Optical burst switching (OBS) network is a new generation optical communication technology. In an OBS network, an edge node first sends a control packet, called burst header packet (BHP) which reserves the necessary resources for the upcoming data burst (DB). Once the reservation is complete, the DB starts travelling to its destination through the reserved path. A notable attack on OBS network is BHP flooding attack where an edge node sends BHPs to reserve resources, but never actually sends the associated DB. As a result the reserved resources are wasted and when this happen in sufficiently large scale, a denial of service (DoS) may take place. In this study, we propose a semi-supervised machine learning approach using k-means algorithm, to detect malicious nodes in an OBS network. The proposed semi-supervised model was trained and validated with small amount data from a selected dataset. Experiments show that the model can classify the nodes into either behaving or not-behaving classes with 90% accuracy when trained with just 20% of data. When the nodes are classified into behaving, not-behaving and potentially not-behaving classes, the model shows 65.15% and 71.84% accuracy if trained with 20% and 30% of data respectively. Comparison with some notable works revealed that the proposed model outperforms them in many respects.

Since the early days of the petroleum industry, prediction of oil prices has been a real challenge. The puzzling question we need to answer when evaluating project's NCF is: how much is the price of a barrel during the life-span of the project? Accordingly, oil price modeling became a vital tool to predict both short-term and long-term prices. Unfortunately, there are many uncertainties associated with the available models and none of them can predict oil prices with acceptable accuracy. Only limited controlling parameters are captured by these models. These parameters are basic and derived from simple assumptions of supply and demand dependency. Nowadays, the need for a reliable oil price model became more critical as a change of oil price is experiencing dramatic fluctuations that affect economic decision parameters a great deal.This paper presents an oil-price model to project the price behavior in the next 20 years. Different scenarios were examined out of which "Economic-Scenario" was found to be the best suitable predictor. This model takes into account multiple effects of fourteen parameters that are believed to have the highest impacts on oil price. These factors have been further classified into key categories such as supply, demand, reserve and externalities (political/environmental/social) which is regionally based. Other parameters such as population growth and technology are embedded within these key factors. According to this model, oil price has been found to have strong reliance on the US Dollar and inflation, which has been incorporate into the model to ensure a more reliable outcome.Market behavior modeling is a continuous process which is planned to be integrated into the proposed model in the near future once consistent data become available. The major obstacle in modeling market behavior is the lack of futuristic behavior that is primarily dependent on accurate historical data. This data should reflect the performance of short-term effects such as lifestyle, human behavior, politics, conflicts, wars, natural disasters, environmental issues and other economies' behaviors. The ultimate goal of this modeling effort is to assist in economic and risk analysis evaluation of petroleum projects.