Short-term Trends Research Articles

Short-Term Trends and Site Differences of Methamphetamine and Ketamine Consumption in Two Cities by Wastewater Analysis

Short-Term Trends and Site Differences of Methamphetamine and Ketamine Consumption in Two Cities by Wastewater Analysis

Monthly Maximum Magnitude Prediction in the North–South Seismic Belt of China Based on Deep Learning

The North–South Seismic Belt is one of the major regions in China where strong earthquakes frequently occur. Predicting the monthly maximum magnitude is of significant importance for proactive seismic hazard defense. This paper uses seismic catalog data from the North–South Seismic Belt since 1970 to calculate and extract multiple seismic parameters. The monthly maximum magnitude is processed using Variational Mode Decomposition (VMD) with sample segmentation to avoid information leakage. The decomposed multiple modal data and seismic parameters together form a new dataset. Based on these datasets, this paper employs four deep learning models and four time windows to predict the monthly maximum magnitude, using prediction accuracy (PA), False Alarm Rate (FAR), and Missed Alarm Rate (MR) as evaluation metrics. It is found that a time window of 12 generally yields better prediction results, with the PA for Ms 5.0–6.0 earthquakes reaching 77.27% and for earthquakes above Ms 6.0 reaching 12.5%. Compared to data not decomposed using VMD, traditional error metrics show only a slight improvement, but the model can better predict short-term trends in magnitude changes.

A Novel Stock Price Prediction and Trading Methodology Based on Active Learning Surrogated with CycleGAN and Deep Learning and System Engineering Integration: A Case Study on TSMC Stock Data

Technical analysis, reliant on statistics and charting tools, is a predominant method for predicting stock prices. However, given the impact of the joint effect of stock price and trading volume, analyses focusing solely on single factors at isolated time points often yield partial or inaccurate results. This study introduces the application of Cycle Generative Adversarial Network (CycleGAN) alongside Deep Learning (DL) models, such as Residual Neural Network (ResNet) and Long Short-Term Memory (LSTM), to assess the joint effects of stock price and trading volume on prediction accuracy. By incorporating these models into system engineering (SE), the research aims to decode short-term stock market trends and improve investment decisions through the integration of predicted stock prices with Bollinger Bands. Thereby, active learning (AL) is employed to avoid over-and under-fitting and find the hyperparameters for the overall system model. Focusing on TSMC’s stock price prediction, the use of CycleGAN for analyzing 30-day stock data showcases the capability of ResNet and LSTM models in achieving high accuracy and F-1 scores for a five-day prediction period. Further analysis reveals that combining DL predictions with SE principles leads to more precise short-term forecasts. Additionally, integrating these predictions with Bollinger Bands demonstrates a decrease in trading frequency and a significant 30% increase in average Return on Investment (ROI). This innovative approach marks a first in the field of stock market prediction, offering a comprehensive framework for enhancing predictive accuracy and investment outcomes.

Comparative analysis of neural network architectures for short-term FOREX forecasting

This document outlines the analysis, design, implementation, and benchmarking of various neural network architectures in a short-term frequency prediction system for the FOREX market. Our objective is to emulate the decision-making process of a human expert (technical analyst) through a system that swiftly adapts to market condition changes, thereby optimizing short-term trading strategies. We have designed and implemented a series of LSTM neural network architectures that take exchange rate values as input to generate short-term market trend forecasts. Additionally, we developed a custom ANN architecture based on simulators for technical analysis indicators. We performed a comparative analysis of the results and came to useful conclusions regarding the suitability of each architecture and the cost in terms of time and computational power to implement them. The ANN custom architecture produces better prediction quality with higher sensitivity using fewer resources and spending less time than LSTM architectures. The ANN custom architecture appears to be ideal for use in low-power computing systems and for use cases that need fast decisions with the least possible computational cost.

UKRAINE AND REPUBLIC OF MOLDOVA IN COOPERATION WITH THE EU AFTER 2014 YEAR: MODELS AND IMPACTS

Abstract. The paper is devoted to solving the problem of co-integration between Ukraine and the Republic of Moldova in the context of foreign trade. The study of co-integration makes it possible to determine common trends in the development of foreign trade and, based on the analysis of the dynamics of the development of one country, to forecast the development of foreign trade in another country. The study of the main indicators of foreign trade was carried out: volumes of exports, imports, trade balance. The share of export-import operations with the EU in the total volume of foreign trade of Ukraine and Moldova was chosen as the studied indicator. The article proposes to consider cointegrations both between long-term trends, which characterize the trend of foreign trade development, and between short-term trends, which reflect the cyclical component. A co-integration research mechanism has been developed, which includes three blocks: a block of analysis of literary sources, a block of mathematical tools, and a block of applied use. The use of decomposition models, trend models, spectral analysis, orthogonality indicators and pairwise correlations is proposed as a mathematical toolkit. Using the Foster-Stewart method, an analysis of the presence of a trend in the variance and average was carried out. The above calculations showed the presence of a trend and cyclical component, which allowed the use of additive decomposition models. For the study of long-term trends, a linear trend model was chosen for both Moldova and Ukraine. A spectral analysis of the cyclic component was carried out, which made it possible to identify five main harmonics with a unique frequency and amplitude. The combination of these harmonics caused 95.8% and 90.4% of the cyclical component for Moldova and Ukraine, respectively. An analysis of cointegration between short-term and long-term trend functions was conducted, which revealed medium cointegration in the long-term trend and high cointegration in the short-term trend. The cointegration analysis of the indicator values proved a high degree of cointegration for both long-term and short-term trends.

A study on the efficacy of an attention mechanism-based strategy planning method for stock trading portfolios

In order to take full advantage of the fact that there is a large amount of information and data available in the field of stock trading, this paper develops a new type of stock trading strategy, which reduces investment risk. A stock trading portfolio strategy planning method based on an attention mechanism, as disclosed in the present invention, relates to the field of stock trading technology. The introduction of an attention mechanism allows the strategy to focus on those stocks with higher evaluation coefficients, thereby improving the selectivity and accuracy of the strategy and thus the effectiveness of the portfolio strategy. Furthermore, based on the prediction results of the deep spatio-temporal neural network model, it is possible to determine the stock's short-term trends and identify the optimal trading points. This information can be utilized as a reference for investors, assisting them in making more informed decisions regarding the timing of buying and selling, improving the success rate and yield of trading, enabling them to swiftly and accurately assess the performance of each stock, facilitating timely adjustments to their portfolios, and enabling them to devise the optimal trading strategy and timing for each stock, enhancing the accuracy and efficiency of their trading decisions.

Utilising integrated bio-behavioural surveillance (IBBS) to investigate declining hepatitis C antibody prevalence among people who inject drugs in the Australian Needle and Syringe Program Survey

BackgroundPrevalence of hepatitis C virus (HCV) antibody (Ab) on dried blood spot (DBS) samples in the Australian Needle and Syringe Program Survey (ANSPS) decreased nationally from 57 % in 2015 to 32 % in 2022. We aimed to investigate potential explanations for this decline. MethodsChanges in DBS HCV Ab prevalence were investigated by redefining positive cases as those with those with either a positive HCV Ab test result or a self-reported history of ever having HCV treatment (modified prevalence), examining HCV Ab prevalence by birth and age cohorts, and assessing trends in key risk behaviours. ResultsOverall prevalence of DBS HCV Ab declined rapidly and significantly from 57 % in 2015 to 32 % in 2022 (p < 0.001) however modified HCV Ab prevalence remained stable over time (85 % and 88 % in 2015 and 2022, respectively, p = 0.357). The proportion of participants with negative HCV Ab and self-reported HCV infection increased from 20 % in 1995 to 40 % in 2022 (p < 0.001) and the proportion with negative HCV Ab and lifetime HCV treatment increased from 3 % in 1999 to 67 % in 2022 (p < 0.001). We also observed a decreasing trend in DBS HCV Ab prevalence in all birth and age cohorts with a noticeable acceleration in the decline commensurate with the advent of HCV DAA treatment. A long-term decreasing trend was also observed for key risk behaviours (p < 0.001) however the short-term trend was not significant for recent receptive syringe sharing. ConclusionThe temporal decline in HCV Ab prevalence appears related to reduced sensitivity of DBS HCV Ab detection with viral clearance following treatment. Since 2016, HCV treatment uptake has increased markedly including among people who inject drugs. In this context, continuing to monitor HCV Ab prevalence by DBS testing is problematic, with a shift to surveillance of active infection the most relevant to guide policy and practice in this setting.

Droughts and windstorms due to climate change increase variability in species and trait composition of a subtropical monsoon evergreen broadleaf forest in China

BackgroundClimate change is accelerating alterations in forest species and community composition worldwide, especially following extreme events like severe droughts and windstorms. Understanding these effects on subtropical forests is crucial for conservation and forest management, but it remains unclear whether the impacts are stochastic or deterministic. MethodsWe analyzed a unique dataset from a 1-ha permanent plot in a subtropical monsoon broadleaf evergreen forest in China, monitored over 26 years with six surveys from 1994 to 2020. The forest has been free from anthropogenic disturbances for over 400 years. In each survey, we measured all trees with a diameter at breast height (DBH) ​≥ ​1 ​cm, and recorded 11 plant functional traits relating to photosynthesis, wood properties, water use, and nutrient dynamics. Using this data, we calculated species and trait dispersion, assessing short-term (∼5 years) and long-term (26 years) trends in species and trait composition following severe droughts and windstorm events. ResultsSevere droughts, and subsequent droughts, increased both species and trait dispersion, while species composition converged, and trait dispersion remained relatively stable throughout the recovery period. Windstorm events led to increased species dispersion but decreased trait dispersion. We observed a clear directional shift in both species and trait composition under these climatic stressors, with a more pronounced increase in trait dispersion compared to species dispersion. ConclusionIn the short term (∼5 years), severe droughts and windstorms increased species composition divergence, while trait composition responses varied. Over 26 years, deterministic processes mainly drove community composition changes, especially for trait composition, although stochastic processes also played a role. These findings suggest enhancing forest resilience to climatic stressors by protecting adaptive species or increasing species diversity in management practices.

Publisher's Note

BackgroundPrevalence of hepatitis C virus (HCV) antibody (Ab) on dried blood spot (DBS) samples in the Australian Needle and Syringe Program Survey (ANSPS) decreased nationally from 57% in 2015 to 32% in 2022. We aimed to investigate potential explanations for this decline. MethodsChanges in DBS HCV Ab prevalence were investigated by redefining positive cases as those with those with either a positive HCV Ab test result or a self-reported history of ever having HCV treatment (modified prevalence), examining HCV Ab prevalence by birth and age cohorts, and assessing trends in key risk behaviours. ResultsOverall prevalence of DBS HCV Ab declined rapidly and significantly from 57% in 2015 to 32% in 2022 (p<0.001) however modified HCV Ab prevalence remained stable over time (85% and 88% in 2015 and 2022, respectively, p=0.357). The proportion of participants with negative HCV Ab and self-reported HCV infection increased from 20% in 1995 to 40% in 2022 (p<0.001) and the proportion with negative HCV Ab and lifetime HCV treatment increased from 3% in 1999 to 67% in 2022 (p<0.001). We also observed a decreasing trend in DBS HCV Ab prevalence in all birth and age cohorts with a noticeable acceleration in the decline commensurate with the advent of HCV DAA treatment. A long-term decreasing trend was also observed for key risk behaviours (p<0.001) however the short-term trend was not significant for recent receptive syringe sharing. ConclusionThe temporal decline in HCV Ab prevalence appears related to reduced sensitivity of DBS HCV Ab detection with viral clearance following treatment. Since 2016, HCV treatment uptake has increased markedly including among people who inject drugs. In this context, continuing to monitor HCV Ab prevalence by DBS testing is problematic, with a shift to surveillance of active infection the most relevant to guide policy and practice in this setting.

Classifying animal migration patterns using small-shuffle surrogate and PCA evaluating short-term trends

Classifying animal migration patterns using small-shuffle surrogate and PCA evaluating short-term trends

Modeling bitcoin price by using Euler-Maruyama method

&lt;p&gt;In this study, we use Euler-Maruyama method to simulate Bitcoin prices dynamics. We investigate a year-long movement of Bitcoin prices. Daily closing prices were collected over a period starting from May 27th, 2023 and ending on May 27th, 2024. This data provides a comprehensive picture of how Bitcoin behaved on a daily basis throughout that specific year. The Euler-Maruyama method is used as numerical method for solving stochastic differential equations (SDEs). The method involves discretizing the SDE into an iterative process to obtain a simulated price trajectory. The drift term was estimated by the average daily return of Bitcoin prices over the study period. The volatility term was estimated by the standard deviation of daily Bitcoin returns. A Monte Carlo simulation was performed to generate a range of possible price trajectories using the Euler-Maruyama method. The result shows that the Euler-Maruyama method was able to capture the short-term trend of Bitcoin prices effectively. However, the method can also be used to capture the long-term trend of Bitcoin prices.&lt;/p&gt;

National and Regional Trends in the Prevalence of Hypertension in South Korea Amid the Pandemic, 2009-2022: Nationwide Study of Over 3 Million Individuals.

Understanding the association between hypertension prevalence and socioeconomic and behavioral variables during a pandemic is essential, and this analysis should extend beyond short-term trends. This study aims to examine long-term trends in the prevalence of participants diagnosed with and receiving treatment for hypertension, using data collected by a nationally representative survey from 2009 to 2022, which includes the COVID-19 pandemic era. A nationwide, population-based, cross-sectional study used data collected from the South Korea Community Health Survey between 2009 and 2022. The study sample comprised 3,208,710 Korean adults over a period of 14 years. We aimed to assess trends in the prevalence of participants diagnosed with and receiving treatment for hypertension in the national population from 2009 to 2022, with a specific focus on the COVID-19 pandemic, using weighted linear regression models. Among the included 3,072,546 Korean adults, 794,239 (25.85%) were aged 19-39 years, 1,179,388 (38.38%) were aged 40-59 years; 948,097 (30.86%) were aged 60-79 years, and 150,822 (4.91%) were aged 80 years or older. A total of 1,426,379 (46.42%) were men; 761,896 (24.80%) and 712,264 (23.18%) were diagnosed with and received treatment for hypertension, respectively. Although the overall prevalence over the 14-year period increased, the upward trends of patients diagnosed with and receiving treatment for hypertension decreased during the COVID-19 pandemic era compared with the prepandemic era (β difference for trend during vs before the pandemic -.101, 95% CI -0.107 to -0.094 vs -.133, 95% CI -0.140 to -0.127). Notably, the trends in prevalence during the pandemic were less pronounced in subgroups of older adults (≥60 years old) and individuals with higher alcohol consumption (≥5 days/month). This nationwide representative study found that the national prevalence of participants diagnosed with and receiving treatment for hypertension increased during the prepandemic era. However, there was a marked decrease in these trends during the prepandemic era, compared with the pandemic era, particularly among specific subgroups at increased risk of negative outcomes. Future studies are needed to evaluate the factors associated with changes in the prevalence of hypertension during the COVID-19 pandemic.

TEMDI: A Temporal Enhanced Multisource Data Integration model for accurate PM2.5 concentration forecasting

Accurate forecasting of PM2.5 concentration is crucial for implementing effective protective measures and mitigating the adverse health impacts of air pollution. To address the complex spatial propagation dynamics and temporal variations of PM2.5, we developed the Temporal Enhanced Multisource Data Integration (TEMDI) model. This innovative approach combines spatial modeling by a Graph Neural Network (GNN) to capture the intricate spatial propagation patterns based on multi-source data fusion, and a novel Time Series Enhancement (TSE) module that includes Ensemble Empirical Mode Decomposition (EEMD), Gated Recurrent Units (GRUs), and a self-attention mechanism to adequately manage the time series’ short-term and long-term trends. Our results demonstrate TEMDI’s superior performance, achieving exceptionally high Probability of Detection (POD) rates of 96.15%, 80.28%, and 71.86% for forecast horizons of 3, 36, and 72 h, respectively. Furthermore, our feature importance analysis reveals that multi-scale features extracted by the EEMD component become increasingly crucial as the prediction horizon extends. The TEMDI model’s ability to provide accurate, reliable PM2.5 forecasts and its enhanced interpretability position it as a valuable tool for guiding environmental policy and management decisions to safeguard public health.

Short-term Functional Outcomes and Treatment Trends between Branch Atheromatous Disease and Lacunar Infarction: Retrospective Cohort Study of the Nationwide Multicenter Registry.

Branch atheromatous disease (BAD) is a form of ischemic stroke that presents with imaging findings similar to those of lacunar infarction, but has a different pathogenesis and is known to cause progressive paralysis. Due to regional variations, the epidemiology of BAD is not wellunderstood, and its relationship with functional prognosis remains unclear. Using a comprehensive Japanese stroke database, we investigated its epidemiological characteristics and associations with functional outcomes. In this multicenter cohort study, we retrospectively analyzed data from the Saiseikai Stroke Database (2013-2021) including 27 hospitals. We used multivariable logistic regression to calculate adjusted odds ratios (ORs) with 95% confidence intervals (CIs) of BAD compared with LI for functional outcomes at discharge. Ischemic stroke caused by BAD or LI was included and demographic characteristics and clinical data were evaluated and contrasted between BAD and LI. Of the 5,966 analyzed patients, 1,549 (25.9%) had BAD and 4,434 (74.1%) had LI. BAD was associated with worse functional outcomes (adjusted OR of 2.77, 95%CI: 2.42-3.17, relative to LI) and extended hospital stays (median 19 days for BAD vs. 13 days for LI). Moreover, aggressive treatment strategies, including the use of argatroban and dual antiplatelet therapy, were more common in BAD patients. BAD presented worse functional outcomes and longer hospital stays than LI, necessitating treatment plans that take into account its progression and prognosis.

Prediction of Daily Climate Using Long Short-Term Memory (LSTM) Model

Climaate prediction plays a vital role in various sectors, including agriculture, disaster management, and urban planning. Traditional methods for climate forecasting often rely on complex physical models, which require substantial computational resources and may not accurately capture local weather patterns. This study explores the potential of Long Short-Term Memory (LSTM) networks, a type of recurrent neural network, for predicting daily climate variables such as temperature, precipitation, and humidity. Utilizing historical climate data from the city of Delhi, we developed an LSTM model to forecast short-term climate trends. The model consists of two LSTM layers followed by three Dense layers and is compiled with the Adam optimizer, mean squared error loss, and mean absolute error as a metric. Our results demonstrate the model's capability to capture temporal dependencies in climate data, achieving a satisfactory level of accuracy in temperature forecasting. This research underscores the potential of machine learning techniques, particularly LSTM networks, in enhancing climate prediction and contributing to more informed decision-making in weather-sensitive sectors.

Comparative Performance of Neural Network Architectures in Gold Price Prediction: a Study of GRU, N-BEATS, LSTM and Hybrid Models

This study assesses the efficacy of a variety of neural network models in predicting gold prices, with a particular emphasis on GRU, N-BEATS, N-BEATS-GRU, N-BEATS-LSTM, and LSTM. We evaluated the models using a comprehensive dataset and metrics such as MSE, MAE, MAPE, and RMSE. The GRU model demonstrated the highest MAPE of 3.10%, as indicated by the results. N-BEATS was the second-best-performing model. In stark contrast to expectations, hybrid models, notably N-BEATS-LSTM, underperformed. Compared to LSTM-based models, visual analysis demonstrated that GRU and N-BEATS more effectively captured short-term and long-term trends. The results indicate that simplified models, such as GRU, may be more effective than complex hybrids in predicting gold prices.

EFFECTIVENESS OF THE USE OF COMPENSATION BONUSES IN THE CZECH REPUBLIC

Aim: This paper focuses on the evaluation of the impact of the use of compensation bonuses during a pandemic on the economic situation of companies. Methods: In order to achieve this objective, a primary quantitative survey in the form of a questionnaire survey was conducted in Czech enterprises and two research questions were set. The research questions were answered by testing four hypotheses, which focused on testing the relationship between the use of compensation bonuses and the nature of the change in the economic situation of the enterprise in terms of sector, size and prevailing business relationship. The parametric two-sample one-factor ANOVA and Pearson's Chi-squared test were used to test the hypotheses. Main findings: The results showed that the use of compensation bonuses was associated with a negative change in the economic situation of the firms. Differences in the magnitude of the effect were observed in terms of the prevailing business relationship and the size of the enterprises. The business sector did not affect the strength of the association between bonus use and change in economic situation. Limitations of the paper: the paper focuses on observing the short-term trend and is limited to Czech enterprises during the pandemic period.

Short-term trend and temporal variations in atmospheric methane at an Atlantic coastal site in Southwestern Europe

Methane (CH4) was measured at El Arenosillo observatory, in an Atlantic coastal area located in Southwestern Europe, throughout a four-year period (September 2019–December 2023). Short-term trend, temporal variations and patterns were explored. A trend of 12.1 ± 1.1 nmol mol−1 year−1 was obtained based on daily averages. CH4 exhibited its highest mole fraction in cold months and its lowest in summer, and a seasonally varying diurnal cycle was also observed, with peaks in the early morning (7:00–8:00 UTC) and minimum values at 18:00–19:00 UTC. Mitigation strategies should be implemented based on an understanding of CH4 patterns. To achieve this, CH4 variations under an atmosphere governed by two synoptic patterns were studied. The atmospheric dynamic was analysed with the wind fields from ERA5 data reanalysis and the air masses pathways with the back-trajectories computed with the HYSPLIT model. CH4 horizontal distribution was explored with the TROPOMI observations. The CH4 baseline was collected under the influence of Atlantic air, while a rise from 40 to 80 nmol mol−1 was found with continental airflows from the inland Guadalquivir Valley. CH4 under sea-land breezes did not contribute to the increase of CH4. However, XCH4 from TROPOMI showed an accumulation in the marine area of the Gulf of Cadiz. Ongoing CH4 observations will be used to identify potential changes in the trend, understand the contribution of transported CH4 from areas such as the Western Mediterranean Basin, or assess its impact on surface ozone, among other objectives.

Analysis of streamflow and rainfall trends and variability over the Lake Kariba catchment, Upper Zambezi Basin

ABSTRACT Hydro-meteorological trend analysis is critical for assessing climate change and variability at basin and regional levels. This study examined the long- and short-term trends from stream discharge and rainfall data in the Lake Kariba catchment. A trend and change point analysis was carried out on the mean, minimum and maximum monthly average time series for 14 gauging stations that are located within the Kariba catchment. The Mann–Kendall and the Pettitt tests were used to determine the trend and any changes in the long-term average of the time series. The magnitude of the trend was determined by Sen's slope method. The results indicate that generally there has been a decreasing trend in river and rainfall long-term mean values across the catchment. A statistically significant trend (p ≤ 0.05) was observed at Zambezi River at Lukulu, Senanga and Victoria Falls, with a positive correlation in Pearsons's coefficient of water levels and rainfall at Lukulu (0.312) and Senanga (0.365). The decrease in the time series trend and the change point observed have been attributed to anthropogenic activities, climate change and variability impact on the catchment. The findings are critical for climate risk management and reduction decisions for near- and long-term timescales.

P112 Real-time estimation of individual long- and short-term lung functions trends in persons with cystic fibrosis within the Swedish cystic fibrosis registry

P112 Real-time estimation of individual long- and short-term lung functions trends in persons with cystic fibrosis within the Swedish cystic fibrosis registry