No abstract

Biscuits are staple bakery foods that are popular worldwide due to their ready-to-eat nature, affordable cost, and prolonged shelflife (Arepally et al., 2020). However, they typically contain a high amount of sugar and fat and produce high calorie but low fiber content. Dietary fiber has received great public attention as it brings numerous health benefits associated with an increased intake of dietary fiber, including the potential to reduce the risk of diabetes, obesity, intestinal diseases, and some types of cancer (He et al., 2022). The use of fiber-rich ingredients in the formulation of food products has been an actual trend in marketing strategy to attract consumers (Soleimanian et al., 2021). Indeed, dietary fiber has been regulated for health and nutrient-related claims in food products labeling by many international markets (Domínguez Díaz et al., 2020). A ratio of approximately 3:1 of IDF:SDF is recommended for a well-balanced proportion to enhance the benefit of physiological effects of both the fiber fractions (Jha et al., 2017). In this context, biscuits and other food products have been fortified with different materials to improve their dietary fiber and nutrient

Revolutionizing operation model of traditional network in programmability, scalability, and orchestration, Software-Defined Networking (SDN) has considered as a novel network management approach for a massive network with heterogeneous devices. However, it is also highly susceptible to security attacks like conventional network. Inspired from the success of different machine learning algorithms in other domains, many intrusion detection systems (IDS) are presented to identify attacks aiming to harm the network. In this paper, leveraging the flow-based nature of SDN, we introduce DeepFlowIDS, a deep learning (DL)-based approach for anomaly detection using the flow analysis method in SDN. Furthermore, instead of using a lot of network properties, we only utilize essential characteristics of traffic flows to analyze with deep neural networks in IDS. This is to reduce the computational and time cost of attack traffic detection. Besides, we also study the practical benefits of applying deep transfer learning from computer vision to intrusion detection. This method can inherit the knowledge of an effective DL model from other contexts to resolve another task in cybersecurity. Our DL-based IDSs are built and trained with the NSL-KDD and CICIDS2018 dataset in both fine-tuning and feature extractor strategy of transfer learning. Then, it is integrated with the SDN controller to analyze traffic flows retrieved from OpenFlow statistics to recognize the anomaly action in the network.

No abstract