Feature descriptors involved in video processing are generally high dimensional in nature. Even though the extracted features are high dimensional, many a times the task at hand depends only on a small subset of these...
详细信息
ISBN:
(纸本)9781479919611
Feature descriptors involved in video processing are generally high dimensional in nature. Even though the extracted features are high dimensional, many a times the task at hand depends only on a small subset of these features. For example, if two actions like running and walking have to be identified, extracting features related to the leg movement of the person is enough. Since, this subset is not known apriori, we tend to use all the features, irrespective of the complexity of the task at hand. Selecting task-aware features may not only improve the efficiency but also the accuracy of the system. In this work, we propose a supervised approach for task-aware selection of features using Deep Neural Networks (DNN) in the context of action recognition. The activation potentials contributed by each of the individual input dimensions at the first hidden layer are used for selecting the most appropriate features. The selected features are found to give better classification performance than the original high-dimensional features. It is also shown that the classification performance of the proposed feature selection technique is superior to the low-dimensional representation obtained by principal component analysis (PCA).
Water distribution system design is a challenging optimisation problem with a high number of search dimensions and constraints. In this way, Evolutionary Algorithms (EAs) have been widely applied to optimise WDS to mi...
详细信息
The ongoing research in Distributed Video Coding (DVC) for low complexity encoding is trying to bridge the substantial performance gap to well known state-of-the-art coders. We introduce our true motion based extrapol...
详细信息
ISBN:
(纸本)9789898109057
The ongoing research in Distributed Video Coding (DVC) for low complexity encoding is trying to bridge the substantial performance gap to well known state-of-the-art coders. We introduce our true motion based extrapolation scheme and compare its performance to other state of the art systems in the field of DVC. The results of the extrapolation based approach display nearly the same performance as interpolation based ones. These results are also significantly better than the results from other state of the art extrapolation approaches. Furthermore we study the influence of the motion estimation part by investigating an interpolation approach, based on the same scheme. Finally, we study the losses incurred by using only past frames to represent the motion in the current one.
This book provides a classification of current and future applications for the domain of Cooperating Objects. The book has been created with a very strong participation of the industry and taking into account current ...
详细信息
ISBN:
(数字)9783642284694
ISBN:
(纸本)9783642284687
This book provides a classification of current and future applications for the domain of Cooperating Objects. The book has been created with a very strong participation of the industry and taking into account current research trends and industrial roadmaps
As service-oriented architectures (SOA) mature, an efficient approach for the integration of Web services in portals is required. This holds true especially in medium and large-scale SOA-based systems with a multitude...
详细信息
As service-oriented architectures (SOA) mature, an efficient approach for the integration of Web services in portals is required. This holds true especially in medium and large-scale SOA-based systems with a multitude of Web services to be made accessible to the users. The integration scenarios, i.e. the Web service-based features within a portal, are usually composed of complex sequences of user interaction and service communication, aggravating the need for an efficient integration solution. We present an approach for the business process-driven modeling of these scenarios in form of 'user interaction (UI) workflows' as well as a technical framework enabling the model execution within existing portal systems. The integration of Web services in a portal can thus be realized very efficiently by modeling UI workflows and configuring highly generic activity building blocks for dialog construction, service communication and data presentation.
Liver cancer is the second leading cause of cancer deaths worldwide. Without treatment, the five-year survival rate is less than 5%. Liver tumors are often detected using MRI. MRI is preferable over other imaging moda...
详细信息
ISBN:
(数字)9781728159072
ISBN:
(纸本)9781728159089
Liver cancer is the second leading cause of cancer deaths worldwide. Without treatment, the five-year survival rate is less than 5%. Liver tumors are often detected using MRI. MRI is preferable over other imaging modalities include absence of ionizing radiation, superior soft tissue contrast resolution, and multiplanar imaging capabilities. Needle interventions are then needed for further diagnosis (biopsy) and treatment (ablation). Respiratory motion is the main cause of inaxccurate needle placement leading to misdiagnosis and insufficient treatment. In order to train clinicians to compensate for the liver respiratory motion during intervention, and also test needle insertion robotics technologies, a realistic liver motion simulator is of great interest which can be used inside MRI scanner. In this study, an MR-compatible soft robotic platform is developed to simulate liver respiratory motion. Pneumatically actuated soft robotic actuators were developed and validated using finite element simulations. A feedforward controller was developed to control the input air pressures of the pneumatic actuators to simulate the respiratory motion. The evaluative experiments indicated that the developed soft robotics diaphragm could acceptably simulate liver respiratory motion in the two directions of motion: superior-inferior and anterior-posterior directions.
Nowadays, many web-based systems have been using machine learning techniques in order to design more intelligent mechanisms for organizing, indexing, and retrieving web content, and it is necessary for more and more r...
详细信息
Nowadays, many web-based systems have been using machine learning techniques in order to design more intelligent mechanisms for organizing, indexing, and retrieving web content, and it is necessary for more and more researches and applications to calculate the distance of web pages rationally. Generally proposed methodology is fit for extracting the differences between HTML documents of web pages, results of which cannot be used to tell the actual distance, between the content of web pages and the facade displayed in internet explorers. Based on these above, content distance, style distance, and hybrid distance are proposed in this paper, to make measurement result more practical. The efficiency will be proved through some classical experiments.
暂无评论