The objective of this paper is to provide improved real-time noise canceling performance while keeping the high quality of enhanced speech by using new robust adaptive beamformer. The proposed beamformer uses a new ad...
详细信息
ISBN:
(纸本)9781424415014
The objective of this paper is to provide improved real-time noise canceling performance while keeping the high quality of enhanced speech by using new robust adaptive beamformer. The proposed beamformer uses a new adaptive blocking matrix, which consists of linear prediction error filters (LPEFs). It also employ a multi-channel noise canceller with adaptive noise estimation filters (ANEFs) used for inverse modeling. The entire proposed system has been implemented in real-time in a real environment using National Instruments NI-PXI-1042Q controller system and data acquisition card NI-PXI-4472. Practical results show that the proposed beamformer produces results that are significantly favorable than standard GSC beamformer.
Unpredictable topology changes, energy constraints and link unreliability make the information transmission a challenging problem in wireless sensornetworks (WSN). Taking some ideas from machine learning methods, we ...
详细信息
ISBN:
(纸本)9781424415014
Unpredictable topology changes, energy constraints and link unreliability make the information transmission a challenging problem in wireless sensornetworks (WSN). Taking some ideas from machine learning methods, we propose a novel geographic routing algorithm for WSN, named Q-Probabilistic Routing (Q-PR), that makes intelligent routing decisions from the delayed reward of previous actions and the local interaction among neighbor nodes, by using reinforcement learning and a Bayesian decision model. Moreover, by considering the message importance embedded in the message itself, routing decisions can-be adapted to traffic importance. Experimental results show that Q-PR becomes a routing policy that, as a function of the message importance, achieves a trade-off among the expected number of retransmissions (ETX), the successful delivery rate and the network lifetime.
In this paper we characterize the relative sensor-target geometry in R-2 in terms of potential localization performance for time-of-arrival based localization. Our aim is to characterize those relative sensor-target g...
详细信息
ISBN:
(纸本)9781424415014
In this paper we characterize the relative sensor-target geometry in R-2 in terms of potential localization performance for time-of-arrival based localization. Our aim is to characterize those relative sensor-target geometries which minimize the relative Cramer-Rao lower bound.
In this paper, the problem of fully-decentralized data fusion is addressed for tracking a target with nonlinear motion model. The problem is solved by applying a fully-decentralized estimation algorithm based on the e...
详细信息
ISBN:
(纸本)9781424407781
In this paper, the problem of fully-decentralized data fusion is addressed for tracking a target with nonlinear motion model. The problem is solved by applying a fully-decentralized estimation algorithm based on the extended information filter. We propose the Neighbor Selection and information Selection algorithms for sensor selection based on their closeness to the estimated target position and their information contribution, respectively. Simulation results show that compared to the DEIF algorithm we obtain an analogous response with less consumption of energy and computations.
Publish/Subscribe (Pub/Sub) systems have been used in traditional distributed computing applications to provide effective and efficient event services. Recently, the design of Pub/Sub systems are proposed for wireless...
详细信息
ISBN:
(纸本)9781424415014
Publish/Subscribe (Pub/Sub) systems have been used in traditional distributed computing applications to provide effective and efficient event services. Recently, the design of Pub/Sub systems are proposed for wireless sensornetworks (WSNs). Some of the proposed Pub/Sub protocols address the issue of establishing event delivery path with low routing cost by using geographic information. However, they have not considered how to reduce redundant event delivery, which may cause high resource consumption and poor system scalability. In this paper, we propose protocols which address both issues. More specifically, our protocols use geographic information to save routing cost, and meanwhile reduce redundant event delivery by letting the subscribers share the event delivery paths. Three highly scalable and efficient Pub/Sub protocols for WSNs, namely Shortest Delivery Path (SDP), Shortest Delivery Path with Lower Delivery Overhead (SDP-LDO), and Lowest Delivery Overhead (LDO), are designed to achieve different performance goals. The results of theoretical and experimental evaluation show that the proposed protocols can significantly improve the resource efficiency and scalability of a Pub/Sub system compared to the previous solutions. Our protocols can also be used to achieve a good tradeoff between the costs of event subscribing and event delivery.
One of the possible causes for global warming is the human intervention in the environment. The increasing amount of industrial and residential contaminants in lakes and rivers is seriously harming the quality of the ...
详细信息
ISBN:
(纸本)9781424415014
One of the possible causes for global warming is the human intervention in the environment. The increasing amount of industrial and residential contaminants in lakes and rivers is seriously harming the quality of the water resources. In many countries, most of the sewage is directly sent to rivers or lakes, without any treatment. The impact on the environment of toxic waste, from a wide variety of manufacturing processes, is well known. More recently, however, it has become clear that the more subtle effects of nutrient level and chemical balance changes arising from farming land run-off and sewage water treatment also have a serious, but indirect, effect on the states of rivers, lakes and even the sea. This paper investigates the use of a hybrid Case Based Reasoning system for monitoring water quality based on chemical and physical parameters and algae population.
Data gathering in wireless sensornetworks is one of the essential tasks that has to be performed efficiently due to the sensors' limited processing, storage, and communication capabilities. When sensor nodes cont...
详细信息
ISBN:
(纸本)9781424418343
Data gathering in wireless sensornetworks is one of the essential tasks that has to be performed efficiently due to the sensors' limited processing, storage, and communication capabilities. When sensor nodes continuously sense and wirelessly transmit raw sensor readings, predicting such readings might be a promising approach to save energy. This paper examines two adaptive prediction algorithms called as Least Mean Square and Recursive Least Square, integrated in a data gathering framework. A comprehensive simulation study of these algorithms assuming Gaussian processes shows that significant communication savings while guaranteeing a user-defined maximum error can be achieved. Especially, low processing costs and memory usage favor these algorithms for practical sensor node implementations. Finally, we prove the wide applicability of our data gathering framework investigating different kinds of real world sensor traces.
In this paper, a new intelligent method of classifying benign and malignant melanoma lesions is implemented. The system consists of four stages;image pre-processing, image segmentation, feature extraction, and image c...
详细信息
ISBN:
(纸本)9781424415014
In this paper, a new intelligent method of classifying benign and malignant melanoma lesions is implemented. The system consists of four stages;image pre-processing, image segmentation, feature extraction, and image classification. As the first step of the image analysis, pre-processing techniques are implemented to remove noise and undesired structures from the images using techniques such as median filtering and contrast enhancement. In the second step, a simple thresholding method is used to segment and localise the lesion, a boundary tracing algorithm is also implemented to validate the segmentation. Then, a wavelet approach is used to extract the features, more specifically Wavelet Packet Transform (WPT). Finally, the dimensionality of the selected features is reduced with Principal Component Chalysis (PCA) and later supplied to an Artificial Neural Network and Support Vector Machine classifiers for classification. The ability to correctly discriminate between benign and malignant lesions was about 95% for the Artificial Neural Network and 85% for the Support Vector Machine classifier.
A new routing protocol for wireless sensornetworks supporting disjoint multi-path is presented in this article. With the incorporation of the concept Of gradient defined on the hop-count from a given node to the sink...
详细信息
ISBN:
(纸本)0769529941
A new routing protocol for wireless sensornetworks supporting disjoint multi-path is presented in this article. With the incorporation of the concept Of gradient defined on the hop-count from a given node to the sink node, the propagation of control messages can be controlled to be within necessary direction, rather than omni-directional flooding. Such an approach will reduce the number of control messages considerably, so as the power consumption of sensor nodes. Experiment results reveal that the proposed scheme outperform it competitor in control overhead, packet delay, as well as throughout.
Wireless sensornetworks have the limitations of energy. An efficient MAC protocol has to be applied to serve the purpose of energy saving and also aiming to make it cost efficient. This paper presents a novel hybrid ...
详细信息
暂无评论