Since there is a cost associated with providing 24/7 support, it is also common to divide user support into tiers where a group focused on usability and training of the software provides tier 1 support and another group, consisting of mainly developers, is focused on feature development, software bug fixing, and related issues work separately in a different tier. This paper focuses on software organizations where the developer tier operates from just one part of the world under a single time zone. This group is not available on a 24/7 basis, but the Tier 1 group works in different regions – and hence time zones - throughout the world to deal with user problems and questions. Users can be internal or external, depending on the purpose of the software. This paper discusses only internal users (developers, users and help desk employees who work for the same company) and the delays in support when dealing with these users who may be working in different regions and/or time zones. Tier 1 support is available around the clock due to hiring help desk resources in different locations under different time zones. If an issue cannot be resolved, the Tier 1 workers escalate the issue to the next tier (the developers), who work regular hours in one region under one time zone. This paper uses discrete event simulation modelling to provide insights for a company with a similar structure to better understand possible software support delays. These delays can be reduced, and better overall support can be provided in the future.

The stock market is one of the most important investment opportunities for small and large investors. Stock market fluctuations provide opportunities and risks for investors. However, some fluctuations are considered as enormous threats for most investors; significantly when the stock market has fallen sharply due to external factors and does not reach its previous point in a long time. For example, at the beginning of 2020, financial market indices, especially the stock market, fell sharply due to the COVID-19 pandemic, and for a long time, the indices did not grow significantly. Many investors suffered huge losses during this period. Although much research has been done in stock market forecasting and very efficient models have been proposed so far, no special effort has been made to build a model resistant to the collapse of financial markets. We propose a Convolutional Neural Network (CNN)-based ensemble model that is highly resilient to the stock market crash, especially at the beginning of the COVID-19 period. The proposed model not only avoids losing money in financial crises but can bring significant returns to investors. Experimental results show that the ensemble CNN models using Gramian Angular Fields (GAF) has greatly improved the resistance of the model in critical market conditions.

The era people live in is the era of big data, and massive data carry a large amount of information. This study aims to analyze RFID data based on big data and clustering algorithms. In this study, a RFID data extraction technology based on joint Kalman filter fusion is proposed. In the system, the proposed data extraction technology can effectively read RFID tags. The data are recorded, and the KM-KL clustering algorithm is proposed for RFID data, which combines the advantages of the K-means algorithm. The improved KM-KL clustering algorithm can effectively analyze and evaluate RFID data. The experimental results of this study prove that the recognition error rate of the RFID data extraction technology based on the joint Kalman filter fusion is only 2.7%. The improved KM-KL clustering algorithm also has better performance than the traditional algorithm.

The increasing number of car accidents is a significant issue in current transportation systems. According to the World Health Organization (WHO), road accidents are the eighth highest top cause of death around the world. More than 80% of road accidents are caused by distracted driving, such as using a mobile phone, talking to passengers, and smoking. A lot of efforts have been made to tackle the problem of driver distraction; however, no optimal solution is provided. A practical approach to solving this problem is implementing quantitative measures for driver activities and designing a classification system that detects distracting actions. In this paper, we have implemented a portfolio of various ensemble deep learning models that have been proven to efficiently classify driver distracted actions and provide an in-car recommendation to minimize the level of distractions and increase in-car awareness for improved safety. This paper proposes E2DR, a new scalable model that uses stacking ensemble methods to combine two or more deep learning models to improve accuracy, enhance generalization, and reduce overfitting, with real-time recommendations. The highest performing E2DR variant, which included the ResNet50 and VGG16 models, achieved a test accuracy of 92% as applied to state-of-the-art datasets, including the State Farm Distracted Drivers dataset, using novel data splitting strategies.

Smart devices are used in the era of the Internet of Things (IoT) to provide efficient and reliable access to services. IoT technology can recognize comprehensive information, reliably deliver information, and intelligently process that information. Modern industrial systems have become increasingly dependent on data networks, control systems, and sensors. The number of IoT devices and the protocols they use has increased, which has led to an increase in attacks. Global operations can be disrupted, and substantial economic losses can be incurred due to these attacks. Cyberattacks have been detected using various techniques, such as deep learning and machine learning. In this paper, we propose an ensemble staking method to effectively reveal cyberattacks in the IoT with high performance. Experiments were conducted on three different datasets: credit card, NSL-KDD, and UNSW datasets. The proposed stacked ensemble classifier outperformed the individual base model classifiers.

Insider trading has become a topic discussed globally. This trading is a criminal offence punishable by an attempt to gain profit using financial information that is not available to the public and can cause a significant market reaction. However, outlier detection studies using statistical approach on detecting insider trading practices are relatively scarce. Therefore, this study aims to identify outliers in the stock market in order to detect insider trading behaviour. This paper proposes an instrumental research regarding the using of sequential fences analysis in the identification of stock market anomaly values in China’s stock market. In order to attain the objective of this research, we exemplified the sequential fences analysis on data related to the China’s securities market insider trading. The results show the viability of sequential fences in detecting unusual behaviour in stock market data and showing abnormal activity in Chinese capital markets.

The Internet of Things (IoT) is a system that connects physical computing devices, sensors, software, and other technologies, and data can be collected, transferred, and exchanged with other devices over the network without requiring human interactions. One challenge that the development of IoT is facing is the existence of malicious botnet attacks. Recently, research on botnet traffic detection has become popular. However, most state-of-the-art detection techniques focus on one specific type of device in IoT or one particular botnet attack type. Therefore, we propose a neural network-based algorithm, 2-FFNN, which can detect malicious traffic in the IoT environment and be deployed generally without restricting device or attack types. The proposed model consists of two levels of the Feed Forward Neural Network framework to identify some hard-to-detect botnet attacks. Experimental analysis has shown that the 2-FFNN outperforms the baseline FFNN and some state-of-the-art methods based on the detection accuracy and ROC score.

In this study, calendar anomalies, a topic that many researchers focus on, are examined. It is being investigated whether it is possible to obtain an abnormal return with the perception of anomaly in a market. For this reason, the Event Study method is used and the holiday effect anomaly is emphasized. Within the scope of the study, national and religious holidays in Turkey were discussed. In the study; daily data were used for the years 2017, 2018 and 2019. Thus, it has tried to determine whether there is a holiday anomaly could provide abnormal returns in Turkey. Sector-based research results do not reveal any important situation in other sectors except the service sector. In the service sector, it has been observed that abnormal returns are predominantly positive before national holidays and negative abnormal returns before religious holidays. Briefly, it is necessary to pay attention especially to the service sector around the holiday periods. In the near-holiday periods, there is an opportunity in order to obtain an extraordinary return from the service sector, as well as the sector risks more during these periods.

Data collected from social media such as tweets, posts, and blogs can assist in an early indication of market sentiment in the financial field. This has frequently been conducted on Twitter data in particular. Using data mining techniques, opinion mining, machine learning, natural language processing (NLP), and knowledge management, the underlying public mood states and sentiment can be uncovered. As cryptocurrencies play an increasingly significant role in global economies, there is an evident relationship between Twitter sentiment and future price fluctuations in Bitcoin. This paper assesses Tweets' collection, manipulation, and interpretation to predict early market movements of cryptocurrency. More specifically, sentiment analysis and text mining methods, including Logistic Regressions, Binary Classified Vector Prediction, Support Vector Mechanism, and Naive Bayes, were considered. Each model was evaluated on their ability to predict public mood states as measured by ‘tweets' from Twitter during the era of covid-19. An XGBoost-Composite ensemble model is constructed, which achieved higher performance than the state-of-the-art prediction models.