Neural network analysis of MINERVA scene image benchmark

Scene analysis is an important area of research with the aim of identifying objects and their relationships in natural scenes. MINERVA benchmark has been recently introduced in this area for testing different image processing and classification schemes. In this paper we present results on the classification of eight natural objects in the complete set of 448 natural images using neural networks. An exhaustive set of experiments with this benchmark has been conducted using four different segmentation methods and five texture-based feature extraction methods. The results in this paper show the performance of a neural network classifier on a tenfold cross-validation task. On the basis of the results produced, we are able to rank how well different image segmentation algorithms are suited to the task of region of interest identification in these images, and we also see how well texture extraction algorithms rank on the basis of classification results.     

Adaptive FH optimization in MEC-assisted 5G environments

Photonic Network Communications - To address the limitations of current radio access networks (RANs), centralized RANs adopting the concept of flexible splits of the BBU functions between radio...     

Multivariable Regulator Approach to Sewer Network Flow Control

The problem of optimal water distribution to a range of retention reservoirs in an urban sewer network during rainfall events is considered in this paper. The goal of the control actions is the minimization of overflows and eventually the reduction of their polluting impact on receiving waters. A multilayer control structure consisting of an adaptation, an optimization, and a direct control layer, is proposed for the solution of this complex control problem. Several approaches have been proposed with regard to the optimization layer. This paper proposes a linear multivariable feedback regulator that is developed via a systematic design procedure, including a simplified model, a quadratic minimization criterion, and subsequent application of the linear-quadratic optimization method. Inflow predictions are accommodated through feedforward terms in the control law. The control design guidelines facilitate a quick and efficient regulator design for a broad class of sewer network control problems. Simulation tests for a particular large network and various inflow scenarios indicate that significant overflow reductions are achieved by the application of the linear-quadratic regulator.     

Hierarchical clustering of mixed-type data based on barycentric coding

Behaviormetrika - Clustering of mixed-type datasets can be a particularly challenging task as it requires taking into account the associations between variables with different level of measurement,...     

Modeling users’ acceptance of mobile services

The success of mobile services adoption hinges on their ability to cover user needs and attract consumer interest. The extant literature focuses on understanding the factors that might affect consumers’ actual adoption of such services through their effect on behavioral intention; these studies are mostly based on behavioral intention theories, such as Technology Acceptance Model, Diffusion of Innovation and Unified Theory of Acceptance and Use of Technology. In this work, new theoretical constructs are combined with existing evidence in order to extend the Technology Acceptance Model (TAM) as it was initially established by Davis and later further enriched by other researchers. The proposed model includes behavioral intention, perceived usefulness, perceived ease of use, trust, innovativeness, relationship drivers, and functionality. Within this approach, relationship drivers introduce a marketing perspective to the original models of technology adoption by building emotional connections between the users and the mobile services. The hypothesized model is empirically tested using data collected from a survey on m-commerce consumers. Structural Equation Modelling (SEM) was used to evaluate the causal model and Confirmatory Factor Analysis (CFA) was performed to examine the reliability and validity of the measurement model. It is briefly concluded that behavioral intention is directly affected by perceived usefulness, innovativeness and relationship drivers; the findings provide interesting insights and useful hints to practitioners and researchers.     

Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer

Deep learning has catalysed progress in tasks such as face recognition and analysis, leading to a quick integration of technological solutions in multiple layers of our society. While such systems have proven to be accurate by standard evaluation metrics and benchmarks, a surge of work has recently exposed the demographic bias that such algorithms exhibit–highlighting that accuracy does not entail fairness. Clearly, deploying biased systems under real-world settings can have grave consequences for affected populations. Indeed, learning methods are prone to inheriting, or even amplifying the bias present in a training set, manifested by uneven representation across demographic groups. In facial datasets, this particularly relates to attributes such as skin tone, gender, and age. In this work, we address the problem of mitigating bias in facial datasets by data augmentation. We propose a multi-attribute framework that can successfully transfer complex, multi-scale facial patterns even if these belong to underrepresented groups in the training set. This is achieved by relaxing the rigid dependence on a single attribute label, and further introducing a tensor-based mixing structure that captures multiplicative interactions between attributes in a multilinear fashion. We evaluate our method with an extensive set of qualitative and quantitative experiments on several datasets, with rigorous comparisons to state-of-the-art methods. We find that the proposed framework can successfully mitigate dataset bias, as evinced by extensive evaluations on established diversity metrics, while significantly improving fairness metrics such as equality of opportunity.

     

Active Foreground Region Extraction and Tracking for Sports Video Annotation

Automatic video segmentation plays a vital role in sports videos annotation. This paper presents a fully automatic and computationally efficient algorithm for analysis of sports videos. Various methods of automatic shot boundary detection have been proposed to perform automatic video segmentation. These investigations mainly concentrate on detecting fades and dissolves for fast processing of the entire video scene without providing any additional feedback on object relativity within the shots. The goal of the proposed method is to identify regions that perform certain activities in a scene. The model uses some low-level feature video processing algorithms to extract the shot boundaries from a video scene and to identify dominant colours within these boundaries. An object classification method is used for clustering the seed distributions of the dominant colours to homogeneous regions. Using a simple tracking method a classification of these regions to active or static is performed. The efficiency of the proposed framework is demonstrated over a standard video benchmark with numerous types of sport events and the experimental results show that our algorithm can be used with high accuracy for automatic annotation of active regions for sport videos.