Accurate classification of brain activity from electroencephalogram signals is essential for diagnosing neurological disorders such as epilepsy. In this paper, we propose an explainable deep learning method for epileptic seizure detection. The proposed approach converts electroencephalogram signals into audio waveforms, which are then transformed into time–frequency representations using two distinct continuous wavelet transforms, i.e., the Morlet and the Mexican Hat. These wavelet-based spectrograms effectively capture both temporal and spectral characteristics of the electroencephalogram signal data and serve as inputs to a set of convolutional neural network models with the aim to detect seizure activity. To improve model transparency, the proposed method integrates three class activation mapping techniques aimed to visualize the salient regions in the wavelet images that influence each prediction. Experimental evaluation on a real-world dataset emphasizes the efficacy of wavelet-based preprocessing in electroencephalogram signal analysis in prompt epileptic seizure detection, showing an accuracy equal to 0.922.
Smart meter networks are part of the critical infrastructure and therefore central to IT security consideration. Besides various forms of access control a permanent monitoring of the network traffic is of utmost importance to the detection of malicious activities taking place. Such monitoring must happen in real time and should possibly be implementable everywhere in the network. These requirements do not allow for the decryption of the network traffic. The paper describes a method by which network packets can be assigned to use cases common in smart meter infrastructures without the need for decryption. It is based solely on metadata and reliably can establish the relationship between a network packet and a use case. The information calculated with this method can be used to detect packets that are not pertaining to any of the allowed use cases and hence are highly suspicious. Moreover, the execution of use cases not initiated by the central server become evident, too, and should raise corresponding alerts. The method was implemented as a proof-of-concept and tested in the real-world environment of a medium-sized city.
It is commonly understood that the resilience of critical information technology (IT) systems based on artificial intelligence (AI) must be ensured. In this regard, we consider resilience both in terms of IT security threats, such as cyberattacks, as well as the ability to robustly persist under uncertain and changing environmental conditions, such as climate change or economic crises. This paper explores the relationship between resilience and sustainability with regard to AI systems, develops fields of action for resilient AI, and elaborates direct and indirect influences on the achievement of the United Nations Sustainable Development Goals. Indirect in this case means that a sustainability effect is reached by taking resilience measures when applying AI in a sustainability-relevant application area, for example precision agriculture or smart health.