Search

Internet user has caused a tremendous growth in the information quantity, information accesses, information classification and complexity of Internet topologies handling information. Multidimensional data (mobile apps usage data (mix data set (log data))) contains a huge number of irrelevant redundant information. Users of a web application find it difficult to get the required information quickly and effectively due to enormous size of data (huge data generated per second). Numerous machine learning algorithms are useful to an amount of dataset to find the efficiency and accuracy of the classifiers. One of the potent solutions for this problem is web personalization. Providing personalized recommendations to users for improving credibility depend on the web application usage of the useful information in web application. It is very difficult to predict the behavior of such personalization systems. Our proposed intelligent map reducer model is based on machine learning concept. The results of this research are significant for training and testing of big datasets for Map Reduce Fusion Deep Learning Based on Back Propagation Neural Network algorithm established classification problems. The proposed algorithm is implemented using the HADOOP framework and enhanced the performance of existing map reducer model by improving the accuracy and reduce error rate.

In this paper, we investigate the impact of the deformable bodies on the control algorithms for physically simulated characters. We hypothesize that ignoring the effect of deformable bodies at the site of contact negatively affects the control algorithms, leading to less robust and unnatural character motions. To verify the hypothesis, we introduce a compact representation for an articulated character with deformable soft tissue and develop a practical system to simulate two-way coupling between rigid and deformable bodies in a robust and efficient manner. We then apply a few simple and widely used control algorithms, such as pose-space tracking control, Cartesian-space tracking control, and a biped controller (SIMBICON), to simulate a variety of behaviors for both full-body locomotion and hand manipulation. We conduct a series of experiments to compare our results with the motion generated by these algorithms on a character comprising only rigid bodies. The evaluation shows that the character with soft contact can withstand larger perturbations in a more noisy environment, as well as produce more realistic motion.

We present a physics-based approach to synthesizing motion of a virtual character in a dynamically varying environment. Our approach views the motion of a responsive virtual character as a sequence of solutions to the constrained optimization problem formulated at every time step. This framework allows the programmer to specify active control strategies using intuitive kinematic goals, significantly reducing the engineering effort entailed in active body control. Our optimization framework can incorporate changes in the character's surroundings through a synthetic visual sensory system and create significantly different motions in response to varying environmental stimuli. Our results show that our approach is general enough to encompass a wide variety of highly interactive motions.

We present an interactive motion editing tool for creating dynamic scenes with human and object interaction. Our approach solves for an optimal control problem that leverages methods for physics-based rigid body control and kinematics-based human motion editing. Because the humans and the objects are coupled via physical contacts, our interface allows the animator to directly change the trajectories of humans or objects and simultaneously render the effect of the edits on the entire scene. Consequently, the animator can efficiently create complex interaction that requires precise synchronization, such as juggling. Our framework is generic to the choice of human motion editing method, as long as the differential information of the motion can be computed.

Modeling the reactions of human characters to a dynamic environment is crucial for achieving perceptual immersion in applications such as video games, training simulations and movies. Virtual characters in these applications need to realistically react to environmental events and precisely follow high-level user commands. Most existing physics engines for computer animation facilitate synthesis of passive motion, but remain unsuccessful in generating motion that requires active control, such as character animation. We present an optimization-based approach to synthesizing active motion for articulated characters, emphasizing both physical realism and user controllability. At each time step, we optimize the motion based on a set of goals specified by higher-level decision makers, subject to the Lagrangian dynamics and the physical limitations of the character. Our framework represents each decision maker as a controller.

Motion pictures of all sorts make heavy use of "extra" actors to bring fidelity and liveliness to a scene. These secondary characters are usually engaged in low-energy, background actions and are often seen close-up and in-detail. This fabric of background human activity comes with two main challenges. First, secondary characters must be able to react to events in their environment. Second, characters should not exhibit motions that are too repetitive. In this paper, we propose an approach to generating physically realistic and non-repetitive motion for small groups of autonomous secondary characters. To equip a character with a wide range of motor skills we introduce the concepts of behavior and transition. A behavior models the ability of a character to remain within range of a set of well-defined configurations, while a transition allows the character to change its behavior. Characters choose their behavior as a response to the environment and in accordance to a simple physiological model.

This paper presents a novel approach to estimate the changing internal and external parameters of the camera in real time using a few 3D-2D point correspondences. We approach the problem by constructing two filters which can individually track motion and zoom respectively in a robust manner. Then, the Viterbi algorithm is used to select a filter depending on whether the camera is undergoing motion or zoom. We assume that the camera cannot move and zoom simultaneously, though our method can tolerate some hand held movement during zoom. The application of our approach is demonstrated on synthetic and real data.