Multi-view human movement recognition based on fuzzy distances and linear discriminant analysis

In this paper, a novel multi-view human movement recognition method is presented. A novel representation of multi-view human movement videos is proposed that is based on learning basic multi-view human movement primitives, called multi-view dynemes. The movement video is represented in a new feature space (called dyneme space) using these multi-view dynemes, thus producing a time invariant multi-view movement representation. Fuzzy distances from the multi-view dynemes are used to represent the human body postures in the dyneme space. Three variants of Linear Discriminant Analysis (LDA) are evaluated to achieve a discriminant movement representation in a low dimensionality space. The view identification problem is solved either by using a circular block shift procedure followed by the evaluation of the minimum Euclidean distance from any dyneme, or by exploiting the circular shift invariance property of the Discrete Fourier Transform (DFT). The discriminant movement representation combined with camera viewpoint identification and a nearest centroid classification step leads to a high human movement classification accuracy.     

Dynamic action recognition based on dynemes and Extreme Learning Machine

In this paper, we propose a novel method that performs dynamic action classification by exploiting the effectiveness of the Extreme Learning Machine (ELM) algorithm for single hidden layer feedforward neural networks training. It involves data grouping and ELM based data projection in multiple levels. Given a test action instance, a neural network is trained by using labeled action instances forming the groups that reside to the test sample’s neighborhood. The action instances involved in this procedure are, subsequently, mapped to a new feature space, determined by the trained network outputs. This procedure is performed multiple times, which are determined by the test action instance at hand, until only a single class is retained. Experimental results denote the effectiveness of the dynamic classification approach, compared to the static one, as well as the effectiveness of the ELM in the proposed dynamic classification setting.     

Sustainable energy planning by using multi-criteria analysis application in the island of Crete

The sustainable energy planning includes a variety of objectives, as the decision-making is directly related to the processes of analysis and management of different types of information (technological, environmental, economic and social). Very often, the traditional evaluation methods, such as the cost-benefit analysis and macro-economic indicators, are not sufficient to integrate all the elements included in an environmentally thorough energy plan. On the contrary the multiple criteria methods provide a tool, which is more appropriate to assemble and to handle a wide range of variables that is evaluated in different ways and thus offer valid decision support.     

Visualising deep network time-series representations

Neural Computing and Applications - Despite the popularisation of machine learning models, more often than not, they still operate as black boxes with no insight into what is happening inside the...     

Double auction mechanisms for resource allocation in autonomous networks

Auction mechanisms are used for allocating a resource among multiple agents with the objective to maximize social welfare. What makes auctions attractive is that they are agnostic to utility functions of agents. Auctions involve a bidding method by agents-buyers, which is then mapped by a central controller to an allocation and a payment for each agent. In autonomic networks comprising self-interested nodes with different needs and utility functions, each entity possesses some resource and can engage in transactions with others to achieve its needs. In fact, efficient network operation relies on node synergy and multi-lateral resource trading. Nodes face the dilemma of devoting their limited resource to their own benefit versus acting altruistically and anticipating to be aided in the future. Wireless ad-hoc networks, peer-to-peer networks and disruption-tolerant networks are instances of autonomic networks where the challenges above arise and the traded resource is energy, bandwidth and storage space respectively. Clearly, the decentralized complex node interactions and the double node role as resource provider and consumer amidst resource constraints cannot be addressed by single-sided auctions and even more by mechanisms with a central controller. We introduce a double-sided auction market framework to address the challenges above. Each node announces one bid for buying and one for selling the resource.We prove that there exist bidding and charging strategies that maximize social welfare and we explicitly compute them. We generalize our result to a generic network objective. Nodes are induced to follow these strategies, otherwise they are isolated by the network. Furthermore, we propose a decentralized realization of the double-sided auction with lightweight network feedback. Finally, we introduce a pricing method which does not need a charging infrastructure. Simulation results verify the desirable properties of our approach.     

Parity-based cumulative fairness-aware boosting

Data-driven AI systems can lead to discrimination on the basis of protected attributes like gender or race. One cause for this is the encoded societal biases in the training data (e.g., under-representation of females in the tech workforce), which is aggravated in the presence of unbalanced class distributions (e.g., when “hired” is the minority class in a hiring application). State-of-the-art fairness-aware machine learning approaches focus on preserving the overall classification accuracy while mitigating discrimination. In the presence of class-imbalance, such methods may further aggravate the problem of discrimination by denying an already underrepresented group (e.g., females) the fundamental rights of equal social privileges (e.g., equal access to employment). To this end, we propose AdaFair, a fairness-aware boosting ensemble that changes the data distribution at each round, taking into account not only the class errors but also the fairness-related performance of the model defined cumulatively based on the partial ensemble. Except for the in-training boosting of the group discriminated over each round, AdaFair directly tackles imbalance during the post-training phase by optimizing the number of ensemble learners for balanced error performance. AdaFair can facilitate different parity-based fairness notions and mitigate effectively discriminatory outcomes.

     

Tracking the history and evolution of entities: entity-centric temporal analysis of large social media archives

International Journal on Digital Libraries - How did the popularity of the Greek Prime Minister evolve in 2015? How did the predominant sentiment about him vary during that period? Were there any...     

Forecasting Financial Time Series Using Robust Deep Adaptive Input Normalization

Deep Learning provided powerful tools for forecasting financial time series data. However, despite the success of these approaches on many challenging financial forecasting tasks, it is not always straightforward to employ DL-based approaches for highly volatile and non-stationary time financial series. To this end, in this paper, an adaptive input normalization layer that can learn to identify the distribution from which the input data were generated and then apply the most appropriate normalization scheme is proposed. This allows for promptly adapting the input to the subsequent DL model, which can be especially important, given recent findings that hint at the existence of critical learning periods in neural networks. Furthermore, the proposed method operates on a sliding window over the time series allowing for overcoming non-stationary issues that often arise. It is worth noting that the main difference with existing approaches is that the proposed method does not just learn to perform static normalization, e.g., using a fixed set of parameters, but instead it adaptively calculates the most appropriate normalization parameters, significantly improving the robustness of the proposed approach when distribution shifts occur. The effectiveness of the proposed formulation is verified using extensive experiments on three challenging financial time-series datasets.