Journal of Ambient Intelligence and Smart Environments

This paper’s main objective is to consolidate the knowledge on context in the realm of intelligent systems, systems that are aware of their context and can adapt their behavior accordingly. We provide an overview and analysis of 36 context models that are heterogeneous and scattered throughout multiple fields of research. In our analysis, we identify five shared context categories: social context, location, time, physical context, and user context. In addition, we compare the context models with the context elements considered in the discourse on intelligent systems and find that the models do not properly represent the identified set of 3,741 unique context elements. As a result, we propose a consolidation of the findings from the 36 context models and the 3,741 unique context elements. The analysis reveals that there is a long tail of context categories that are considered only sporadically in context models. However, particularly these context elements in the long tail may be necessary for improving intelligent systems’ context awareness.

The advent of Internet of Things (IoT) has shown a new direction of innovative research in agricultural domain. Being at nascent stage, IoT needs to be widely experimented so as to get widely applied in various agricultural applications. In this paper, I review various potential IoT applications, and the specific issues and challenges associated with IoT deployment for improved farming. To focus on the specific requirements the devices, and wireless communication technologies associated with IoT in agricultural and farming applications are analyzed comprehensively. Investigations are made on those sensor enabled IoT systems that provide intelligent and smart services towards smart agriculture. Various case studies are presented to explore the existing IoT based solutions performed by various organizations and individuals and categories according to their deployment parameters. Related difficulties in these solutions, while identifying the factors for improvement and future road map of work using the IoT are also highlighted.

Today’s ubiquitous presence of sensors provides a large amount of data which can be analyzed to study human behavior. The last few years saw the birth and diffusion of a new class of sensing systems: smartphones. With a diverse range of embedded sensors, smartphones have now become a commodity, and their capabilities can be leveraged to collect data to be used in different domains, including study of human behavior. This paper presents a review of past research works where mobile phone sensors are used to detect various aspects characterizing human behavior. Methods for automatic recognition of the placement of a mobile phone are first described as useful tools to improve the accuracy of sensing systems. Activity detection, at different abstraction levels from basic body motions to high-level activities, is then surveyed extensively, including studies focusing on detection of transportation mode and characterization of health-related activities such as physical exercise and sleeping. Other related works reviewed in this paper are continuous sensing systems for lifelogging applications, techniques to identify the environment where a user is located, and behavior modeling methods that allow extracting common patterns from behavioral data, studying psychological profiles and predicting future behaviors.

This article presents a Building Information Model (BIM), which describes the topology, geometry, and semantics of buildings; user preferences; and status of sensors deployed in the building. The aim is to propose an approach for developing a context-aware indoor navigation system, which assists blind and visually impaired people in unfamiliar large public buildings with complex horizontal and vertical connectivity. The proposed building data model aims to overcome the drawbacks of existing BIM-based Indoor Navigation Systems (INS). The innovation aspects of the proposed data model can be summarized as follows: 1) Abstract description of the hierarchy of building elements; 2) BIM is focused on indoor navigation. It allows one to extract information about the topology of a specified part of the building, which is used by an algorithm for coarse-to-fine path finding; 3) Provides rich semantic information on all building elements, objects and users located in the building; and 4) Provides all necessary information for obstacle (fixed and movable) avoidance.

This work concerns the development of low-cost ambient systems for helping elderly to stay at home. Depth cameras allow a real-time analysis of the displacement of the person. We show that it is possible to recognize the activity of the person and to measure gait parameters from the analysis of simple features extracted from depth images. Activity recognition is based on Hidden Markov Models and performs fall detection. When a person is walking, the analysis of the trajectory of her centre of mass allows to measure gait parameters that can then be used for frailty evaluation. We show that the proposed models are robust enough for activity classification, and that gait parameters measurement is accurate. We believe that such a system could be installed in the home of the elderly, while respecting privacy, since it relies on a local processing of depth images. Our system would be able to provide daily information on the person’s activity, the evolution of her gait parameters, and her habits, information that is useful for securing her and evaluating her frailty.

This work proposes a key pose based intelligent system for recognition of human interactions from video streams. In addition to interaction recognition, the task is useful for some of other applications like content based video retrieval. The main idea is to use the shape of the bilateral silhouette between the persons and analyze it using shape context descriptor, which is one of the popular shape descriptors in object recognition and matching tasks. At first, a dictionary from random samples for the whole classes is collected and the bilateral silhouette image is extracted for all samples and classes to train the low level classifier named frame classifier. Then, the frames of test sequence are compared with these samples and labeled as one class using frame classifier. Finally, a high level classifier is used to categorize the interaction as a function of predefined labels of frame sequence. We call this classifier as the sequence classifier. Because of probable errors in foreground extraction, some faults may occur in frame classification. Moreover, each interaction sequence is composed of two types of frames, which contain related or unrelated information about interaction. To tackle the problem, a normalized histogram of the frame labels is used as the action descriptor, which is robust against misclassification of some frames. This histogram is applied to a sequence classifier like random decision forests (RDF), Probabilistic Neural Network (PNN) or Support Vector Machine (SVM) to perform interaction recognition. Experimental results on SBU and UT-interaction dataset emphasize the privileged performance of the proposed method.

In recent years Near Field Communication (NFC) technology has undergone a rapid evolution, In the tourism sector this technology enables any user equipped with a smart phone to interact with the surrounding objects and have access to in-formation and related services. In this paper, we present a fully configurable system for tourist services. The proposal contains a database and multimedia services that can be presented and personalized on mobile devices using dynamic websites. Users may use NFC technology to interact with smart objects, augmented with NFC tags to store information and services that will be customized according to user interaction based on content and services defined in the metamodel. Associating metamodels to objects, solutions can be applied to any tourism sectors.

WiFi-enabled buses of the Public Transportation System (PTS) may be employed as the backbone of a metropolitan delay tolerant network that exploits ad hoc connectivity and predictable bus mobility to deliver non-real time information. In this paper, we discuss and study the feasibility of a Mobile Delay Tolerant Networking (MDTN) solution deployed over an actual PTS to provide service opportunistic connectivity. Our solution follows an opportunistic carrier-based approach where buses act as data collectors for users’ requests involving Internet access. Obtained results demonstrate that MDTN represents a viable approach able to provide delay-tolerant service access. To support our claim, we have carried out a set of simulations considering MDTN coupled with state of the art routing protocols deployed over a near-to-real scenario: the PTS of Milan, Italy.