No abstract

In this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/ body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).

Everyday life of the elderly and impaired population living in smart homes is challenging because of possible accidents that may occur due to daily activities. In such activities, persons often lean over (to reach something) and, if they not cautious, are prone to falling. To identify fall incidents, which could stochastically cause serious injuries or even death, we propose specific temporal inference models; namely, CM-I and CM-II. These models can infer a fall incident based on classification methods by exploiting wearable Internet of Things (IoT) altimeter sensors adopted by seniors. We analyzed real and synthetic data of fall and lean over incidents to test the proposed models. The results are promising for incorporating such inference models to assist healthcare for fall verification of seniors in smart homes. Specifically, the CM-II model achieved a prediction accuracy of 0.98, which is the highest accuracy when compared to other models in the literature under the McNemar’s test criterion. These models could be incorporated in wearable IoT devices to provide early warning and prediction of fall incidents to clinical doctors.

No abstract

The population of the Earth is moving towards urban areas forming smart cities (SCs). Waste management is a component of SCs. We consider a SC which contains a distribution of waste bins and a distribution of waste trucks located in the SC sectors. Bins and trucks are enabled with Internet of Things (IoT) sensors and actuators. Prior approaches focus mainly on the dynamic scheduling and routing issues emerging from IoT-enabled waste management. However, less research has been done in the area of the stochastic reassignment process during the four seasons of the year over a period of two years. In this paper we aim to stochastically reassign trucks to collect waste from bins through time. We treat this problem with a multi-agent system for stochastic analyses.

No abstract

Purpose As regards the assessment of the market values of properties that compose real estate portfolios, the purpose of this paper is to propose and test an automated valuation model. In particular, the method defined allows for providing for objective, reliable and “quick” valuations of the assets in the phases of periodic reviews of the property values. Design/methodology/approach Aiming at both predictive and interpretative purposes, the method, based on multi-objective genetic algorithms to search those model expressions that simultaneously maximize the accuracy of the data and the parsimony of the mathematical functions, is applied to a sample data of office properties characterized by medium and large size, located in the city of Milan (Italy) and sold in the period between 2004 and 2015. Findings The model obtained could be an integration of the canonical methodologies (market approach, income approach, cost approach) implemented in the assessment of the market values of properties, so as to provide an additional tool to verify the results. In particular, the inclusion of economic variables in the model is consistent with the need to reiterate the valuations, contextualizing them to the locational characteristics and to the current property cycle phase in the specific area. Practical implications The model can be applied by all the operators involved in the periodic reviews of the values of property portfolios: from real estate funds’ insiders, in order to monitor the values obtained through the canonical approaches, to the public institutions, such as the revenue agencies, in order to ensure the fair payment of the taxes through the updating values of the properties according to the actual and current market trends. Originality/value The method proposed can be a valid support for all public and private entities that hold significant property assets and that, for various reasons (periodic reviews of the balance sheets, sales, enhancement, investment, etc.), require cyclical updated values of the properties. The automated valuation model developed can be used for the assessment of “comparison” values with the estimates values obtained by other assessment techniques, in order to ensure a further monitoring tool of the results from the subjects involved.

This paper presents an efficient technique for unsupervised content-based segmentation in stereoscopic video sequences by appropriately combined different content descriptors in a hierarchical framework. Three main modules are involved in the proposed scheme; extraction of reliable depth information, image partition into color and depth regions and a constrained fusion algorithm of color segments using information derived from the depth map. In the first module, each stereo pair is analyzed and the disparity field and depth map are estimated. Occlusion detection and compensation are also applied for improving the depth map estimation. In the following phase, color and depth regions are created using a novel complexity-reducing multiresolution implementation of the Recursive Shortest Spanning Tree algorithm (M-RSST). While depth segments provide a coarse representation of the image content, color regions describe very accurately object boundaries. For this reason, in the final phase, a new segmentation fusion algorithm is employed which projects color segments onto depth segments. Experimental results are presented which exhibit the efficiency of the proposed scheme as content-based descriptor, even in case of images with complicated visual content.