Recent Advances in Computer Science and Communications - Volume 16, Issue 1, 2023

Background: In reality, time series is composed of several basic components, which have linear, nonlinear and non-stationary characteristics at the same time. Directly using a single model will show some limitations and the prediction accuracy is difficult to improve. Methods: We propose a mixed forecasting model based on time series decomposition, namely STL-EEMD-LSTM model. First, we use STL filtering algorithm to decompose the time series to obtain the trend component, seasonal component and the remainder component of the time series; then we use EEMD to decompose the seasonal component and the remainder component to obtain multiple sub-sequences. After this, we reconstruct the new seasonal component and the remainder component according to the fluctuation frequency of the sub-sequence. Finally, we use LSTM to build a prediction model for each component obtained by decomposition. Results: We applied the proposed model to simulation data and the time series of satellite calibration parameters and found that the hybrid prediction model proposed in this paper has high prediction accuracy. Conclusion: Therefore, we believe that our proposed model is more suitable for the prediction of time series with complex components.

Background: Cloud computing refers to the computing capacities of remote computers, where the user has considerable computing power without having to own power units. The probability of failures, which can occur during execution, increases in the number of nodes. Since failures cannot be completely avoided, one solution is to use failure tolerance mechanisms. Predicting failures has become a major task for engineers and software developers, as failure increases resource usage costs. Objectives and Methods: This paper presents a hybrid method of predicting failures in a cloudcomputing environment based on the passive replication technique and multi-agent systems. It detects failures, improves the average response time and minimizes lost time. This method makes it possible to efficiently and transparently guarantee the continuity of cloud computing services in the presence of failures. Results: The results show that the proposed method performs well in the presence of failures, improves the response time and minimizes the additional costs caused by the failures. Conclusion: This paper proposes a hybrid method of predicting failures in cloud-computing based on the passive replication technique and multi-agent systems to detect failures and minimize lost time. The replication technique works by duplicating some system components, which are deployed simultaneously across different resources. This technique aims to make the system robust, increase availability and guarantee the execution of jobs. In addition, it is suitable for long-running tasks.

Objective: Natural disasters caused by landslides have done great harm to agricultural production, people's lives, and property. Considering the slope disaster caused by heavy rainfall, it is important to establish an early warning system to monitor rainfall disaster prevention. Huafang University Slope Sustainable Development Research Center (HUSSDRC) has set up a meteorological station equipped with many sensors to provide early warning for landslides in Taiwan. Since the amount of data collected will soon become very large, there is a need to implement strong parallel frameworks containing information from the meteorological station and the displacement of tiltmeters required to predict the landslides caused by rainfall. Apache Spark (AS) is a general framework that contains the parallel process engine for data analytics. In this study, a hybrid method is utilized to predict rainfall-induced landslides. The proposed method combines support vector regression (SVR) with an artificial bee colony (ABC) algorithm on the parallel platform of AS. For the proposed method, the RMSE is 0.562, and it is the best value among these compared approaches. Methods: The SVR together with an ABC algorithm is applied to predict rainfall-induced landslides on AS. The AS can perform parallel data analytics in memory to speed up performance. However, it is hard to set up the best parameters for SVR. Thereafter, the ABC algorithm is utilized to search for the best parameters for SVR. Results: Compared with other methods, the proposed method results provide the smallest root mean square error (RMSE) for predicting rainfall-induced landslides Conclusion: A hybrid method is proposed to predict rainfall-induced landslides. The proposed hybrid method is based on the parallel platform of AS in which SVR predicts the rainfall-induced landslides, and the ABC algorithm adjusts the best values of parameters for SVR. The comparison of RMSE for the method with existing approaches shows that the method indeed has the best value among compared approaches.

Background: Software Measurement (SM) is pivotal for efficient planning, scheduling, tracking, and controlling software projects, which significantly affects the success or failure of a project. Machine Learning (ML) techniques have been applied for software measurements for the past three decades. Objective: This review aims to synthesize the studies conducted from the years 1990 to 2020 to provide a broad picture of the role of machine learning in the world of software measurement. Methods: The Systematic Literature Review (SLR) approach is adopted to conduct this review. Inclusion/exclusion criteria are defined to select the most relevant studies. The researcher searched the prominent databases and archives and obtained around 2310 studies, from which 108 studies were selected as primary studies, which were then summarized to accomplish the goals of this review. Results: The distinguished contribution of this review is that it covers all aspects of software measurements from the perspective of the application of machine learning techniques. It guides the software practitioners regarding the journey of software measurements to date using machine learning techniques in a single synthesized study. It further provides future guidelines for the researchers working in this field. Conclusion: Machine learning techniques have extensive applications for software measurements. Software fault prediction and software effort estimation are the most prevailing SM tasks harnessing the ML techniques. The most popular ML technique is the artificial neural network for SM. For empirical studies, NASA and promise datasets are extensively used. Over the last decade (2011-2020), SM paradigm has been shifting towards ensembles of individual ML models and deep learning models.

Background: The increasing demand for Internet of Things (IoT) devices has been accompanied by an increase in the amount of data generated by them that need to be transferred, processed, and stored. Transferring the data of these devices to cloud computing leads to the occurrence of bottlenecks in the data networks, and therefore, an increase in the delay. Edge computing is used to reduce the delay by executing the computing process close to the data source, and it provides an important security advantage by reducing the amount of data actually at risk in a single moment. Furthermore, it provides an affordable and scalable avenue, providing unparalleled reliability. Objective: The study aimed to highlight the challenges associated with moving data from the cloud to the edge. Methods: In this paper, a survey has been presented related to edge computing from the perspective of requirements and applications, mentioning the most important contributions made by researchers in this field. Conclusion: The increase in the number of sensors in the Internet of Things revolution created a great momentum that can be addressed by relying on the edges close to the user to ensure the confidentiality of information, especially in real-time applications, such as health care systems and drones, etc.

Background: Investors estimate how a company's stock or financial instrument will perform in the future, which is known as the stock market prediction. Stock markets are one of the many industries that have benefited substantially from the incredible breakthroughs in machine learning. To effectively estimate these markets, many researchers and companies are continually researching and developing various state-of-the-art approaches and algorithms. Objective: The objective is to predict stock prices based on public sentiments. With a big collection of data from microblogging sites like Twitter, it is possible to analyse the thoughts or feelings of users on a wide scale. These sentiments play a major part in the way the stock market works. We review multiple papers and provide the advantages and disadvantages of various methods. Methods: An in-depth examination of the most recent methodologies for predicting stock market values using sentiment analysis is offered, as well as the multiple consequences for stock markets when epidemics or major events occur. Results: According to the findings, impact sentiment analysis has a significant part in predicting stock market price movement, allowing for greater profit. Conclusion: With modern machine learning and deep learning processes, we can forecast stock costs with a few degrees of precision. This research examines how stock expectations have changed over time, as well as the most recent and effective technique for forecasting, supplying, and minimizing speculators' losses.

Around trillions of data are uploaded to the internet every year. Extracting useful information using only a few keywords has become a major challenge. The field of Query Reformulation (QR) is focused on the efficient retrieval of information to overcome this. It is widely used in the domain of information retrieval (IR) and related fields such as search engines, multimedia IR, cross-language IR, recommender systems, and so on. Query reformulation techniques incur extra computational costs. Due to this reason, the use of query reformulation techniques is sometimes prohibited in internet searches as searching over the internet requires a fast response time. But due to the success of NLP (Natural Language Processing) using machine learning/deep learning in recent years, there has been a boom of study in this area. In this literature, a variety of term selection, term extraction, and query reformulation strategies based on recent technologies used by researchers have been presented, necessitating a wide survey to focus research in this promising area. Recent QR approaches and the datasets, techniques, and evaluation metrics used in this paper will help researchers understand and focus more on research in this promising area so that a better solution will be proposed. From the survey, it may be observed that one of the hottest subjects in the field of IR right now is applying deep learning to IR systems for query reformulation.