Tag: time series analysis

An ecological time-series study in Shanghai found limited evidence linking air pollution and weather to drug-resistant tuberculosis after adjusting for ...

A 51-year time-series analysis finds food price volatility raises Ethiopian under-five mortality mainly over medium and long horizons, with declines ...

Zimbabwe sits among the world's most remittance-dependent economies, and a new open-access study argues that the country's chronic economic uncertainty ...

A 31-year time-series analysis of Somalia finds humanitarian aid supports food security in the long run while food aid, conflict ...

A Spanish regional study found that short-term increases in government pharmaceutical spending were associated with lower premature treatable mortality, especially ...

A hybrid LSTM and CNN model outperformed traditional time series and individual machine learning models in predicting monthly hepatitis B ...

A time-series analysis of India from 1990 to 2018 finds that natural resource depletion and renewable energy consumption increase ecological ...

A new study projects that India's greenhouse gas emissions will continue rising through 2035 under current trends.

A study of 34 real footwear production observations found ARIMA delivered the most accurate short-term forecasts of pairs per hour, ...

A conditional diffusion model reached an F1-score of 0.975 when detecting abnormal data in a 90-day, 18-channel bridge monitoring dataset ...

A hybrid model combining visibility-graph features with an explicit data-quality score cut 30-minute urban carbon monoxide forecast error by 8.7% ...

A surveillance analysis found that reported incidence and mortality from five vector-borne diseases were substantially lower in China during 2020–2023, ...

A 16-year Malaysian ecological time-series study found that non-fatal intentional poisoning reports were weakly associated with official suicide mortality from ...

An analysis of 23,755 reported mumps cases in Chongqing found delayed, nonlinear associations with temperature, humidity and air pollution, with ...

A hybrid deep learning model combining CNN and bidirectional LSTM networks can identify MOOC students at risk of dropping out ...

A six-year time-series study in Guiyang, a low-pollution karst city in Southwest China, finds that short-term exposure to six major ...

A new Oxford study introduces OFTER, an online forecasting pipeline that combines ARIMA models, PCA-based dimensionality reduction, k-nearest neighbors and ...

Researchers have developed an unsupervised deep learning model called GSA-VAE that detects faults in electric vehicle batteries by fusing causal ...

A compact deep learning model that mathematically separates normal machining signals from anomalous disturbances has set new benchmarks for predicting ...

A large retrospective benchmark across six countries and more than 70 infectious diseases finds that zero-shot time series foundation models ...