Wastewater-based prediction of COVID-19 cases using a random forest algorithm with strain prevalence data: A case study of five municipalities in Latvia.

Wastewater-based epidemiology (WBE) is a rapid and cost-effective method that can detect SARS-CoV-2 genomic components in wastewater and can provide an early warning for possible COVID-19 outbreaks up to one or two weeks in advance. However, the quantitative relationship between the intensity of the epidemic and the possible progression of the pandemic is still unclear, necessitating further research. This study investigates the use of WBE to rapidly monitor the SARS-CoV-2 virus from five municipal wastewater treatment plants in Latvia and forecast cumulative COVID-19 cases two weeks in advance. For this purpose, a real-time quantitative PCR approach was used to monitor the SARS-CoV-2 nucleocapsid 1 (N1), nucleocapsid 2 (N2), and E genes in municipal wastewater. The RNA signals in the wastewater were compared to the reported COVID-19 cases, and the strain prevalence data of the SARS-CoV-2 virus were identified by targeted sequencing of receptor binding domain (RBD) and furin cleavage site (FCS) regions employing next-generation sequencing technology. The model methodology for a linear model and a random forest was designed and carried out to ascertain the correlation between the cumulative cases, strain prevalence data, and RNA concentration in the wastewater to predict the COVID-19 outbreak and its scale. Additionally, the factors that impact the model prediction accuracy for COVID-19 were investigated and compared between linear and random forest models. The results of cross-validated model metrics showed that the random forest model is more effective in predicting the cumulative COVID-19 cases two weeks in advance when strain prevalence data are included. The results from this research help inform WBE and public health recommendations by providing valuable insights into the impact of environmental exposures on health outcomes.

Combining knowledge graph with deep adversarial network for water quality prediction.

Water quality prediction is an important research focus in smart water and can provide the support to control and reduce water pollution. However, existing water quality prediction models are mainly data-driven and only rely on various sensor data. This paper proposes a new water quality prediction modeling approach integrating data and knowledge. We develop a water quality prediction framework that combines knowledge graph and deep adversarial networks. The knowledge extraction and management compound extracts the water quality knowledge graph from different knowledge sources by using the deep adversarial joint model. The fusing parameter importance learning compound calculates the contribution of parameters in water quality prediction by taking into account both knowledge and data levels of correlation. Finally, a water quality prediction model combining weighted CNN-LSTM with adversarial learning predicts the values of total nitrogen based on real-time monitoring data. The experimental results on monitoring data from the Juhe River of China show that the proposed model can greatly improve the effect of water quality prediction.

Parameter importance assessment improves efficacy of machine learning methods for predicting snow avalanche sites in Leh-Manali Highway, India.

Due to ongoing climate change, water mass redistribution and related hazards are getting stronger and frequent. Therefore, predicting extreme hydrological events and related hazards is one of the highest priorities in geosciences. Machine Learning (ML) methods have shown promising prospects in this venture. Every ML method requires training where we know both the output (extreme event) and input (relevant physical parameters and variables). This step is critical to the efficacy of the ML method. The usual approach is to include a wide variety of hydro-meteorological observations and physical parameters, but recent advances in ML indicate that the efficacy of ML may not improve by increasing the number of input parameters. In fact, including unimportant parameters decreases the efficacy of ML algorithms. Therefore, it is imperative that the most relevant parameters are identified prior to training. In this study, we demonstrate this concept by predicting avalanche susceptibility in Leh-Manali highway (one of the most severely affected regions in India) with and without Parameter Importance Assessment (PIA). The avalanche locations were randomly divided into two groups: 70% for training and 30% for testing. Then, based on temporal and spatial sensor data, eleven avalanche influencing parameters were considered. The Boruta algorithm, an extension of Random Forest (RF) ML method that utilizes the importance measure to rank predictors, was used and it found nine out of eleven parameters to be important. Support Vector Machine (SVM) based ML technique is used for avalanche prediction, and to be comprehensive, four different kernel functions were employed (linear, polynomial, sigmoid, and radial basis function (RBF)). The prediction accuracy for linear, polynomial, sigmoid, and RBF kernels, with all the eleven parameters were found to be 80.4%, 81.7%, 39.2%, and 85.7%, respectively. While, when using selected parameters, the prediction accuracy for linear, polynomial, sigmoid, and RBF kernels were 84.1%, 86.6%, 43.0%, and 87.8%, respectively. We also identified locations where occurrences of avalanches are most likely. We conclude that parameter selection should be considered when applying ML methods in geosciences.

Applying data mining techniques to determine important parameters in chronic kidney disease and the relations of these parameters to each other.

Introduction: Chronic kidney disease (CKD) includes a wide range of pathophysiological processes which will be observed along with abnormal function of kidneys and progressive decrease in glomerular filtration rate (GFR). According to the definition decreasing GFR must have been present for at least three months. CKD will eventually result in end-stage kidney disease. In this process different factors play role and finding the relations between effective parameters in this regard can help to prevent or slow progression of this disease. There are always a lot of data being collected from the patients' medical records. This huge array of data can be considered a valuable source for analyzing, exploring and discovering information. Objectives: Using the data mining techniques, the present study tries to specify the effective parameters and also aims to determine their relations with each other in Iranian patients with CKD. Material and Methods: The study population includes 31996 patients with CKD. First, all of the data is registered in the database. Then data mining tools were used to find the hidden rules and relationships between parameters in collected data. Results: After data cleaning based on CRISP-DM (Cross Industry Standard Process for Data Mining) methodology and running mining algorithms on the data in the database the relationships between the effective parameters was specified. Conclusion: This study was done using the data mining method pertaining to the effective factors on patients with CKD.