This paper considers the problem of predicting earthquakes. It uses a small amount of information to create a descriptive key that can be used as a footprint to describe an event. A frequency grid clusters events that occurred at the same time and then the algorithm averages the history of these events over preceding days, in particular the gaps when the events did not occur. The gaps are measured for the clustered events only and can be used to create a description that is quite unique. Results suggest that seismic events can in fact be traced using this key and subsequently recognised again, if the same conditions reoccur. They also suggest that force direction may be more important than magnitude, for this type of earthquake. Greek and USA datasets have been looked at and the prediction accuracy can be 70% or better. The author therefore suggests that this is an interesting method that deserves attention.

Cervical cancer is a common malignancy in women and has a poor prognosis.More and more studies have shown that autophagy disorder is closely related to the occurrence of tumors. However, the prognostic role of autophagy gene in cervical cancer is still unclear. In this study, we constructed the risk signatures of autophagy related genes to predict the prognosis of cervical cancer. The expression profiles and clinical information of autophagy gene sets were downloaded from the TCGA and GES52903 queues as training sets and validation sets. The cervical normal tissue expression profile data from UCSC XENA website is GTEx data as a supplement to TCGA normal cervical tissue. Univariate COX regression analysis of 17 different autophagy genes with the Consensus approach tumor samples from the TCGA is divided into six subtypes, and the clinical traits in the six subtypes have different distribution, with further then absolute shrinkage and selection operator (LASSO) and multiariable COX regression method finally got seven autophagy genetic risk model is constructed, in the training set, the survival rate of high risk group is lower than the low risk group (p < 0.0001), the validation set,The AUC area of the receiver operating characteristic (ROC) curve, the training set is 0.894, and the verification set is 0.736. We find that the high and low risk score is closely related to the TMN stage (All P is less than 0.05).The nomogram shows that the risk score combined with other indicators such as age, G,T,M, and N better predicts 1-year, 2-year, 3-year survival, and the DCA curve shows that the risk model combined with other indicators produces better clinical efficacy.Then immune cells in 28 in the enrichment score, there were statistically significant differences, high and low risk most GSEA enrichment analysis, the main enrichment in G2 / M checkpoint high-risk score, Genes defining epithelial and mesenchymal transition, raised in response to the low oxygen levels (hypoxia) gene, gene is important to the mitotic spindle assembly, these are closely related with the occurrence of tumor . In conclusion, our constructed autophagy risk signature may be a prognostic tool for cervical cancer.

Effective prediction of wastewater treatment is beneficial for precise control of wastewater treatment processes. The nonlinearity of pollutant indicators such as COD and TP makes the model difficult to fit and has low prediction accuracy. The classical deep learning methods have been shown to perform nonlinear modeling. However, there are enormous numerical differences between multi-dimensional data in the prediction problem of wastewater treatment, such as COD above 3000 mg/L and TP around 30 mg/L. It will make current normalization methods challenging to handle effectively, leading to the training failing to converge and the gradient disappears or exploding. This paper proposes a multi-factor prediction model based on deep learning. The model consists of a combined normalization layer and a codec. The combined normalization layer combines the advantages of three normalization calculation methods: z-score, Interval, and Max, which can realize the adaptive processing of multi-factor data, fully retain the characteristics of the data, and finally cooperate with the codec to learn the data characteristics and output the prediction results. Experiments show that the proposed model can overcome data differences and complex nonlinearity in predicting industrial wastewater pollutant indicators and achieve better prediction accuracy than classical models.

Wireless Sensor Networks (WSNs) are gaining traction in the realm of network communication, renowned for their adaptability, configuration, and flexibility. The forthcoming network traffic within WSNs can be forecasted through temporal sequence models. In this correspondence, We present a method (TSENet) that can accurately predict the traffic in the cellular network. TSENet is composed of transformers and self-attention network. We have designed a temporal transformer module specifically for extracting temporal features. This module accomplishes this by modeling the traffic flow within each grid of the communication network at both near-term and periodical intervals. Simultaneously, we amalgamate the spacial features of each grid with information from its correlated grids, generating spacial predictions within the spacial transformer. Furthermore, we employ self-attention aggregation to capture dependencies between external factor features and celluar data features. Empirical assessments performed on a genuine cellular traffic dataset offer compelling evidence substantiating the efficacy of TSENet.

The main channel for disseminating information is now the Internet. Users have different expectations for the calibre of websites regarding the posted and presented content. The WEB site's quality is influenced by up to 120 factors, each represented by two to fifteen attributes. A major challenge is quantifying the features and evaluating the quality of a website based on the feature counts. One of the aspects that determines a website's quality is its completeness, which focuses on the existence of all the objects and their connections with one another. It isn’t easy to build an expert model based on feature counts to evaluate website quality, so this paper has focused on that challenge. Both a methodology for calculating a website's quality and a parser-based approach for measuring feature counts are offered. We provide a multi-layer perceptron model that is an expert model for forecasting website quality from the "Completeness" perspective. The accuracy of the predictions is 98%, whilst the accuracy of the nearest model is 87%.