A Hierarchical Decision-Making Framework in Social Networks for Efficient Disaster Management

One of the major challenges faced by the current society is developing disaster management strategies to minimize the effects of catastrophic events. Disaster planning and strategy development phases of this urgency require larger amounts of cooperation among communities or individuals in society. Social networks have also been playing a crucial role in the establishment of efficient disaster management planning. This article proposes a hierarchical decision-making framework that would assist in analyzing two imperative information flow processes (innovation diffusion and opinion formation) in social networks under the consideration of community detection. The proposed framework was proven to capture the heterogeneity of individuals using cognitive behavior models and evaluate its impact on diffusion speed and opinion convergence. Moreover, the framework demonstrated the evolution of communities based on their inter-and intracommunication. The simulation results with real social network data suggest that the model can aid in establishing an efficient disaster management policy using social sensing and delivery.

Urbanization in the Middle Niger of Mali

When the tell site of Jenne-jeno was brought to light in the vast floodplain of the southern Middle Niger of Mali, archaeologists had to question certain expectations about just what constitutes an ancient city. The city was certainly too early (3rd century bce rather than the expected late first millennium ce) and Jenne-jeno did not conform to the standard city form (a mosaic of satellites rather than the expected agglomeration). But it was the persistent lack of evidence of a centralized ruler, social strata of elites, and of the hierarchical decision-making mechanisms of the state that set this urban landscape so at odds with then prevalent urban theory. The seventy apparently contemporaneous hamlets and specialists’ occupation mounds surrounding Jenne-jeno form the Jenne-jeno Urban Complex. It is a classic example of African originality in evolving urban landscapes. In place of the top-down, often despotic state control as the organizing principle of the city, here there is a classic city without citadel—and thus heterarchy (authority and power relations arrayed horizontally) instead of a social and political hierarchy at the heart of the city can be posited. The search for the pre-Jenne-jeno antecedents has taken a newer generation of archaeologists to look at “pre-urban” landscapes in other, now-dry parts of the Middle Niger deep in the northern. Sahel and Sahara. Back to the second millennium bce, the single site can be found to be the exception; clustering had roots deep in time.

Deep convolutional tree-inspired network: a decision-tree-structured neural network for hierarchical fault diagnosis of bearings

The fault diagnosis of bearings is crucial in ensuring the reliability of rotating machinery. Deep neural networks have provided unprecedented opportunities to condition monitoring from a new perspective due to the powerful ability in learning fault-related knowledge. However, the inexplicability and low generalization ability of fault diagnosis models still bar them from the application. To address this issue, this paper explores a decision-tree-structured neural network, that is, the deep convolutional tree-inspired network (DCTN), for the hierarchical fault diagnosis of bearings. The proposed model effectively integrates the advantages of convolutional neural network (CNN) and decision tree methods by rebuilding the output decision layer of CNN according to the hierarchical structural characteristics of the decision tree, which is by no means a simple combination of the two models. The proposed DCTN model has unique advantages in 1) the hierarchical structure that can support more accuracy and comprehensive fault diagnosis, 2) the better interpretability of the model output with hierarchical decision making, and 3) more powerful generalization capabilities for the samples across fault severities. The multiclass fault diagnosis case and cross-severity fault diagnosis case are executed on a multicondition aeronautical bearing test rig. Experimental results can fully demonstrate the feasibility and superiority of the proposed method.

Monkey Plays Pac-Man with Compositional Strategies and Hierarchical Decision-making

Humans can often handle daunting tasks with ease by developing a set of strategies to reduce decision making into simpler problems. The ability to use heuristic strategies demands an advanced level of intelligence and has not been demonstrated in animals. Here, we trained macaque monkeys to play the classic video game Pac-Man. The monkeys' decision-making may be described with a strategy-based hierarchical decision-making model with over 90% accuracy. The model reveals that the monkeys adopted the take-the-best heuristic by using one dominating strategy for their decision-making at a time and formed compound strategies by assembling the basis strategies to handle particular game situations. With the model, the computationally complex but fully quantifiable Pac-Man behavior paradigm provides a new approach to understanding animals' advanced cognition.

On the Identifiability of Hierarchical Decision Models

Interpretability is a desirable property for machine learning and decision models, particularly in the context of safety-critical applications. Another most desirable property of the sought model is to be unique or {\em identifiable} in the considered class of models: the fact that the same functional dependency can be represented by a number of syntactically different models adversely affects the model interpretability, and prevents the expert from easily checking their validity. This paper focuses on the Choquet integral (CI) models and their hierarchical extensions (HCI). HCIs aim to support expert decision making, by gradually aggregating preferences based on criteria; they are widely used in multi-criteria decision aiding {and are receiving interest from the} Machine Learning {community}, as they preserve the high readability of CIs while efficiently scaling up w.r.t. the number of criteria. The main contribution is to establish the identifiability property of HCI under mild conditions: two HCIs implementing the same aggregation function on the criteria space necessarily have the same hierarchical structure and aggregation parameters. The identifiability property holds even when the marginal utility functions are learned from the data. This makes the class of HCI models a most appropriate choice in domains where the model interpretability and reliability are of primary concern.