100,677 research outputs found
Gait Learning-Based Regenerative Model: a Level Set Approach
No full textWe propose a learning method for gait synthesis from a sequence of shapes(frames) with the ability to extrapolate to novel data. It involves the application of PCA, first to reduce the data dimensionality to certain features, and second to model corresponding features derived from the training gait cycles as a Gaussian distribution. This approach transforms a non Gaussian shape deformation problem into a Gaussian one by considering features of entire gait cycles as vectors in a Gaussian space. We show that these features which we formulate as continuous functions can be modeled by PCA. We also use this model to in-between (generate intermediate unknown) shapes in the training cycle. Furthermore, this paper demonstrates that the derived features can be used in the identification of pedestrians
Level Set Gait Analysis for Synthesis and Reconstruction
No full textWe describe a new technique to extract the boundary of a walking subject, with ability to predict movement in missing frames. This paper uses a level sets representation of the training shapes and uses an interpolating cubic spline to model the eigenmodes of implicit shapes. Our contribution is to use a continuous representation of the feature space variation with time. The experimental results demonstrate that this level set-based technique can be used reliably in reconstructing the training shapes, estimating in-between frames to help in synchronizing multiple cameras, compensating for missing training sample frames, and the recognition of subjects based on their gai
Shape registration using characteristic functions
No full textThis paper presents a fast algorithm for the registration of shapes implicitly represented by their characteristic functions. The proposed algorithm aims to recover the transformation parameters (scaling, rotation, and translation) by minimizing a dissimilarity term between two shapes. The algorithm is based on phase correlation and statistical shape moments to compute the registration parameters individually. The algorithm proposed here is applied to various registration problems, to address issues such as the registration of shapes with various topologies, and registration of complex shapes containing various numbers of sub-shapes. Our method proposed here is characterized with a better performance for registration over large databases of shapes, a better accuracy, a higher convergence speed and robustness at the presence of excessive noise in comparison with other state-of-the-art shape registration algorithms in the literatur
Robust Rigid Shape Registration Method Using a Level Set Formulation
No full textThis paper presents a fast algorithm for robust registration of shapes implicitly represented by signed distance functions(SDF). The proposed algorithm aims to recover the transformation parameters( scaling, rotation, and translation) by minimizing the dissimilarity between two shapes. To achieve a robust and fast algorithm, linear orthogonal transformations are employed to minimize the dissimilarity measures. The algorithm is applied to various shape registration problems, to address issues such as topological invariance, shape complexity, and convergence speed and stability. The outcomes are compared with other state-of-the-art shape registration algorithms to show the advantages of the new technique
On analysing deformable (moving) objects
No full textPerforming a high level vision is usually based on features extracted at low and intermediate levels of the process of perception of a visual scene.Segmentation and matching are instrumental tasks in producing comparable features in applications such as medical imaging, mining and oil extraction, gaming consoles, face, ear and gait biometrics, and etc.The ultimate goal of this study is to develop a fully functional prior aided segmentation framework to extract deformable shapes over a sequence of frames. This thesis acknowledges the demand by these applications for a robust and flexible approach which is particularly designed to extract deformable timely shape sequences. It is also recognised that existing methods are either too general, and thus inaccurate, or too specific, thereby limited in usability.This thesis suggests a learning model for gait synthesis with the ability to extrapolate to novel data. It involves computing comparable features from multiple sources. We show that these features which we formulate as continuous functions can be modelled by linear PCA.This thesis also proposes a new fast and robust shape registration algorithm to match shapes from different sources in the proposed framework. This algorithm is based on linear orthogonal transformations and shape moments. The registration parameters are computed directly by analysing the signed distance functions of the shapes. This is in-line with the level sets based prior shape segmentation framework adopted here. The segmentation is performed in a balanced framework between the data in the given images on one hand and the prior induced by the shape model and the registration algorithm proposed here on the other hand. This configuration ensures more control for the shape force over the overall shape geometry. Thus, favouring shapes familiar to the learned knowledge
Optimization of Vehicles Routing Problem using GA For AL-Rasheed municipality, Baghdad, Iraq
No full textThere are several problems with waste collection, transportation, processing, and disposal, particularly in major cities. The frequency of garbage collection is an important concern for municipal control. If waste is not disposed of properly, environmental problems such as air pollution and groundwater contamination may occur. This problem raises the alarm for the need for specialized solutions for averting potential calamities that might occur throughout the world. Before deploying to actual situations, computer modeling and planning of waste collection are frequently performed to minimize the negative impact solid waste can have on the environment. As a result, choosing the optimal waste collection policy has a large effect on cost savings. The current study's objective is to apply a genetic algorithm to reach the goals, illustrating the process of selecting the optimal route for the vehicle with the lowest time and greatest weight among several paths. The other goal is to create a schedule for the vehicles in order to decrease them. The schedule will minimize vehicle-related costs such as maintenance, gasoline, work staff salaries, and other vehicle-related costs. In the current study, the MATLAB application R2020a is used to apply reliable data of 10 vehicles from the AL-Rasheed Municipality waste collection vehicles after processing it to be acceptable with the GA. After optimizing the time for routes and weights of lifted trash, the majority of the results improved dramatically. The results reveal that the top five vehicles (8, 6, 7, 1, 4) have a great percentage improvement in the number of collection points (133.3%, 100%, 100%, 66.7%, and 50%), respectively
An e-Learning Environment Based on the Moodle Platform for Iraq Universities
No full textThis paper proposes the deployment of learning management systems to provide virtual environment to higher education in Iraq. In this paper we show that implementing a learning management system (LMS) to manage learning process is within reach even with little material and human resources. This paper proposes an open source popular and free of charge platform called Moodle. We also show that other solutions such as web-based alternatives to LMS are completely unaffordable given the limited financial resources of our universities. The system is aimed for use by university level students and educators (teachers and instructors). Further, a deployment plan is given in this paper to provide a guidance and reference for the implementation requirements and steps of this LMS operation
Maktabat Al Muthanna Baghdad Feb-May 1962
No full textOn the same date, Ali Al-Mansouri issued an official financial statement confirming that the Al-Khanji Foundation owed a total of 11.375.أصدر علي المنصوري بيانًا ماليًا رسميًا بتاريخ 25 نيسان 1962 يُفيد بأن مؤسسة الخانجي مدينة بمبلغ إجمالي قدره 11,375
Detection of epileptic seizures in EEG by using machine learning techniques
No full textIn this research a public dataset of recordings of EEG signals of healthy subjects and epileptic patients was used to build three simple classifiers with low time complexity, these are decision tree, random forest and AdaBoost algorithm. The data was initially preprocessed to extract short waves of electrical signals representing brain activity. The signals are then used for the selected models. Experimental results showed that random forest achieved the best accuracy of detection of the presence/absence of epileptic seizure in the EEG signals at 97.23% followed by decision tree with accuracy of 96.93%. The least performing algorithm was the AdaBoost scoring accuracy of 87.23%. Further, the AUC scores were 99% for decision tree, 99.9% for random forest and 95.6% for AdaBoost. These results are comparable to state-of-the-art classifiers which have higher time complexity
- …
