Real-Time Maritime Traffic Anomaly Detection Based on Sensors and History Data Embedding.

The automated identification system of vessel movements receives a huge amount of multivariate, heterogeneous sensor data, which should be analyzed to make a proper and timely decision on vessel movements. The large number of vessels makes it difficult and time-consuming to detect abnormalities, thus rapid response algorithms should be developed for a decision support system to identify abnormal movements of vessels in areas of heavy traffic. This paper extends the previous study on a self-organizing map application for processing of sensor stream data received by the maritime automated identification system. The more data about the vessel's movement is registered and submitted to the algorithm, the higher the accuracy of the algorithm should be. However, the task cannot be guaranteed without using an effective retraining strategy with respect to precision and data processing time. In addition, retraining ensures the integration of the latest vessel movement data, which reflects the actual conditions and context. With a view to maintaining the quality of the results of the algorithm, data batching strategies for the neural network retraining to detect anomalies in streaming maritime traffic data were investigated. The effectiveness of strategies in terms of modeling precision and the data processing time were estimated on real sensor data. The obtained results show that the neural network retraining time can be shortened by half while the sensitivity and precision only change slightly.

Cabozantinib in progressive medullary thyroid cancer.

PURPOSE: Cabozantinib, a tyrosine kinase inhibitor (TKI) of hepatocyte growth factor receptor (MET), vascular endothelial growth factor receptor 2, and rearranged during transfection (RET), demonstrated clinical activity in patients with medullary thyroid cancer (MTC) in phase I. PATIENTS AND METHODS: We conducted a double-blind, phase III trial comparing cabozantinib with placebo in 330 patients with documented radiographic progression of metastatic MTC. Patients were randomly assigned (2:1) to cabozantinib (140 mg per day) or placebo. The primary end point was progression-free survival (PFS). Additional outcome measures included tumor response rate, overall survival, and safety. RESULTS: The estimated median PFS was 11.2 months for cabozantinib versus 4.0 months for placebo (hazard ratio, 0.28; 95% CI, 0.19 to 0.40; P < .001). Prolonged PFS with cabozantinib was observed across all subgroups including by age, prior TKI treatment, and RET mutation status (hereditary or sporadic). Response rate was 28% for cabozantinib and 0% for placebo; responses were seen regardless of RET mutation status. Kaplan-Meier estimates of patients alive and progression-free at 1 year are 47.3% for cabozantinib and 7.2% for placebo. Common cabozantinib-associated adverse events included diarrhea, palmar-plantar erythrodysesthesia, decreased weight and appetite, nausea, and fatigue and resulted in dose reductions in 79% and holds in 65% of patients. Adverse events led to treatment discontinuation in 16% of cabozantinib-treated patients and in 8% of placebo-treated patients. CONCLUSION: Cabozantinib (140 mg per day) achieved a statistically significant improvement of PFS in patients with progressive metastatic MTC and represents an important new treatment option for patients with this rare disease. This dose of cabozantinib was associated with significant but manageable toxicity.