Electroencephalogram (EEG) contains important physiological information that can reflect the activity of human brain, making it useful for epileptic seizure detection and epilepsy diagnosis. However visual inspection of large amounts of EEG by human expert is time-consuming, and meanwhile there are often inconsistences in judgement between physicians. In this paper, we develop a unified framework for early epileptic seizure detection and epilepsy diagnosis, which includes two phases. In the first phase, the signal intensity is first calculated for each data point of the given EEG, enabling the well-known autoregressive moving average (ARMA) model to characterize the dynamic behavior of the EEG time series. The residual error between the predicted value of learned ARMA model and the actually observed value is used as the anomaly score to support a null hypothesis testing for making epileptic seizure decision. The epileptic seizure detection phase can provide a quick detection for anomaly EEG patterns, but the resulting suspicious segment may include epilepsy or other disordering EEG activities thus required to be identified. Therefore, in the second phase, we use pattern recognition technique to classify the suspicious EEG segments. In particular, we propose a new and practical classifier based on a pairwise of one-class SVMs for epilepsy diagnosis. The proposed classifier requires normal and epilepsy data for training, but can recognize normal, epilepsy and even other disorders that would not be trained in the training samples. This point is practical and meaningful in real clinic scenarios as the input EEG may include other brain disordering diseases besides of epilepsy. We conducted experiments on the publicly-available Bern-Barcelona and CHB-MIT EEG database, respectively, to validate the effectiveness of the proposed framework, and our method achieved classification accuracy of 93% and 94% on them. Comprehensive experimental results, outperforming the state-of-the-arts, suggest its great potentials in real applications.

With data increasingly collected by end devices and the number of devices is growing rapidly in which data source mainly located outside the cloud today. To guarantee data privacy and remain data on client devices, federated learning (FL) has been proposed. In FL, end devices train a local model with their data and send the model parameters rather than raw data to server for aggregating a new global model. However, due to the limited wireless bandwidth and energy of mobile devices, it is not practical for FL to perform model updating and aggregation on all participating devices in parallel. And it is difficulty for FL server to select apposite clients to take part in model training which is important to save energy and reduce latency. In this paper, we establish a novel mobile edge computing (MEC) system for FL and propose an experience-driven control algorithm that adaptively chooses client devices to participate in each round of FL. Adaptive client selection mechanism in MEC can be modeled as a Markov Decision Process in which we do not need any prior knowledge of the environment. We then propose a client selection scheme based on reinforcement learning that learns to select a subset of devices in each communication round to minimize energy consumption and training delay that encourages the increase number of client devices to participate in model updating. The experimental results show that the unit of energy required in FL can be reduced by up to 50% and training delay required can be reduced by up to 20.70% compared to the other static algorithms. Finally, we demonstrate the scalability of MEC system with different tasks and the influence of different non independent and identically distributed (non-IID) settings.INDEX TERMS Client selection, federated learning, mobile edge computing, reinforcement learning.

In recent years, automatic change detection for real-time monitoring of electroencephalogram (EEG) signals has attracted widespread interest with a large number of clinical applications. However, it is still a challenging problem. This paper presents a novel framework for this task where joint time-domain features are firstly computed to extract temporal fluctuations of a given EEG data stream; and then, an auto-regressive (AR) linear model is adopted to model the data and temporal anomalies are subsequently calculated from that model to reflect the possibilities that a change occurs; a non-parametric statistical test based on Randomized Power Martingale (RPM) is last performed for making change decision from the resulting anomaly scores. We conducted experiments on the publicly-available Bern-Barcelona EEG database where promising results for terms of detection precision (96.97%), detection recall (97.66%) as well as computational efficiency have been achieved. Meanwhile, we also evaluated the proposed method for real detection of seizures occurrence for a monitoring epilepsy patient. The results of experiments by using both the testing database and real application demonstrated the effectiveness and feasibility of the method for the purpose of change detection in EEG signals. The proposed framework has two additional properties: (1) it uses a pre-defined AR model for modeling of the past observed data so that it can be operated in an unsupervised manner, and (2) it uses an adjustable threshold to achieve a scalable decision making so that a coarse-to-fine detection strategy can be developed for quick detection or further analysis purposes.

No abstract