Neurologic disability level at hospital discharge is an important outcome in many clinical research studies. Outside of clinical trials, neurologic outcomes must typically be extracted by labor intensive manual review of clinical notes in the electronic health record (EHR). To overcome this challenge, we set out to develop a natural language processing (NLP) approach that automatically reads clinical notes to determine neurologic outcomes, to make it possible to conduct larger scale neurologic outcomes studies. We obtained 7314 notes from 3632 patients hospitalized at two large Boston hospitals between January 2012 and June 2020, including discharge summaries (3485), occupational therapy (1472) and physical therapy (2357) notes. Fourteen clinical experts reviewed notes to assign scores on the Glasgow Outcome Scale (GOS) with 4 classes, namely 'good recovery', 'moderate disability', 'severe disability', and 'death' and on the Modified Rankin Scale (mRS), with 7 classes, namely 'no symptoms', 'no significant disability', 'slight disability', 'moderate disability', 'moderately severe disability', 'severe disability', and 'death'. For 428 patients' notes, 2 experts scored the cases generating interrater reliability estimates for GOS and mRS. After preprocessing and extracting features from the notes, we trained a multiclass logistic regression model using LASSO regularization and 5-fold cross validation for hyperparameter tuning. The model performed well on the test set, achieving a micro average area under the receiver operating characteristic and F-score of 0.94 (95% CI 0.93-0.95) and 0.77 (0.75-0.80) for GOS, and 0.90 (0.89-0.91) and 0.59 (0.57-0.62) for mRS, respectively. Our work demonstrates that an NLP algorithm can accurately assign neurologic outcomes based on free text clinical notes. This algorithm increases the scale of research on neurological outcomes that is possible with EHR data.

In order to reduce the possibility of neural injury from seizures and sidestep the need for a neurologist to spend hours on manually reviewing the EEG recording, it is critical to automatically detect and classify "interictal-ictal continuum" (IIC) patterns from EEG data. However, the existing IIC classification techniques are shown to be not accurate and robust enough for clinical use because of the lack of high quality labels of EEG segments as training data. Obtaining high-quality labeled data is traditionally a manual process by trained clinicians that can be tedious, time-consuming, and error-prone. In this work, we propose Smile, an industrial scale system that provides an end-to-end solution to the IIC pattern classification problem. The core components of Smile include a visualization-based time series labeling module and a deep-learning based active learning module. The labeling module enables the users to explore and label 350 million EEG segments (30TB) at interactive speed. The multiple coordinated views allow the users to examine the EEG signals from both time domain and frequency domain simultaneously. The active learning module first trains a deep neural network that automatically extracts both the local features with respect to each segment itself and the long term dynamics of the EEG signals to classify IIC patterns. Then leveraging the output of the deep learning model, the EEG segments that can best improve the model are selected and prompted to clinicians to label. This process is iterated until the clinicians and the models show high degree of agreement. Our initial experimental results show that our Smile system allows the clinicians to label the EEG segments at will with a response time below 500 ms. The accuracy of the model is progressively improved as more and more high quality labels are acquired over time.

Dialogue Management (DM) is a key issue in Spoken Dialogue System. Most of the existing data-driven DM schemes train the dialogue policy for some specific domain (or vertical domain), only using the dialogue corpus in this domain, which might suffer from the scarcity of dialogue corpus in some domains. In this paper, we divide Dialogue Act (DA), as semantic representation of utterance, into DA type and slot parameter, where the former one is domain-independent and the latter one is domain-specific. Firstly, based on multiple-domain dialogue corpus, the DA type prediction model is trained via Recurrent Neutral Networks (RNN). Moreover, DA type decision problem is modeled as a multi-order POMDP, and transformed to be a one-order MDP with continuous states, which is solved by Natural Actor Critic (NAC) algorithm and applicable for every domain. Furthermore, a slot parameter selection scheme is designed to generate a complete machine DA according to the features of specific domain, which yields the Multi-domain Corpus based Dialogue Management (MCDM) scheme. Finally, extensive experimental results illustrate the performance improvement of the MCDM scheme, compared with the existing schemes.

In this study, the authors consider the application of a system architecture called cognitive radio (CR) with fibre‐connected distributed antennas in IEEE 802.22 wireless regional area networks (WRANs) as it could bring the benefits of much shorter wireless transmission distances, lower transmission power and the possibility of utilising multi‐antenna transmission techniques. In this architecture, the authors study the secondary user (SU) access problem in uplink, where the SU to primary user (PU) link estimation is subject to random errors because PU could not assist link estimation of SU. This SU access problem is divided into two parts: antenna selection and access control. Thus, first antenna selection problem is modelled as a restless bandit problem, which is solved by the primal‐dual index heuristic algorithm based on first order relaxation. In addition, the access control problem is modelled as a stochastic knapsack (SASK) problem with random weight, and then relaxed to be a deterministic second order cone programming problem. With the deduced upper bound, the access control problem is solved by the branch and bound algorithm, which yields the SU access based on SASK scheme. Simulation results illustrate the significant performance improvement of SASK scheme, compared with existing SU access methods.

In conventional WLANs, stations (STAs) select access points (APs) using the existing scheme based on the current quality of links. However, some novel improved architecture of WLANs is proposed with cognitive radio (CR) to negotiate spectrum usage, where the existing AP selection scheme might not be suitable for it. Thus in this paper, a new optimal AP Selection based on Restless Bandits (APSRB) scheme with the "indexability" property is proposed for WLANs with CR to maximize the throughput and to minimize the energy consumption. The AP selection problem is firstly established as a restless bandit problem, which is solved by the primal-dual index heuristic algorithm based on the first order relaxation with low complexity to yield APSRB scheme. Additionally, the APSRB scheme is divided into offline computation and online selection, where main work will be finished in former one so as to decrease the complexity further. Finally, extensive simulation results illustrate the significant performance improvement of the APSRB scheme compared to the existing one in different scenarios.

Large-scale multi-AP WMAPNs with a high density of users and access points (APs) have emerged widely in various hotspots, where inter-cell interference is detrimental to the performance of WLANs. In order to mitigate the interference, channel assignment scheme has been a major research topic in recent years. In this paper, based on Bianchi's throughput performance evaluation, we model a channel assignment problem for WLAN with Multiple APs (WLMAPN) not only to maximize the overall system throughput, but also to achieve the fairness among APs, where the inter-cell interference is measured in terms of the throughput reduction. In order to cope with this problem, channel assignment based on the Order of Throughput Reduction (CAOTR) scheme is proposed with low computation complexity, using local search. Finally, extensive simulation results illustrate that the proposed CAOTR scheme significantly enhances the overall throughput and guarantees the fairness of APs in density WMAPN systems.