Traffic prediction is a critical task for intelligent transportation systems (ITS). Prediction at intersections is challenging as it involves various participants, such as vehicles, cyclists, and pedestrians. In this paper, we propose a novel approach for the accurate intersection traffic prediction by introducing extra data sources other than road traffic volume data into the prediction model. In particular, we take advantage of the data collected from the reports of road accidents and roadworks happening near the intersections. In addition, we investigate two types of learning schemes, namely batch learning and online learning. Three popular ensemble decision tree models are used in the batch learning scheme, including Gradient Boosting Regression Trees (GBRT), Random Forest (RF) and Extreme Gradient Boosting Trees (XGBoost), while the Fast Incremental Model Trees with Drift Detection (FIMT-DD) model is adopted for the online learning scheme. The proposed approach is evaluated using public data sets released by the Victorian Government of Australia. The results indicate that the accuracy of intersection traffic prediction can be improved by incorporating nearby accidents and roadworks information.

With the increasing technological development that has led to the complexity of big data systems, the importance lies in the challenge that ensures the security of sensitive information. Encryption is one of the basic methods used to protect data, hence the importance of the encryption key and its sensitivity, which play a vital role in the strength of encryption. Encryption sensitivity is the simple change in the encryption key that produces a very different encrypted text. This study is concerned with methods of controlling the sensitivity of the encryption key and its effect on the strength of encryption of big data. This context is in line with the nature of cloud data and the focus on the attacks that this data suffers from, such as brute-force attacks and statistical attacks. The research discusses the components that make up the encryption key, logistics maps, and chaos. The results reached by the study proved the merit of the research in terms of accuracy 1015 and appropriate key sensitivity 2128. This study discussed future challenges and the possibility of using artificial intelligence algorithms and adaptive security algorithms and solving quantum encryption problems.

The agricultural sector's importance is highlighted by the upcoming global population growth predicted by the food and agriculture organization. This growth will lead to increased food demand. However, traditional farming methods require a lot of time and effort and result in diminishing returns. Recent technological advancements, especially in the Internet of Things (IoT), are changing this landscape by introducing smart agriculture. Smart agriculture aims to improve decision-making and crop management using IoT's connectivity and data analysis capabilities. Artificial intelligence (AI) is becoming crucial in this context, offering speed, accuracy, and cost-effectiveness. Machine learning, a type of AI, is beneficial in detecting yields and forecasting weather. This survey highlights the evolving field of intelligent agriculture, covering topics like crop monitoring, and anomaly detection, and explains the main challenges in farming practices.