In this paper, we propose a unified deep learning model for monitoring elderly in execution of daily life activities such as eating, sleeping or taking medication. The proposed approach consists of three stages which are activity recognition, anomaly detection and next activity prediction. Such a system can provide useful information for the elderly, caregivers and medical teams to identify activities and generate preventive and corrective measures. In literature, these stages are discussed separately, however, in our approach, we make use of each stage to progress into the next stage. At first, activity recognition based on different extracted features is performed using a deep neural network (DNN), then an overcomplete-deep autoencoder (OCD-AE) is employed to separate the normal from anomalous activities. Finally, a cleaned sequence of consecutive activities is constructed and used by a long short-term memory (LSTM) algorithm to predict the next activity. Since the last two stages depend on the activity recognition stage, we propose to increase its accuracy by exploiting different extracted features. The performance of the proposed unified approach has been evaluated on real smart home datasets to demonstrate its ability to recognize activities, detect anomalies and predict the next activity.

The intrusion detection system (IDS) is a promising technology for ensuring security against cyber-attacks in internet-of-things networks. In conventional IDS, anomaly detection and feature extraction are performed by two different models. In this paper, we propose a new integrated model based on deep autoencoder (AE) for anomaly detection and feature extraction. Firstly, AE is trained based on normal network traffic and used later to detect anomalies. Then, the trained AE model is employed again to extract useful low-dimensional features for anomalous data without the need for a feature extraction training stage, which is required by other methods such as principal components analysis (PCA) and linear discriminant analysis (LDA). After that, the extracted features are used by a machine learning (ML) or deep learning (DL) classifier to determine the type of attack (multi-classification). The performance of the proposed unified approach was evaluated on real IoT datasets called N-BaIoT and MQTTset, which contain normal and malicious network traffics. The proposed AE was compared with other popular anomaly detection techniques such as one-class support vector machine (OC-SVM) and isolation forest (iForest), in terms of performance metrics (accuracy, precision, recall, and F1-score), and execution time. AE was found to identify attacks better than OC-SVM and iForest with fast detection time. The proposed feature extraction method aims to reduce the computation complexity while maintaining the performance metrics of the multi-classifier models as much as possible compared to their counterparts. We tested the model with different ML/DL classifiers such as decision tree, random forest, deep neural network (DNN), conventional neural network (CNN), and hybrid CNN with long short-term memory (LSTM). The experiment results showed the capability of the proposed model to simultaneously detect anomalous events and reduce the dimensionality of the data.

In this article, we propose an iterative soft decision feedback (ISDF) equalizer to compensate for the chromatic dispersion and nonlinear phase noise effects in 30-Gbaud coherent optical filter bank multicarrier with off-set quadrature amplitude modulation (FBMC/OQAM) system. Conventional optical FBMC/OQAM system usually uses a 1-tap zero-forcing equalizer per subcarrier to combat the inter-symbol interference (ISI) caused by the chromatic dispersion (CD) in optical fiber. However, residual ISI and inter-carrier interference (ICI) still remain in the system and have significant impact on the system performance. To overcome this problem, a new ISDF N-tap frequency sampling (FS) equalizer is proposed to jointly mitigate the residual ISI and ICI which permits a better trade-off between performance and complexity. Simulation results show that, the proposed technique is capable of suppressing the interference more effectively than using only 1-tap equalizer. The feedback branch of the proposed ISDF equalizer can be exploited further to compensate for the nonlinear effect of the optical fiber. With compensation of linear and nonlinear impairments the proposed technique acts as a backpropagation method for optical FBMC/OQAM system.

Continuous variable quantum key distribution (CV-QKD) using a local-local oscillator (LLO) is recently proposed to overcome security issues in conventional CV-QKD systems. However, Eve can manipulate the phase or amplitude of the phase reference pulse (PRP) transmitted over the insecure quantum channel, which has opened the door to new security issues. Maintaining optimal performance and preventing Eve’s activities on the quantum channel depends on such a choice of modulation technique. In this paper, the performance of CV-QKD employing LLO over the free space optical (FSO) channel under weak turbulence conditions is investigated. Channel transmittance is introduced into the system model according to the log-negative Weibull distribution. We have adopted the trusted noise model and included the channel phase distortion in the excess noise calculations. We have also evaluated the secret key rate (SKR) using Gaussian modulation (GM) and discrete modulation (DM) protocols. We have reported the superiority of GM in achieving the highest SKR over long distances with the optimum choice of the modulation variance under Eve’s attack on the PRP. Moreover, we analyzed phase and amplitude attacks on the PRP and showed that phase attacks are more severe and deteriorate the communication link more rapidly than amplitude attacks.

Continuous-variable quantum key distribution (CV-QKD) with a real local oscillator (LO) experiences a phase attack security challenge due to the reference pulses transmitted along with quantum signals over an unsecure quantum channel. In this paper, a phase attack on reference pulses of CV-QKD with a real LO is investigated. The performance of the discrete-modulated (DM) CV-QKD under this attack is analyzed analytically and by simulation, and compared with the Gaussian-modulated (GM) CV-QKD. It is found that such an attack by an eavesdropper's, significantly reduce the transmission distance for the GM based CV-QKD, whereas, the DM based CV-QKD shows a high tolerance to high phase noise. Based on phase attack monitoring, a new adaptive modulation scheme is proposed for CV-QKD to adaptively switch between GM and DM so as to maintain the optimum secret key rate.