Currently, expert systems and applied machine learning algorithms are widely used to automate network intrusion detection. In critical infrastructure applications of communication technologies, the interaction among various industrial control systems and the Internet environment intrinsic to the IoT technology makes them susceptible to cyber-attacks. Given the existence of the enormous network traffic in critical Cyber-Physical Systems (CPSs), traditional methods of machine learning implemented in network anomaly detection are inefficient. Therefore, recently developed machine learning techniques, with the emphasis on deep learning, are finding their successful implementations in the detection and classification of anomalies at both the network and host levels. This paper presents an ensemble method that leverages deep models such as the Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) and a meta-classifier (i.e., logistic regression) following the principle of stacked generalization. To enhance the capabilities of the proposed approach, the method utilizes a two-step process for the apprehension of network anomalies. In the first stage, data pre-processing, a Deep Sparse AutoEncoder (DSAE) is employed for the feature engineering problem. In the second phase, a stacking ensemble learning approach is utilized for classification. The efficiency of the method disclosed in this work is tested on heterogeneous datasets, including data gathered in the IoT environment, namely IoT-23, LITNET-2020, and NetML-2020. The results of the evaluation of the proposed approach are discussed. Statistical significance is tested and compared to the state-of-the-art approaches in network anomaly detection.

Anticipating human intentional actions is essential for many applications involving service robots and social robots. Nowadays assisting robots must do reasoning beyond the present with predicting future actions. It is difficult due to its non-Markovian property and the rich contextual information. This task requires the subtle details inherent in human movements that may imply a future action. This paper presents a probabilistic method for action prediction in human-object interactions.The key idea of our approach is the description of the so-called object affordance, the concept which allows us to deliver a trajectory visualizing a possible future action. Extensive experiments were conducted to show the effectiveness of our method in action prediction. For evaluation we applied a new RGB-D activity video dataset recorded by the Sez3D depth sensors. The dataset contains several human activities composed out of different actions.

The goal of this work is to forecast human activities that may require robot assistance. Each activity consists of consecutive actions. Each action is bounded by initial and final state and is created by the motion trajectory. The states are defined in the training phase. The vision and depth sensors are used for data collection. The data are processed and the structured database is built. This base is used for making prediction. The method allows us to forecast the trajectories of nominally possible motion goals (prognosing of an action). The probability functions support the selection of possible motion goal. Then the possible motion trajectory is created which predicts the ongoing action. The activity is predicted on the basis of already completed action sequences and using knowledge about possible sequences stored in the database. The core of the reasoning process are: the probability functions, the action graphs (describing the activities) and the structured database. The approach was evaluated using four datasets: CAD 60, CAD-120, WUT-17, and WUT-18. The efficiency of the presented solution compared to the other existing state-of-the-art methods is also investigated.

No abstract