Tunnel section is the throat of transportation and attracts lots of attentions. This paper proposed a method to evaluate the driver's visual search stability based on the Markov Chain properties of eye movements. Firstly, visual and physiological data about 16 participants driving through 13 urban tunnels were collected. Then, the view area was divided into six AOIs (Area of Interest) by fast clustering of the drivers' fixation points. The one-step fixation transition probability and the stable distribution of different lane changing behavior were obtained based on the division of the view area. The probability of transition from the forward windscreen to the left rearview mirror and other 6 visual parameters were selected as indexes by correlation tests. And the first four principal components which covered 96.1% of all information were extracted. Then an evaluation method for visual search stability was implemented by principal component analysis. In order to validate the method, average lane change times, average speed and SDNN (Standard Deviation of NN Intervals) of the drivers' heart rate were clustered into two categories. According to the consistency between the evaluation results and the clustering results, the evaluation method proposed in this paper has been proven to be reliable. Finally, the score threshold for judging the driver's stability was obtained as E = 0.313. The method could be applied to adjustment of tunnel facilities, assistance in driving training and development of auto driving system by assessing whether a driver can take over the control of the vehicle or not.
The knowledge of preference drift is important to maintain the user’s preference accurate. With the swift development of mobile service the recognition of such knowledge has attracted immense attention in recent times. However, existing research based on clustering is inadequate for the description of item objects with weak N-ary associations. This paper, through the analysis of contextual recommendation, proposes a “hypergraph model” for contextual items. Furthermore, similarities between pair of items, item clusters and the degree of user preference drift are defined. Based on above definitions, a method to discover user preference drift is proposed. In addition two experiments are being carried out to validate its significance.
An increasing web services run in mobile context. Context may influence customer potential needs and buying behaviors in some specific situation. However existent customer segmentation method do not attach importance to context factors, which weakly support the development of context-sensitive mobile service . Therefore a mobile customer segmentation method based on context is proposed and validated by a case. The further research is mentioned in the end of the paper.
Objective: To investigate the clinicopathological characteristics and CT manifestations of gastric neuroendocrine tumors using an optimized DCT filtering algorithm. Methods: An optimized DCT filtering algorithm was used to retrospectively analyze the CT image data and clinical pathological data of 31 patients with gastric neuroendocrine tumors. Results: Of the 31 patients, 23 were male and 8 were female, with a median age of 63 years. There were 4 cases of clinical type I, the lesions were located on the major curve side in 3 cases, and the minor curve side in 1 case; 3 cases had CT with polypoid moderately enhanced nodules, and 1 case was missed; pathological grades were all G1 grade; the maximum diameter of the lesion was 1.7∼6.3 cm, average 1.1 cm. There were 2 cases of clinical type II, 1 case was polypoid on the gastric fundus, grade G1; 1 case was on the gastric antrum, CT showed mild gastric wall thickening, grade G2, with liver metastasis. There were 25 cases of clinical type III, 14 cases of cardia gastric fundus, 4 cases of small curvature of the gastric body, 3 cases of large curvature of the gastric body, and 4 cases of gastric antrum; CT signs showed localized thickening of the gastric wall and 3 cases of gastric wall focal 15 cases were irregularly thickened gastric wall with or without soft tissue masses, 6 of which had ulcers on the surface; the largest diameter of the lesions was 1.7 to 6.3 cm with an average of 4.5 cm; the density of the lesions was 11 and 14 were uneven; The enhanced scan showed significant enhancement in 16 cases, moderate enhancement in 9 cases, uniform enhancement in 8 cases, and uneven enhancement in 17 cases, of which the enhancement peak was located in the arterial phase; 25 cases were all grade G3, 10 were local lymph node metastases, and 4 were liver metastases. There were 4 cases of liver metastasis with local lymph node metastasis, and 1 case of intraperitoneal implantation with local lymph node metastasis. Conclusion: The optimized DCT filtering algorithm can enumerate the CT features of gastric neuroendocrine tumors with different clinical and pathological types. The combination of clinical and CT data is valuable for preoperative diagnosis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.