With the increasing deployment of wireless sensordevices and networks,security becomes a criticalchallenge for sensor networks.In this paper,a schemeusing data mining is proposed for routing anomalydetection in wirele...With the increasing deployment of wireless sensordevices and networks,security becomes a criticalchallenge for sensor networks.In this paper,a schemeusing data mining is proposed for routing anomalydetection in wireless sensor networks.The schemeuses the Apriori algorithm to extract traffic patternsfrom both routing table and network traffic packetsand subsequently the K-means cluster algorithmadaptively generates a detection model.Through thecombination of these two algorithms,routing attackscan be detected effectively and automatically.Themain advantage of the proposed approach is that it isable to detect new attacks that have not previouslybeen seen.Moreover,the proposed detection schemeis based on no priori knowledge and then can beapplied to a wide range of different sensor networksfor a variety of routing attacks.展开更多
Through analyzing the failure mechanics of rock under blasting effect, the optical fiber sensing system was used to monitor the strain of surrounding rock under blasting effect. Combined with practical exploration, th...Through analyzing the failure mechanics of rock under blasting effect, the optical fiber sensing system was used to monitor the strain of surrounding rock under blasting effect. Combined with practical exploration, the stability of surrounding rock was computed by numerical simulation using the blasting wave obtained from the site. According to the change regularities of displacement, stress, acceleration, and velocity of tunnels before and after explosion, the layout of key monitoring points was optimized. When disposed the monitoring position of sensors, the regular points should be considered to use as key points and the periodical monitor should be a part of the long-term monitor. In practical application, considering the geology condition in site, monitor points should be added on the area with joints and faults to assure the integrity of monitor data and the preciseness of decision.展开更多
In Wireless Sensors Networks, the computational power and storage capacity is limited. Wireless Sensor Networks are operated in low power batteries, mostly not rechargeable. The amount of data processed is incremental...In Wireless Sensors Networks, the computational power and storage capacity is limited. Wireless Sensor Networks are operated in low power batteries, mostly not rechargeable. The amount of data processed is incremental in nature, due to deployment of various applications in Wireless Sensor Networks, thereby leading to high power consumption in the network. For effectively processing the data and reducing the power consumption the discrimination of noisy, redundant and outlier data has to be performed. In this paper we focus on data discrimination done at node and cluster level employing Data Mining Techniques. We propose an algorithm to collect data values both at node and cluster level and finding the principal component using PCA techniques and removing outliers resulting in error free data. Finally a comparison is made with the Statistical and Bucket-width outlier detection algorithm where the efficiency is improved to an extent.展开更多
基金the supports of the National Natural Science Foundation of China (60403027) the projects of science and research plan of Hubei provincial department of education (2003A011)the Natural Science Foundation Of Hubei Province of China (2005ABA243).
文摘With the increasing deployment of wireless sensordevices and networks,security becomes a criticalchallenge for sensor networks.In this paper,a schemeusing data mining is proposed for routing anomalydetection in wireless sensor networks.The schemeuses the Apriori algorithm to extract traffic patternsfrom both routing table and network traffic packetsand subsequently the K-means cluster algorithmadaptively generates a detection model.Through thecombination of these two algorithms,routing attackscan be detected effectively and automatically.Themain advantage of the proposed approach is that it isable to detect new attacks that have not previouslybeen seen.Moreover,the proposed detection schemeis based on no priori knowledge and then can beapplied to a wide range of different sensor networksfor a variety of routing attacks.
文摘Through analyzing the failure mechanics of rock under blasting effect, the optical fiber sensing system was used to monitor the strain of surrounding rock under blasting effect. Combined with practical exploration, the stability of surrounding rock was computed by numerical simulation using the blasting wave obtained from the site. According to the change regularities of displacement, stress, acceleration, and velocity of tunnels before and after explosion, the layout of key monitoring points was optimized. When disposed the monitoring position of sensors, the regular points should be considered to use as key points and the periodical monitor should be a part of the long-term monitor. In practical application, considering the geology condition in site, monitor points should be added on the area with joints and faults to assure the integrity of monitor data and the preciseness of decision.
文摘In Wireless Sensors Networks, the computational power and storage capacity is limited. Wireless Sensor Networks are operated in low power batteries, mostly not rechargeable. The amount of data processed is incremental in nature, due to deployment of various applications in Wireless Sensor Networks, thereby leading to high power consumption in the network. For effectively processing the data and reducing the power consumption the discrimination of noisy, redundant and outlier data has to be performed. In this paper we focus on data discrimination done at node and cluster level employing Data Mining Techniques. We propose an algorithm to collect data values both at node and cluster level and finding the principal component using PCA techniques and removing outliers resulting in error free data. Finally a comparison is made with the Statistical and Bucket-width outlier detection algorithm where the efficiency is improved to an extent.
