values with less mean square error and less data loss.

Short-Term Tree-Ring Series of Pinus hartwegii Lindl. Taken at Ground Level Correlate to Normalized Difference Vegetation Index Series

In this work, we propose that small wood core samples (≤10 cm length), taken from 0.3 m above the soil, represent an accurate means of correlating forest growth with remote sensing data. Short-term correlations between the Normalized Difference Vegetation Index (NDVI) and tree-ring components of the last three to four decades were tested, using 210 Pinus hartwegii wood cores collected at two locations, Tláloc (TLA) and Jocotitlán (JOCO) in central Mexico. The NDVI time series were generated with the Google Earth Engine (GEE) using Landsat 8 images. Also, seasonal trends in NDVI (e.g., spring, summer, autumn, winter) were analyzed through longitudinal analysis. The results showed more statistically significant dendrochronological indices in TLA than in JOCO, but both locations consistently showed an NDVI decrease in 2018 and 2020, indicating a reduction in vegetation vigor. At the two locations, the minimum and maximum NDVI occurred in April and October, respectively. Seasonal NDVI changes for spring were mainly seen at TLA with a decreasing trend, which may be related to a less defined dry season. The significant correlations (p < 0.05) between tree-ring components and the NDVI occurred in the dry season, indicating that the productivity of a given year is defined by the tree vigor shown in April and May, in the case of TLA, and between January and March, for JOCO. Although the NDVI values of JOCO were higher than those of TLA, tree growth, expressed by tree-ring indices, was lower. Our proposed field method to correlate tree-ring information and the NDVI is reliable and can be used in other coniferous forests.

Deep Learning Low-cost Photogrammetry for 4D Short-term Glacier Dynamics Monitoring

AbstractShort-term monitoring of alpine glaciers is crucial to understand their response to climate change. This paper presents a low-cost multi-camera system tailored for 4D glacier monitoring using deep learning stereo-photogrammetry. Our approach integrates multi-temporal 3D reconstruction from stereo cameras and surface velocity estimation from a monoscopic camera through digital image correlation. To address the challenges posed by wide camera baselines in complex environments, we have integrated state-of-the-art deep learning feature matching algorithms into ICEpy4D, a Python toolkit designed for 4D monitoring (https://github.com/franioli/icepy4d). In a pilot study conducted on the debris-covered Belvedere Glacier (Italian Alps), our stereoscopic setup, with a camera base–height ratio close to one, captured daily images from May to November 2022. Our approach utilized SuperPoint and SuperGlue for feature matching, resulting in a daily 3D reconstruction of the glacier terminus, as traditional SIFT-like feature matching fails in this scenario. Using dense point clouds with decimetric accuracy, we estimated daily ice volume loss and glacier retreat at the terminus. The total ice volume loss was $$63\,000\,\text{m}$$ 63 000 m $${}^{3}$$ 3 and the retreat was $$17.8\,\text{m}$$ 17.8 m . Surface kinematics revealed three times higher surface velocity during the warm season (May–September) than in the fall (September–November). Daily analyses revealed a significant short-term correlation between air temperature, glacier surface velocity and ice ablation, providing insight into the glacier’s response to external forces. The low cost and ease of deployment of the proposed system facilitates replication at other sites for short-term monitoring of glacier dynamics.

국제 자발적 탄소시장 크레딧 가격 결정요인분석

This study analyzes the correlation between voluntary carbon market credit prices and three key sets of variables. Prior research on compliance carbon markets has identified these factors as a significant influence on emission price factors. This study employs the Autoregressive Distributed Lag (ARDL) model to test these relationships and empirically examines short and long term correlations by conducting cointegration tests between each variable and the emission credit price. The results of the study are as follows:First, electricity prices exhibit a positive relationship with credit prices in the short term but a negative relationship in the long term. Second, compared to regulatory carbon market prices, credit prices are influenced by temperature variables, reflecting local weather conditions. Third, the energy variable emerges as the most crucial factor impacting prices in both compliance emissions trading systems and voluntary carbon credits. This implies that companies aiming for carbon neutrality through voluntary carbon market credits must develop comprehensive strategies that consider various external circumstances.

Real-time prediction of ROP based on GRU-Informer

Accurate ROP (rate of penetration) prediction contributes to better production task planning, ensuring efficient production line operation, and reducing production costs. ROP prediction is influenced by multiple factors, making accurate prediction challenging. Current research primarily relies on historical data for training and modeling, lacking methods for real-time ROP prediction. This paper introduces a GRU-Informer model for real-time ROP prediction. The model employs GRU (Gated Recurrent Unit) neural networks at the lower level to capture short-term correlations in drilling parameters and uses the Informer model at the top to address long-term dependencies among drilling parameters. Thus, the GRU-Informer can capture both short-term and long-term time dependencies, providing better ROP predictions. This paper constructs a dataset using historical data from a southwestern Chinese oil field for experimentation. RMSE (Root Mean Square Error), MAE (mean absolute error) and R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}^{2}$$\\end{document} (Coefficient of Determination) are employed as evaluation metrics for the model. Experimental results demonstrate that the GRU-Informer outperforms traditional recurrent neural networks like LSTM (Long Short-Term Memory), GRU neural networks and Informer in real-time ROP prediction, indicating its practical value.

Degradation state estimation for insulated gate bipolar transistor based on multi-scale fusion learning

Insulated gate bipolar transistor (IGBT) modules are widely used in power electronic systems. Estimating the degradation state of IGBT modules is especially crucial when operating under different conditions, as they are highly likely to experience aging or faults, resulting in system failure. However, a fixed time window is generally used, which is not easy to fully learn the correlation between data. To address the issues, this paper proposes a multi-scale fusion learning method for estimating the degradation state of IGBT. The method can effectively mine the short-term and long-term correlations of IGBT aging data, which helps to implement the accurate estimation based on IGBT aging data. To validate the effectiveness of the proposed method, the accelerated aging test data provided by the NASA Predictive Center of Excellence (PCoE) is utilized. The results show that the method can accurately estimate the degradation state of IGBTs.