Review of ML and AutoML Solutions to Forecast Time-Series Data

Deep learning-driven hybrid model for short-term load forecasting and smart grid information management

Accurate power load forecasting is crucial for the sustainable operation of smart grids. However, the complexity and uncertainty of load, along with the large-scale and high-dimensional energy information, present challenges in handling intricate dynamic features and long-term dependencies. This paper proposes a computational approach to address these challenges in short-term power load forecasting and energy information management, with the goal of accurately predicting future load demand. The study introduces a hybrid method that combines multiple deep learning models, the Gated Recurrent Unit (GRU) is employed to capture long-term dependencies in time series data, while the Temporal Convolutional Network (TCN) efficiently learns patterns and features in load data. Additionally, the attention mechanism is incorporated to automatically focus on the input components most relevant to the load prediction task, further enhancing model performance. According to the experimental evaluation conducted on four public datasets, including GEFCom2014, the proposed algorithm outperforms the baseline models on various metrics such as prediction accuracy, efficiency, and stability. Notably, on the GEFCom2014 dataset, FLOP is reduced by over 48.8%, inference time is shortened by more than 46.7%, and MAPE is improved by 39%. The proposed method significantly enhances the reliability, stability, and cost-effectiveness of smart grids, which facilitates risk assessment optimization and operational planning under the context of information management for smart grid systems.

Inefficacious drugs against covid-19: analysis of sales, tweets, and search engines

OBJECTIVE

Assess the correlation between the sales of two drugs with no proven efficacy against covid-19, ivermectin and chloroquine, and other relevant variables, such as Google® searches, number of tweets related to these drugs, number of cases and deaths resulting from covid-19.

METHODS

The methodology adopted in this study has four stages: data collection, data processing, exploratory data analysis, and correlation analysis. Spearman's method was used to obtain cross-correlations between each pair of variables.

RESULTS

The results show similar behaviors between variables. Peaks occurred in the same or near periods. The exploratory data analysis showed shortage of chloroquine in the period corresponding to the beginning of advertising for the application of these drugs against covid-19. Both drugs showed a high and statistically significant correlation with the other variables. Also, some of them showed a higher correlation with drug sales when we employed a one-month lag. In the case of chloroquine, this was observed for the number of deaths. In the case of ivermectin, this was observed for the number of tweets, cases, and deaths.

CONCLUSIONS

The results contribute to decision making in crisis management by governments, industries, and stores. In times of crisis, as observed during the covid-19 pandemic, some variables can help sales forecasting, especially Google® and tweets, which provide a real-time analysis of the situation. Monitoring social media platforms and search engines would allow the determination of drug use by the population and better prediction of potential peaks in the demand for these drugs.

High-Throughput Analysis of Leaf Chlorophyll Content in Aquaponically Grown Lettuce Using Hyperspectral Reflectance and RGB Images

Chlorophyll content reflects plants' photosynthetic capacity, growth stage, and nitrogen status and is, therefore, of significant importance in precision agriculture. This study aims to develop a spectral and color vegetation indices-based model to estimate the chlorophyll content in aquaponically grown lettuce. A completely open-source automated machine learning (AutoML) framework (EvalML) was employed to develop the prediction models. The performance of AutoML along with four other standard machine learning models (back-propagation neural network (BPNN), partial least squares regression (PLSR), random forest (RF), and support vector machine (SVM) was compared. The most sensitive spectral (SVIs) and color vegetation indices (CVIs) for chlorophyll content were extracted and evaluated as reliable estimators of chlorophyll content. Using an ASD FieldSpec 4 Hi-Res spectroradiometer and a portable red, green, and blue (RGB) camera, 3600 hyperspectral reflectance measurements and 800 RGB images were acquired from lettuce grown across a gradient of nutrient levels. Ground measurements of leaf chlorophyll were acquired using an SPAD-502 m calibrated via laboratory chemical analyses. The results revealed a strong relationship between chlorophyll content and SPAD-502 readings, with an R2 of 0.95 and a correlation coefficient (r) of 0.975. The developed AutoML models outperformed all traditional models, yielding the highest values of the coefficient of determination in prediction (Rp2) for all vegetation indices (VIs). The combination of SVIs and CVIs achieved the best prediction accuracy with the highest Rp2 values ranging from 0.89 to 0.98, respectively. This study demonstrated the feasibility of spectral and color vegetation indices as estimators of chlorophyll content. Furthermore, the developed AutoML models can be integrated into embedded devices to control nutrient cycles in aquaponics systems.

Automated Prediction of Crack Propagation Using H2O AutoML

Crack propagation is a critical phenomenon in materials science and engineering, significantly impacting structural integrity, reliability, and safety across various applications. The accurate prediction of crack propagation behavior is paramount for ensuring the performance and durability of engineering components, as extensively explored in prior research. Nevertheless, there is a pressing demand for automated models capable of efficiently and precisely forecasting crack propagation. In this study, we address this need by developing a machine learning-based automated model using the powerful H2O library. This model aims to accurately predict crack propagation behavior in various materials by analyzing intricate crack patterns and delivering reliable predictions. To achieve this, we employed a comprehensive dataset derived from measured instances of crack propagation in Acrylonitrile Butadiene Styrene (ABS) specimens. Rigorous evaluation metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2) values, were applied to assess the model's predictive accuracy. Cross-validation techniques were utilized to ensure its robustness and generalizability across diverse datasets. Our results underscore the automated model's remarkable accuracy and reliability in predicting crack propagation. This study not only highlights the immense potential of the H2O library as a valuable tool for structural health monitoring but also advocates for the broader adoption of Automated Machine Learning (AutoML) solutions in engineering applications. In addition to presenting these findings, we define H2O as a powerful machine learning library and AutoML as Automated Machine Learning to ensure clarity and understanding for readers unfamiliar with these terms. This research not only demonstrates the significance of AutoML in future-proofing our approach to structural integrity and safety but also emphasizes the need for comprehensive reporting and understanding in scientific discourse.

Mechanical effect of reconstructed shapes of autologous ossicles on middle ear acoustic transmission

Conductive hearing loss is caused by a variety of defects, such as chronic otitis media, osteosclerosis, and malformation of the ossicles. In such cases, the defective bones of the middle ear are often surgically reconstructed using artificial ossicles to increase the hearing ability. However, in some cases, the surgical procedure does not result in increased hearing, especially in a difficult case, for example, when only the footplate of the stapes remains and all of the other bones are destroyed. Herein, the appropriate shapes of the reconstructed autologous ossicles, which are suitable for various types of middle-ear defects, can be determined by adopting an updating calculation based on a method that combines numerical prediction of the vibroacoustic transmission and optimization. In this study, the vibroacoustic transmission characteristics were calculated for bone models of the human middle ear by using the finite element method (FEM), after which Bayesian optimization (BO) was applied. The effect of the shape of artificial autologous ossicles on the acoustic transmission characteristics of the middle ear was investigated with the combined FEM and BO method. The results suggested that the volume of the artificial autologous ossicles especially has a great influence on the numerically obtained hearing levels.

A Low-Cost, Low-Power, Multisensory Device and Multivariable Time Series Prediction for Beehive Health Monitoring

We present a custom platform that integrates data from several sensors measuring synchronously different variables of the beehive and wirelessly transmits all measurements to a cloud server. There is a rich literature on beehive monitoring. The choice of our work is not to use ready platforms such as Arduino and Raspberry Pi and to present a low cost and power solution for long term monitoring. We integrate sensors that are not limited to the typical toolbox of beehive monitoring such as gas, vibrations and bee counters. The synchronous sampling of all sensors every 5 min allows us to form a multivariable time series that serves in two ways: (a) it provides immediate alerting in case a measurement exceeds predefined boundaries that are known to characterize a healthy beehive, and (b) based on historical data predict future levels that are correlated with hive's health. Finally, we demonstrate the benefit of using additional regressors in the prediction of the variables of interest. The database, the code and a video of the vibrational activity of two months are made open to the interested readers.

Artificial Intelligence, Wearables and Remote Monitoring for Heart Failure: Current and Future Applications

Substantial milestones have been attained in the field of heart failure (HF) diagnostics and therapeutics in the past several years that have translated into decreased mortality but a paradoxical increase in HF-related hospitalizations. With increasing data digitalization and access, remote monitoring via wearables and implantables have the potential to transform ambulatory care workflow, with a particular focus on reducing HF hospitalizations. Additionally, artificial intelligence and machine learning (AI/ML) have been increasingly employed at multiple stages of healthcare due to their power in assimilating and integrating multidimensional multimodal data and the creation of accurate prediction models. With the ever-increasing troves of data, the implementation of AI/ML algorithms could help improve workflow and outcomes of HF patients, especially time series data collected via remote monitoring. In this review, we sought to describe the basics of AI/ML algorithms with a focus on time series forecasting and the current state of AI/ML within the context of wearable technology in HF, followed by a discussion of the present limitations, including data integration, privacy, and challenges specific to AI/ML application within healthcare.