Local Probability Model Research Articles

Object detection and tracking under Complex environment using deep learning‐based LPM

Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand‐crafted features, which are not sufficiently robust to a complex environment. Moreover, the processes of detection and tracking are separated, which leads to the overall efficiency not high. In this study, a novel local probability model (LPM)‐based mean shift (MS) algorithm is proposed to integrate object detection and tracking. The main contributions include: (i) a new framework based on the combination of LPM and MS is established for the integration of object tracking and detection. (ii) For object detection, the training and prediction of LPM are built by stacked denoising autoencoders based deep learning. (iii) For object tracking, an MS tracking algorithm leveraging LPM is modified to improve the tracking efficiency under a complex environment. Experimental results demonstrate that the proposed method is superior to the colour histograms based MS and histograms of oriented gradients based MS in terms of robustness and tracking accuracy.

Bell’s Nonlocality in a General Nonsignaling Case: Quantitatively and Conceptually

Quantum violation of Bell inequalities is now used in many quantum information applications and it is important to analyze it both quantitatively and conceptually. In the present paper, we analyze violation of multipartite Bell inequalities via the local probability model - the LqHV (local quasi hidden variable) model [Loubenets, J. Math. Phys. 53, 022201 (2012)], incorporating the LHV model only as a particular case and correctly reproducing the probabilistic description of every quantum correlation scenario, more generally, every nonsignaling scenario. The LqHV probability framework allows us to construct nonsignaling analogs of Bell inequalities and to specify parameters quantifying violation of Bell inequalities - Bell's nonlocality - in a general nonsignaling case. For quantum correlation scenarios on an N-qudit state, we evaluate these nonlocality parameters analytically in terms of dilation characteristics of an N-qudit state and also, numerically - in d and N. In view of our rigorous mathematical description of Bell's nonlocality in a general nonsignaling case via the local probability model, we argue that violation of Bell inequalities in a quantum case is not due to violation of the Einstein-Podolsky-Rosen (EPR) locality conjectured by Bell but due to the improper HV modelling of "quantum realism".

On the existence of a local quasi hidden variable (LqHV) model for eachN-qudit state and the maximal quantum violation of Bell inequalities

We specify the local quasi hidden variable (LqHV) model reproducing the probabilistic description of all N-partite joint von Neumann measurements on an N-qudit state. Via this local probability model, we derive a new upper bound on the maximal violation by an N-qudit state of Bell inequalities of any type (either on correlation functions or on joint probabilities) for [Formula: see text] observables per site. This new upper bound not only improves for all [Formula: see text] [Formula: see text] and d the corresponding results available for general Bell inequalities in the literature but also, for the N-qubit case with two observables per site, reduces exactly to the attainable upper bound known for quantum violations of correlation [Formula: see text] setting Bell inequalities in a dichotomic case.

A bi-population EDA for solving the no-idle permutation flow-shop scheduling problem with the total tardiness criterion

In this paper, an effective bi-population estimation of distribution algorithm (BEDA) is presented to solve the no-idle permutation flow-shop scheduling problem (NIPFSP) with the total tardiness criterion. To enhance the search efficiency and maintain the diversity of the whole population, two sub-populations are used in the BEDA. The two sub-populations are generated by sampling the probability models that are updated differently for the global exploration and the local exploitation, respectively. Meanwhile, the two sub-populations collaborate with each other to share search information for adjusting the models. To well adjust the models for generating promising solutions, the global probability model is updated during the evolution with the superior population and the local probability model is updated with the best solution that has been explored. To further enhance exploitation in the promising region, the insertion operator is used iteratively as the local search procedure. To investigate the influence of parameter setting, numerical study based on the Taguchi method of design-of-experiment is carried out. The effectiveness of the bi-population strategy and local search procedure is shown by numerical comparisons, and the comparisons with the recently published algorithms by using the benchmarking instances also demonstrate the effectiveness of the proposed BEDA.

Adaptive Local Outlier Probability for Dynamic Process Monitoring

Complex industrial processes often have multiple operating modes and present time-varying behavior. The data in one mode may follow specific Gaussian or non-Gaussian distributions. In this paper, a numerically efficient moving window local outlier probability algorithm is proposed. Its key feature is the capability to handle complex data distributions and incursive operating condition changes including slow dynamic variations and instant mode shifts. First, a two-step adaption approach is introduced and some designed updating rules are applied to keep the monitoring model up-to-date. Then, a semi-supervised monitoring strategy is developed with an updating switch rule to deal with mode changes. Based on local probability models, the algorithm has a superior ability in detecting faulty conditions and fast adapting to slow variations and new operating modes. Finally, the utility of the proposed method is demonstrated with a numerical example and a non-isothermal continuous stirred tank reactor.