Multi-layer Hierarchical Model Research Articles

Hazard identification, risk assessment and management of industrial system: Process safety in mining industry

Hazard identification, risk assessment and management are of great significance for the safe and efficient production of industrial system. However, due to the lack of quantitative methods, the production of industrial systems still lacks safety guarantees. Firstly, we revise the accident causation model of mining industry based on the “Swiss-Cheese” model and construct a three-dimensional multi-granular structure model applied to the mining industry. To identify hazards of mining industry, a multi-layer hierarchical structure model and a system safety assessment model are established according to finite covering theorem. Then, the hazard identification is carried out based on the multi-layer hierarchical model and the risk matrix method, and a quantitative method is proposed to calculate the process indicators. Subsequently, the weighted grey relational analysis method is used for risk assessment on the driving system in mining industry. To improve the safety level of the driving system, the Hazard Identification-Assessment-Check-Action risk closed-loop management mode is used for risk management in the purpose of obtaining hazard rectification measures. Risk assessment is carried out again after risk rectification, and the safety level of the driving system can reach higher level. This research can provide guidance for the process safety improvement of industrial systems.

Evaluation of Hierarchical, Multi-Agent, Community-Based, Local Energy Markets Based on Key Performance Indicators

In recent years, local energy markets (LEMs) have been introduced to empower end-customers within energy communities at the distribution level of the power system, in order to be able to trade their energy locally in a competitive and fair environment. However, there is still some challenge with regard to the most efficient approach in organising the LEMs for the electricity exchange between consumers and prosumers while ensuring that they are responsible for their electricity-related choices, and concerning which LEM model is suitable for which prosumer or consumer type. This paper presents a hierarchical model for the organisation of agent-based local energy markets. According to the proposed model, prosumers and consumers are enabled to transact electricity within the local energy community and with the grid in a coordinated manner to ensure technical and economic benefits for the LEM’s agents. The model is implemented in a software tool called Grid Singularity Exchange (GSyE), and it is verified in a real German energy community case study. The simulation results demonstrate that trading electricity within the LEM offers economic and technical benefits compared to transacting with the up-stream grid. This can further lead to the decarbonization of the power system sector. Furthermore, we propose two models for LEMs consisting of multi-layer and single-layer hierarchical agent-based structures. According to our study, the multi-layer hierarchical model is more profitable for household prosumers as compared to trading within the single-layer hierarchical LEM. However, the single-layer LEM is more be beneficial for industrial prosumers.

Unsupervised lip segmentation based on quad-tree MRF framework in wavelet domain

In this paper, we propose a new extended method to implement lip segmentation. Based on a quad-tree structure (QTS) Markov random field (MRF) model under unsupervised situation, the proposed method achieves the lip segmentation in wavelet domain. Firstly, we set up a multi-layer hierarchical model, in which each pixel of every layer corresponds to the four nodes in quad-tree structure. Then the probability of a branch node can be calculated by using the probability of the previous branch node through the tree structure easily. Subsequently, a Markov random field derived from the model is obtained so that the segmentation problem is formulated as a labeling optimization problem in the framework of the maximum a posteriori Markov random field (MAP-MRF). Assuming that the pre-assigned cluster of data segments may overestimate the underlying fact, and leads to over-segmentation, we propose a variable-weight segmentation approach to improve the robustness of the segmentation. The experimental results show that this method has better segmentation accuracy than traditional methods.

Robust Multi-Layer Hierarchical Model for Digit Character Recognition

Although digit character recognition has got a significant improvement in recent years, it is still challenging to achieve satisfied result if the data contains an amount of distracting factors. This paper proposes a novel digit character recognition approach using a multi-layer hierarchical model, Hybrid Restricted Boltzmann Machines (HRBMs), which allows the learning architecture to be robust to background distracting factors. The insight behind the proposed model is that useful high-level features appear more frequently than distracting factors during learning, thus the high-level features can be decompose into hybrid hierarchical structures by using only small label information. In order to extract robust and compact features, a stochastic 0-1 layer is employed, which enables the model's hidden nodes to independently capture the useful character features during training. Experiments on the variations of Mixed National Institute of Standards and Technology (MNIST) dataset show that improvements of the multi-layer hierarchical model can be achieved by the proposed method. Finally, the paper shows the proposed technique which is used in a real-world application, where it is able to identify digit characters under various complex background images.

Lip segmentation and tracking under MAP-MRF framework with unknown segment number

This paper proposes a color lip segmentation method with unknown true segment number. Firstly, we build up a multi-layer hierarchical model, in which each layer corresponds to one segment cluster. Subsequently, a Markov random field derived from this model is obtained such that the segmentation problem is formulated as a labeling optimization problem under the maximum a posteriori Markov random field (MAP-MRF) framework. Suppose the pre-assigned number of segment clusters may over-estimate the ground truth, whereby leading to the over-segmentation. We present a rival penalized iterative algorithm capable of performing segment clusters and over-segmentation elimination simultaneously. Based upon this algorithm, we propose a lip segmentation and tracking scheme, featuring the robust performance to the estimate of the number of segment clusters. Experimental results show the efficacy of the proposed method in comparison with the existing counterparts.