Search

In a network architecture, an intrusion detection system (IDS) is one of the most commonly used approaches to secure the integrity and availability of critical assets in protected systems. Many existing network intrusion detection systems (NIDS) utilize stand-alone classifier models to classify network traffic as an attack or as normal. Due to the vast data volume, these stand-alone models struggle to reach higher intrusion detection rates with low false alarm rates( FAR). Additionally, irrelevant features in datasets can also increase the running time required to develop a model. However, data can be reduced effectively to an optimal feature set without information loss by employing a dimensionality reduction method, which a classification model then uses for accurate predictions of the various network intrusions. In this study, we propose a novel feature-driven intrusion detection system, namely χ2-BidLSTM, that integrates a χ2 statistical model and bidirectional long short-term memory (BidLSTM). The NSL-KDD dataset is used to train and evaluate the proposed approach. In the first phase, the χ2-BidLSTM system uses a χ2 model to rank all the features, then searches an optimal subset using a forward best search algorithm. In next phase, the optimal set is fed to the BidLSTM model for classification purposes. The experimental results indicate that our proposed χ2-BidLSTM approach achieves a detection accuracy of 95.62% and an F-score of 95.65%, with a low FAR of 2.11% on NSL-KDDTest + . Furthermore, our model obtains an accuracy of 89.55%, an F-score of 89.77%, and an FAR of 2.71% on NSL-KDDTest -21 , indicating the superiority of the proposed approach over the standard LSTM method and other existing feature-selection-based NIDS methods.

The internet of things (IoT) and deep learning are emerging technologies in diverse research fields, including the provision of IT services in medical domains. In the COVID-19 era, intelligent medication behavior monitoring systems for stable patient monitoring are further required, because many patients cannot easily visit hospitals. Several previous studies made use of wearable devices to detect medication behaviors of patients. However, the wearable devices cause inconvenience while equipping the devices. In addition, they suffer from inconsistency problems due to errors of measured values. We devise a medication behavior monitoring system that uses the IoT and deep learning to avoid sensing errors and improve user experiences by effectively detecting various activities of patients. Based on the real-time operation of our proposed IoT device, the proposed solution processes captured images of patents via OpenPose to check medication situations. The proposed system identifies medication status on time by using a human activity recognition scheme and provides various notifications to patients' mobile devices. To support reliable communication between our system and doctors, we employ MQTT protocol with periodic data transmissions. Thus, the measured information of patient's medication status is transmitted to the doctors so that they can periodically perform remote treatments. Experimental results show that all medication behaviors are accurately detected and notified to the doctor efficiently, improving the accuracy of monitoring the patient's medication behavior.