Seizure detection and type classification from electroencephalogram (EEG) has the potential to improve the diagnosis and treatment of epilepsy. Although the task of seizure detection has been well-investigated, seizure type classification remains largely unexplored. The intricate nature of seizure dynamics presents a significant challenge in effectively extracting distinguishing features from noisy and high-dimensional EEG signals. Previous studies mainly focus on extracting features from temporal, spectral or special domain. Extracting temporal-spatial-spectral features simultaneously from EEG remains challenging. In this paper, we introduce an attention-based neural network to effectively extract temporal-spatial-spectral EEG features, for seizure type classification. It utilizes an attention module with one-shot aggregation to extract multi-level temporal-spatial-spectral EEG features, aiming to differentiate the complex patterns of various seizure types. Specifically, we construct the 3-dimensional representation of EEG by stacking the time-frequency matrices obtained from short time Fourier transform. The attention module consists of paralleled temporal and spatial-spectral attention blocks, allowing the model to focus on the most distinctive time stamps, sensor locations, and frequency bands. The proposed approach is validated on the largest public seizure EEG database, TUSZ v1.5.2. Five-fold cross validation demonstrates that our framework achieved 0.951 weighted F1 score on seizure type classification, achieving state-of-the-art performance. Ablation study confirmed the effectiveness of the temporal and spatial-spectral attention blocks.

The current wireless communication network is a content-careless network, in which every request needs a new transmission, even those requests imply the same content. However, the Long-Tail distribution of users' interests caused by the converging behavior, determines that the redundant traffic, which is the re-transmission bearing same content, is rather enormous. Therefore the content-careless scheme of network transmission introduces large energy waste. In our previous work, we put forward a novel transmission scheme CASoRT to mitigate such energy waste by broadcasting those hot contents. After the contents are broadcast, the terminals in coverage could cache those contents in local memory and load those contents when request. Thus, the massive redundant transmission of the very content is relieved by one broadcast transmission. In order to exploit the advantage of broadcast, the proper recommender scheme, deciding which contents should be broadcast, needs to be optimized. In this paper, we present certain perspective in analyzing the log of campus network in Tsinghua University. It shows that utilizing users converging character could improve the efficiency of CASoRT with analysis. Finally, location based content recommendation scheme is proposed, verified by simulation.

In this paper, we present a duo-graph Simultaneous Localization and Mapping (SLAM) method that enables visual-guided robot to efficiently and robustly generate consistent 3D map in a large-scale environment. Recently the conditional independent graph (CI-GRAPH) has been proved to be an efficient and robust method for solving the large-scale SLAM problem. However, it stems from extended kalman filter (EKF) SLAM that suffers from high computational load when number of the landmarks becomes large. Moreover, the big noise in the measurement can lead EKF SLAM far from convergence. These disadvantages are the cases in the visual-guided robot. To solve these problems, we propose a duo-graph structure that sustains the feasibility of a hierarchical graph-based SLAM framework. It implements two level graph-based SLAM: local and global SLAM. Utilizing the characteristic of the duo-graph structure, the local SLAM can efficiently localize itself while the global SLAM can accurately close loops in the large scale environment. In addition, our method can filter massive noisy visual features and eliminate mismatches in the global SLAM process. To demonstrate the superiority of our method, both simulation and real experiments are carried out.

In this paper, we present experimental studies on Multi-channel Multi-radio Multi-hop (M3) wireless networks. The interference of multiple channels and multiple radios is studied. The result may help to understand effect of multi-channel and multi-radio in real system and is useful as reference for network performance optimization. We evaluate the coexistence of real-time traffic and best-effort traffic in multi-hop wireless networks. Our experiments show that coordination among wireless nodes is critical for optimal network performance, especially in the scenarios with quality of service (QoS) requirements. To perform the experiments, an M3 testbed with 32 nodes is built. The testbed is based on Windows operating system and provides convenient programming interface and management tools. The architecture and key modules of the testbed design are described.