Aiming to improve the navigation accuracy during global navigation satellite system (GNSS) outages, an algorithm based on long short-term memory (LSTM) is proposed for aiding inertial navigation system (INS). The LSTM algorithm is investigated to generate the pseudo GNSS position increment substituting the GNSS signal. Almost all existing INS aiding algorithms, like the multilayer perceptron neural network (MLP), are based on modeling INS errors and INS outputs ignoring the dependence of the past vehicle dynamic information resulting in poor navigation accuracy. Whereas LSTM is a kind of dynamic neural network constructing a relationship among the present and past information. Therefore, the LSTM algorithm is adopted to attain a more stable and reliable navigation solution during a period of GNSS outages. A set of actual vehicle data was used to verify the navigation accuracy of the proposed algorithm. During 180 s GNSS outages, the test results represent that the LSTM algorithm can enhance the navigation accuracy 95% compared with pure INS algorithm, and 50% of the MLP algorithm.

BackgroundNicardipine (NC) is the most commonly used antihypertensive drug in neurological patients with hypertension. Although nimodipine (NM) is widely used to treat cerebral vasospasm in patients with aneurysmal subarachnoid hemorrhage, trials exploring its antihypertensive effect after intravenous administration in subjects with intracerebral hemorrhage (ICH) are scarce.MethodsA retrospective study was carried out to compare the safety and efficacy of NC and NM administered intravenously in patients with ICH. Therapeutic responses were assessed by achievement of goal blood pressure (BP); use of additional medications for BP control; proportion of time spent within goal; variability in BP; time to goal BP; number of dose adjustments; variability in ICH volume, Glasgow Coma Scale score, and intracranial pressure; and drug-related complications.ResultsA total of 87 patients were eligible for analysis (n=46 [NC]; n=41 [NM]), and baseline characteristics between groups were similar. Both agents were effective in achieving goal BP during infusion, with 93.5% and 87.8% patients in the NC and NM groups achieving goal, respectively. Fewer additional medications were needed to control BP in the NC group. BP variability was similar and no differences were observed in the mean time to goal BP and mean numbers of dose adjustments between both groups. Interestingly, intracranial pressure declined (P=0.048) during NC administration but increased (P=0.066) after NM treatment. Finally, the incidences of hematoma expansion, neurological deterioration, and adverse drug events were similar in both groups.ConclusionNM is effective and safe for BP control in patients with ICH.

No abstract

No abstract

No abstract