Automatic target recognition (ATR) from satellite imagery involves detection of foreground (FG) objects from the background (BG). ATR demands higher fidelity, which in turn requires more bitrate, hence a conventional ...
详细信息
Automatic target recognition (ATR) from satellite imagery involves detection of foreground (FG) objects from the background (BG). ATR demands higher fidelity, which in turn requires more bitrate, hence a conventional compression, which does not discriminate targets with the background results in poor detection rate. Here we propose a mechanism to achieve lower bitrate without compromising the detection efficiency. By allowing the background to be coded with lower fidelity than the regions-of-interest (ROIs), significant gains can be achieved in terms of compression and hence in storage space and transmission times. One interesting feature of the new JPEG-2000 image coding standard is support of ROI coding using maximum shift (maxshift) method, which allows for arbitrarily shaped ROI image compression without shape coding or explicitly transmitting any shape information to the decoder. We propose a fuzzy C-means clustering approach to generating arbitrary shape mask so as to cluster the images into regions of varying homogeneity. Homogenous ROIs can be coded at a lower bitrate than the high detail regions. This ensures that the target recognition process is not affected by the compression process. A validation benchmark using 'fuzzy feature vectors' is proposed which checks the foreground objects for features like rectangularity, circularity, elongatedness, symmetry, area etc., as compared to its uncompressed equivalent. The validation is done on Standard JPEG, JPEG-2000 with ROI coding and JPEG-2000 without ROI coding at preset bitrates and compared.
In this paper we study uninorms with given strict underlying t-norm and t-conorm. Such uninorms are the only candidates for being represented by (additive) generator functions. We prove that representability depends e...
详细信息
In this paper we study uninorms with given strict underlying t-norm and t-conorm. Such uninorms are the only candidates for being represented by (additive) generator functions. We prove that representability depends exclusively on the value of the uninorm at a single point in the ldquoremainingrdquo open part of the unit square. The uninorm turns out to be representable if and only if this single value is strictly between the two bounds min and max. If this single value equals to one of the bounds then all values are equal to the same bound at any point in that ldquoremainingrdquo part.
In the flotation process, the concentrate grade and the tailing grade are crucial technical indices which reflect the product quality and efficiency. There are strong nonlinearity and uncertainty in such technical ind...
In the flotation process, the concentrate grade and the tailing grade are crucial technical indices which reflect the product quality and efficiency. There are strong nonlinearity and uncertainty in such technical indices dynamic behaviors, which can hardly be described using accurate mathematical model. The technical indices which cannot be measured online continuously vary with boundary conditions. Therefore conventional control methods are incapable of keeping the actual the concentrate grade and the tailing grade within the target ranges. In this paper, an intelligent control method comprised of the setting layer and the closed loop control layer for the flotation reagent addition to the process has been presented. In flotation reagent feeding setting layer, a unit reagent pre-setting model, a feedback compensator and a feed forward compensator RBR based on (Rule-based reasoning) are integrated with a flotation reagent computation model to set the flotation reagent feeding. The control system updates automatically flotation reagent feeding when the boundary conditions changes. Successfully industrial application has shown that the concentrate grate has been increased by 0.52%, the tailing grade has been reduced by 4%, and the consumption of the flotation reagent feeding has been reduced by 17.5%. Significant application effect has been achieved.
Since the mid 1990s there has been on increasing recognition of chemical engineering's multiscale nature. Multiscale modelling attempts to create flexible and efficient models by linking two or more partial models...
Since the mid 1990s there has been on increasing recognition of chemical engineering's multiscale nature. Multiscale modelling attempts to create flexible and efficient models by linking two or more partial models that describe phenomena at different characteristic length and time scales. In the first part of this paper, we briefly review multiscale modelling in chemical engineering. Three key tasks used in multiscale modelling are identified, and the current practices and unresolved issues in each are discussed. The second part of the paper examines the modelling of a wet granulation circuit from a multiscale perspective. A ‘scale map’ for drum granulation is proposed to assist in visualising the multiscale nature of the system. The three multiscale modelling tasks are considered in turn and some suggestions for modelling are proposed. Through this paper we are seeking to promote discussion on multiscale modelling and to receive feedback on its application to granulation.
State estimation and model predictive control using finite Markov chains are considered. A Bayesian state estimate of the probability distribution of the systems current state is constructed, based on measured data an...
详细信息
During hot rolling processes, the material under deformation undergoes different deformation conditions, i.e. temperature changes and strain rates. One particular variable is the change in strain rate which can vary f...
详细信息
During the thermomechanical processing of aluminium alloys, the material experiences a complex history of temperature, time, and strain path. The rolling and deformation process has an effect on the evolution of the m...
详细信息
This study presents the application of FE modelling and intelligent systems techniques to the prediction of microstructural mapping for aluminium alloys. Here, the material within each finite element is defined using ...
详细信息
State estimation and model predictive control using finite Markov chains are considered. A Bayesian state estimate of the probability distribution of the systems current state is constructed, based on measured data an...
详细信息
State estimation and model predictive control using finite Markov chains are considered. A Bayesian state estimate of the probability distribution of the systems current state is constructed, based on measured data and prior estimate. A control action is then determined under the predictive control paradigm, starting from the uncertain state estimate. A simulation illustrates the feasibility of the approach using a standard office PC.
暂无评论