More than six million people died of the COVID-19 by April 2022. The heavy casualties have put people on great and urgent alert, and people have tried to find all kinds of information to keep them from being infected by the coronavirus. This research tries to find out whether the mobile health text information sent to people's devices is correct as smartphones have become the major information source for people. The proposed method uses various mobile information retrieval and data mining technologies including lexical analysis, stopword elimination, stemming, and decision trees to classify the mobile health text information to one of the following classes: (1) true, (2) fake, (3) misinformative, (4) disinformative, and (5) neutral. Experiment results show the accuracy of the proposed method is above the threshold value 50% but is not optimal. It is because the problem, mobile text misinformation identification, is intrinsically difficult.

This work presents an investigation into the ability of recurrent neural networks (RNNs) to provide long term predictions of time series data generated by coal fired power plants. While there are numerous studies which have used artificial neural networks (ANNs) to predict coal plant parameters, to the authors’ knowledge these have almost entirely been restricted to predicting values at the next time step, and not farther into the future. Using a novel neuro-evolution strategy called Evolutionary eXploration of Augmenting Memory Models (EXAMM), we evolved RNNs with advanced memory cells to predict per-minute plant parameters and per-hour boiler parameters up to 8 hours into the future. These data sets were challenging prediction tasks as they involve spiking behavior in the parameters being predicted. While the evolved RNNs were able to successfully predict the spikes in the hourly data they did not perform very well in accurately predicting their severity. The per-minute data proved even more challenging as medium range predictions miscalculated the beginning and ending of spikes, and longer range predictions reverted to long term trends and ignored the spikes entirely. We hope this initial study will motivate further study into this highly challenging prediction problem. The use of fuel properties data generated by a new Coal Tracker Optimization (CTO) program was also investigated and this work shows that their use improved predictive ability of the evolved RNNs.

Big data provides a challenging environment to store, process and analyze large scale data. Various requirements that impact the architectural solution of big data include the source of data and its involved features such as volume, velocity, variety and the type of data. While processing big data, other challenges raised related to scalability, availability, integrity, concurrency, parallelism and performance. Because of all these features and requirements, building a suitable big data solution needs to consider the architectural solutions to satisfy those different elements of the system. Different software architectural styles exist. The aim of this paper is to provide an overview of the important commonly used architecture styles for building big data systems, compare their benefits, performance and main components. And mostly cover how each style can help in resolving the challenges required by developing big data software systems. The goal is to identify and discuss software architectural issues imposed by Hadoop that impact its performance. A new hybrid architecture system to achieve the requirement for Hadoop is proposed and all possible challenges the Hybrid system could face are investigated.