Conventional Canny edge detector can detect edges in image with additive noise effectively but not ultrasound image that are corrupted by multiplicative speckle noise which alleviates image resolution resulting in ina...
详细信息
ISBN:
(纸本)9781618040237
Conventional Canny edge detector can detect edges in image with additive noise effectively but not ultrasound image that are corrupted by multiplicative speckle noise which alleviates image resolution resulting in inaccurate characterization of object features. In this paper, we proposed to incorporate the modified SRAD into the Canny edge detector to replace the Gaussian blurring in the conventional Canny edge detector in order to suppress the multiplicative noise effectively while preserving the edge of the object in ultrasound image. The result shows that the proposed method can provide better result than conventional method in a much wider range of parameter values. The proposed method through experimental result indicates that it is capable of producing promising edge detection result in ultrasound image.
Ultrasound medical imaging is widely used nowadays in clinical application due to its intuitive, convenient, safety, non-invasive, and low cost. However, ultrasound image formation always comes with speckle-noise whic...
详细信息
ISBN:
(纸本)9781618040237
Ultrasound medical imaging is widely used nowadays in clinical application due to its intuitive, convenient, safety, non-invasive, and low cost. However, ultrasound image formation always comes with speckle-noise which will greatly reduce the image quality, and makes the identification and analysis of image detail become more challenging. Hence, we present an extended robust diffusion algorithm for optimum diffusion while retain the edge of image features. Total eight spreading diffusion directions are implemented in the proposed algorithm. Finding showed that this method is able to provide consistent and more objective results.
This paper focus on radial-basis function (RBF) neural networks, the most popular and widely-used paradigms in many applications, including renewable energy forecasting. It provides an analysis of short term load fore...
详细信息
ISBN:
(纸本)9789898425751
This paper focus on radial-basis function (RBF) neural networks, the most popular and widely-used paradigms in many applications, including renewable energy forecasting. It provides an analysis of short term load forecasting STLF performances of RBF neural networks. Precisely, the goal is to forecast the DPcg (difference between the electricity produced from renewable energy sources and consumed), for short-term horizon. The forecasting accuracy and precision, in capturing nonlinear interdependencies between the load and solar radiation of these neural networks are illustrated and discussed using a data based obtain from an experimental photovoltaic amphitheatre of minimum dimension 0.4kV/10kW.
The agent's decision mechanism should take into account only the events which can influence the agent's decision. That is way it is necessary to embed the event processing technology into multi-agent systems d...
详细信息
Electroencephalography is an important diagnostic tool for functional investigations of the human brain. Recent EEG measurement technologies provide high numbers of electrodes and sampling rates, which results in a co...
详细信息
This paper introduces a new methodology to develop comprehensive structural and behavioral models of kinesin nanomotor within its cell using agent technology. In this work, firstly, kinesin nanomotor is introduced as ...
详细信息
Bio-nanorobotic systems are made from bio-nanocomponents, particularly proteins. An important group of such protein-based bio-nanocomponents are myosin protein nanomotors that are involved in a wide variety of cellula...
详细信息
This paper concerns a trajectory tracking control problem for a pendulum with variable length, which is an underactuated mechanical system of two degrees-of-freedom with a single input of adjusting the length of the p...
详细信息
A low cost hardware platform consisting of a measurement system, a communication system and a data processing system is presented. Wired and wireless sensors are developed for supporting motor current signature analys...
详细信息
Positive and unlabelled learning (PU learning) has been investigated to deal with the situation where only the positive examples and the unlabelled examples are available. Most of the previous works focus on identifyi...
详细信息
ISBN:
(纸本)9781577355120
Positive and unlabelled learning (PU learning) has been investigated to deal with the situation where only the positive examples and the unlabelled examples are available. Most of the previous works focus on identifying some negative examples from the unlabelled data, so that the supervised learning methods can be applied to build a classifier. However, for the remaining unlabelled data, which can not be explicitly identified as positive or negative (we call them ambiguous examples), they either exclude them from the training phase or simply enforce them to either class. Consequently, their performance may be constrained. This paper proposes a novel approach, called similarity-based PU learning (SPUL) method, by associating the ambiguous examples with two similarity weights, which indicate the similarity of an ambiguous example towards the positive class and the negative class, respectively. The local similarity-based and global similarity-based mechanisms are proposed to generate the similarity weights. The ambiguous examples and their similarity-weights are thereafter incorporated into an SVM-based learning phase to build a more accurate classifier. Extensive experiments on real-world datasets have shown that SPUL outperforms state-of-the-art PU learning methods.
暂无评论