Search

Background and Aims Allometric scaling between stomata and xylem for terrestrial woody plants is a widely observed pattern that may be constrained by water transport. Floating-leaved plants, a particular life form of aquatic plants, have leaves in direct contact with both air and water and a poorly developed xylem that may not be limited by water supply as for terrestrial plants. However, whether such an allometric scaling relationship still exists in floating-leaved plants has not been explored. Methods We analysed 31 floating-leaved species/varieties with a range in leaf area covering six orders of magnitude. For all 31 floating-leaved plants, we studied the allometric relationships between leaf area and petiole transverse area, and between total stomatal area and petiole vascular area. Key Results The slopes of both relationships were similar to the slope of the allometric relationship (1.23) between total stomatal area and xylem area of 53 terrestrial plants. However, for ten of them with xylem that can be clearly defined, the strong positive relationship between total stomatal area and petiole xylem area had a significantly smaller slope than that of terrestrial plants (0.64 vs. 1.23). Furthermore, after considering phylogeny, the scaling relationships between total stomatal area and petiole traits in floating-leaved plants remained significant. Conclusions We speculated that for floating-leaved plants, the hyperallometric relationship (slope >1) between the construction of leaf/stoma and petiole was promoted by the high demand for photosynthesis and thus more leaves/stomata. While the hypoallometric relationship (slope <1) between stomatal and xylem area was related more to hydraulic processes, the selection pressure on stomata was lower than xylem of floating-leaved plants. Allometric relationships among the hydraulic traits on water transport of aquatic plants are the result of natural selection to achieve max, Background and Aims Allometric scaling between stomata and xylem for terrestrial woody plants is a widely observed pattern that may be constrained by water transport. Floating-leaved plants, a particular life form of aquatic plants, have leaves in direct contact with both air and water and a poorly developed xylem that may not be limited by water supply as for terrestrial plants. However, whether such an allometric scaling relationship still exists in floating-leaved plants has not been explored. Methods We analysed 31 floating-leaved species/varieties with a range in leaf area covering six orders of magnitude. For all 31 floating-leaved plants, we studied the allometric relationships between leaf area and petiole transverse area, and between total stomatal area and petiole vascular area. Key Results The slopes of both relationships were similar to the slope of the allometric relationship (1.23) between total stomatal area and xylem area of 53 terrestrial plants. However, for ten of them with xylem that can be clearly defined, the strong positive relationship between total stomatal area and petiole xylem area had a significantly smaller slope than that of terrestrial plants (0.64 vs. 1.23). Furthermore, after considering phylogeny, the scaling relationships between total stomatal area and petiole traits in floating-leaved plants remained significant. Conclusions We speculated that for floating-leaved plants, the hyperallometric relationship (slope >1) between the construction of leaf/stoma and petiole was promoted by the high demand for photosynthesis and thus more leaves/stomata. While the hypoallometric relationship (slope

Background and Aims Allometric scaling between stomata and xylem for terrestrial woody plants is a widely observed pattern that may be constrained by water transport. Floating-leaved plants, a particular life form of aquatic plants, have leaves in direct contact with both air and water and a poorly developed xylem that may not be limited by water supply as for terrestrial plants. However, whether such an allometric scaling relationship still exists in floating-leaved plants has not been explored. Methods We analysed 31 floating-leaved species/varieties with a range in leaf area covering six orders of magnitude. For all 31 floating-leaved plants, we studied the allometric relationships between leaf area and petiole transverse area, and between total stomatal area and petiole vascular area. Key Results The slopes of both relationships were similar to the slope of the allometric relationship (1.23) between total stomatal area and xylem area of 53 terrestrial plants. However, for ten of them with xylem that can be clearly defined, the strong positive relationship between total stomatal area and petiole xylem area had a significantly smaller slope than that of terrestrial plants (0.64 vs. 1.23). Furthermore, after considering phylogeny, the scaling relationships between total stomatal area and petiole traits in floating-leaved plants remained significant. Conclusions We speculated that for floating-leaved plants, the hyperallometric relationship (slope >1) between the construction of leaf/stoma and petiole was promoted by the high demand for photosynthesis and thus more leaves/stomata. While the hypoallometric relationship (slope <1) between stomatal and xylem area was related more to hydraulic processes, the selection pressure on stomata was lower than xylem of floating-leaved plants. Allometric relationships among the hydraulic traits on water transport of aquatic plants are the result of natural selection to achieve max, Background and Aims Allometric scaling between stomata and xylem for terrestrial woody plants is a widely observed pattern that may be constrained by water transport. Floating-leaved plants, a particular life form of aquatic plants, have leaves in direct contact with both air and water and a poorly developed xylem that may not be limited by water supply as for terrestrial plants. However, whether such an allometric scaling relationship still exists in floating-leaved plants has not been explored. Methods We analysed 31 floating-leaved species/varieties with a range in leaf area covering six orders of magnitude. For all 31 floating-leaved plants, we studied the allometric relationships between leaf area and petiole transverse area, and between total stomatal area and petiole vascular area. Key Results The slopes of both relationships were similar to the slope of the allometric relationship (1.23) between total stomatal area and xylem area of 53 terrestrial plants. However, for ten of them with xylem that can be clearly defined, the strong positive relationship between total stomatal area and petiole xylem area had a significantly smaller slope than that of terrestrial plants (0.64 vs. 1.23). Furthermore, after considering phylogeny, the scaling relationships between total stomatal area and petiole traits in floating-leaved plants remained significant. Conclusions We speculated that for floating-leaved plants, the hyperallometric relationship (slope >1) between the construction of leaf/stoma and petiole was promoted by the high demand for photosynthesis and thus more leaves/stomata. While the hypoallometric relationship (slope

Accurately tracking mobile devices in wireless and sensor networks using received-signal-strength (RSS) values is a useful task in robotics and activity recognition. It is also a difficult task since radio signals usually attenuate in a highly nonlinear and uncertain way in a complex environment where client devices may be moving. Many existing RSS localization systems suffer from the following problems: first, many of them are inaccurate. Second, to increase their accuracy, many require costly manual calibration. Third, many of them cannot cope with changing data as users move in a dynamic environment. In this thesis, we will describe our learning-based solution using kernels, manifolds and graph Laplacian for solving the these problems. We will demonstrate the effectiveness of our algorithms for tracking static and mobile devices in complex indoor environments using wireless local area network, wireless sensor networks and radio frequency identification networks with much less calibration effort.

This paper addresses the problem of recovering the locations of both mobile devices and access points from radio signals that come in a stream manner, a problem which we call online co-localization, by exploiting both labeled and unlabeled data from mobile devices and access points. Many tracking systems function in two phases: an offline training phase and an online localization phase. In the training phase, models are built from a batch of data that are collected offline. Many of them can not cope with a dynamic environment in which calibration data may come sequentially. In such case, these systems may gradually become inaccurate without a manually costly re-calibration. To solve this problem, we proposed an online co-localization method that can deal with labeled and unlabeled data stream based on semi-supervised manifold-learning techniques. Experiments conducted in wireless local area networks show that we can achieve high accuracy with less calibration effort as compared to several previous systems. Furthermore, our method can deal with online stream data relatively faster than its two-phase counterpart. Copyright © 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Accurately locating users in a wireless environment is an important task for many pervasive computing and AI applications, such as activity recognition. In a WiFi environment, a mobile device can be localized using signals received from various transmitters, such as access points (APs). Most localization approaches build a map between the signal space and the physical location space in a offline phase, and then using the received-signal-strength (RSS) map to estimate the location in an online phase. However, the map can be outdated when the signal-strength values change with time due to environmental dynamics. It is infeasible or expensive to repeat data calibration for reconstructing the RSS map. In such a case, it is important to adapt the model learnt in one time period to another time period without too much recalibration. In this paper, we present a location-estimation approach based on Manifold co-Regularization, which is a machine learning technique for building a mapping function between data. We describe LeManCoR, a system for adapting the mapping function between the signal space and physical location space over different time periods based on Manifold Co-Regularization. We show that LeManCoR can effectively transfer the knowledge between two time periods without requiring too much new calibration effort.We illustrate LeMan-CoR's effectiveness in a real 802.11 WiFi environment. Copyright © 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

The service providers are providing cost effective data preprocessing that support data mining, to find a classification based solution to the direct-marketing problem. Data preprocessing is incorporated into a software system to easily identify customers and predict customer attrition with high accuracy. The SOM is a data-visualization tool that converts high-dimensional data items into geometric relationships and uses nonlinear classification method for data preprocessing. The cost-sensitive-data problem is solved by processing the training subset and considering the samples and actual profit of the customers. The algorithms are developed into ED-Money, which accurately predicts the churned customer and helps business and marketing actions of the service providers. Data preprocessing is an intelligent marketing tool to study customer behavior, increase customer base, exploit customer values, and minimize customer churning.

This paper addresses the problem of recovering the locations of both mobile devices and access points from radio signals that come in a stream manner, a problem which we call online co-localization, by exploiting both labeled and unlabeled data from mobile devices and access points. Many tracking systems function in two phases: an offline training phase and an online localization phase. In the training phase, models are built from a batch of data that are collected offline. Many of them can not cope with a dynamic environment in which calibration data may come sequentially. In such case, these systems may gradually become inaccurate without a manually costly re-calibration. To solve this problem, we proposed an online co-localization method that can deal with labeled and unlabeled data stream based on semi-supervised manifold-learning techniques. Experiments conducted in wireless local area networks show that we can achieve high accuracy with less calibration effort as compared to several previous systems. Furthermore, our method can deal with online stream data relatively faster than its two-phase counterpart. Copyright © 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Accurately locating users in a wireless environment is an important task for many pervasive computing and AI applications, such as activity recognition. In a WiFi environment, a mobile device can be localized using signals received from various transmitters, such as access points (APs). Most localization approaches build a map between the signal space and the physical location space in a offline phase, and then using the received-signal-strength (RSS) map to estimate the location in an online phase. However, the map can be outdated when the signal-strength values change with time due to environmental dynamics. It is infeasible or expensive to repeat data calibration for reconstructing the RSS map. In such a case, it is important to adapt the model learnt in one time period to another time period without too much recalibration. In this paper, we present a location-estimation approach based on Manifold co-Regularization, which is a machine learning technique for building a mapping function between data. We describe LeManCoR, a system for adapting the mapping function between the signal space and physical location space over different time periods based on Manifold Co-Regularization. We show that LeManCoR can effectively transfer the knowledge between two time periods without requiring too much new calibration effort.We illustrate LeMan-CoR's effectiveness in a real 802.11 WiFi environment. Copyright © 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

The service providers are providing cost effective data preprocessing that support data mining, to find a classification based solution to the direct-marketing problem. Data preprocessing is incorporated into a software system to easily identify customers and predict customer attrition with high accuracy. The SOM is a data-visualization tool that converts high-dimensional data items into geometric relationships and uses nonlinear classification method for data preprocessing. The cost-sensitive-data problem is solved by processing the training subset and considering the samples and actual profit of the customers. The algorithms are developed into ED-Money, which accurately predicts the churned customer and helps business and marketing actions of the service providers. Data preprocessing is an intelligent marketing tool to study customer behavior, increase customer base, exploit customer values, and minimize customer churning.

Accurately tracking mobile devices in wireless and sensor networks using received-signal-strength (RSS) values is a useful task in robotics and activity recognition. It is also a difficult task since radio signals usually attenuate in a highly nonlinear and uncertain way in a complex environment where client devices may be moving. Many existing RSS localization systems suffer from the following problems: first, many of them are inaccurate. Second, to increase their accuracy, many require costly manual calibration. Third, many of them cannot cope with changing data as users move in a dynamic environment. In this thesis, we will describe our learning-based solution using kernels, manifolds and graph Laplacian for solving the these problems. We will demonstrate the effectiveness of our algorithms for tracking static and mobile devices in complex indoor environments using wireless local area network, wireless sensor networks and radio frequency identification networks with much less calibration effort.

The service providers are providing cost effective data preprocessing that support data mining, to find a classification based solution to the direct-marketing problem. Data preprocessing is incorporated into a software system to easily identify customers and predict customer attrition with high accuracy. The SOM is a data-visualization tool that converts high-dimensional data items into geometric relationships and uses nonlinear classification method for data preprocessing. The cost-sensitive-data problem is solved by processing the training subset and considering the samples and actual profit of the customers. The algorithms are developed into ED-Money, which accurately predicts the churned customer and helps business and marketing actions of the service providers. Data preprocessing is an intelligent marketing tool to study customer behavior, increase customer base, exploit customer values, and minimize customer churning.

Accurately tracking mobile devices in wireless and sensor networks using received-signal-strength (RSS) values is a useful task in robotics and activity recognition. It is also a difficult task since radio signals usually attenuate in a highly nonlinear and uncertain way in a complex environment where client devices may be moving. Many existing RSS localization systems suffer from the following problems: first, many of them are inaccurate. Second, to increase their accuracy, many require costly manual calibration. Third, many of them cannot cope with changing data as users move in a dynamic environment. In this thesis, we will describe our learning-based solution using kernels, manifolds and graph Laplacian for solving the these problems. We will demonstrate the effectiveness of our algorithms for tracking static and mobile devices in complex indoor environments using wireless local area network, wireless sensor networks and radio frequency identification networks with much less calibration effort.

Accurately locating users in a wireless environment is an important task for many pervasive computing and AI applications, such as activity recognition. In a WiFi environment, a mobile device can be localized using signals received from various transmitters, such as access points (APs). Most localization approaches build a map between the signal space and the physical location space in a offline phase, and then using the received-signal-strength (RSS) map to estimate the location in an online phase. However, the map can be outdated when the signal-strength values change with time due to environmental dynamics. It is infeasible or expensive to repeat data calibration for reconstructing the RSS map. In such a case, it is important to adapt the model learnt in one time period to another time period without too much recalibration. In this paper, we present a location-estimation approach based on Manifold co-Regularization, which is a machine learning technique for building a mapping function between data. We describe LeManCoR, a system for adapting the mapping function between the signal space and physical location space over different time periods based on Manifold Co-Regularization. We show that LeManCoR can effectively transfer the knowledge between two time periods without requiring too much new calibration effort.We illustrate LeMan-CoR's effectiveness in a real 802.11 WiFi environment. Copyright © 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

This paper addresses the problem of recovering the locations of both mobile devices and access points from radio signals that come in a stream manner, a problem which we call online co-localization, by exploiting both labeled and unlabeled data from mobile devices and access points. Many tracking systems function in two phases: an offline training phase and an online localization phase. In the training phase, models are built from a batch of data that are collected offline. Many of them can not cope with a dynamic environment in which calibration data may come sequentially. In such case, these systems may gradually become inaccurate without a manually costly re-calibration. To solve this problem, we proposed an online co-localization method that can deal with labeled and unlabeled data stream based on semi-supervised manifold-learning techniques. Experiments conducted in wireless local area networks show that we can achieve high accuracy with less calibration effort as compared to several previous systems. Furthermore, our method can deal with online stream data relatively faster than its two-phase counterpart. Copyright © 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.