Recognising and monitoring high-level behaviours in complex spatial environments

The recognition of activities from sensory data is important in advanced surveillance systems to enable prediction of high-level goals and intentions of the target under surveillance. The problem is complicated by sensory noise and complex activity spanning large spatial and temporal extents. This paper presents a system for recognising high-level human activities from multi-camera video data in complex spatial environments. The Abstract Hidden Markov mEmory Model (AHMEM) is used to deal with noise and scalability The AHMEM is an extension of the Abstract Hidden Markov Model (AHMM) that allows us to represent a richer class of both state-dependent and context-free behaviours. The model also supports integration with low-level sensory models and efficient probabilistic inference. We present experimental results showing the ability of the system to perform real-time monitoring and recognition of complex behaviours of people from observing their trajectories within a real, complex indoor environment.

Hierarchical monitoring of people's behaviors in complex environments using multiple cameras

We present a distributed, surveillance system that works in large and complex indoor environments. To track and recognize behaviors of people, we propose the use of the Abstract Hidden Markov Model (AHMM), which can be considered as an extension of the Hidden Markov Model (HMM), where the single Markov chain in the HMM is replaced by a hierarchy of Markov policies. In this policy hierarchy, each behavior can be represented as a policy at the corresponding level of abstraction. The noisy observations are handled in the same way as an HMM and an efficient Rao-Blackwellised particle filter method is used to compute the probabilities of the current policy at different levels of the hierarchy The novelty of the paper lies in the implementation of a scalable framework in the context of both the scale of behaviors and the size of the environment, making it ideal for distributed surveillance. The results of the system demonstrate the ability to answer queries about people's behaviors at different levels of details using multiple cameras in a large and complex indoor environment.

A mutation-based evolving neural network model and its application to condition monitoring

Data analysis using intelligent systems is a key solution to many industrial problems. In this paper, a mutation-based evolving artificial neural network, which is based on an integration of the Fuzzy ARTMAP (FAM) neural network and evolutionary programming (EP), is proposed. The proposed FAMEP model is applied to detect and classify possible faults from a number of sensory signals of a circulating water system in a power generation plant. The efficiency of FAM-EP is assessed and compared with that of the original FAM network in terms of classification accuracy as well as network complexity. In addition, the bootstrap method is used to quantify the performance statistically. The results positively demonstrate the usefulness of FAM-EP in tackling data classification problems.

Mobile phone sensing systems : a survey

Mobile phone sensing is an emerging area of interest for researchers as smart phones are becoming the core communication device in people's everyday lives. Sensor enabled mobile phones or smart phones are hovering to be at the center of a next revolution in social networks, green applications, global environmental monitoring, personal and community healthcare, sensor augmented gaming, virtual reality and smart transportation systems. More and more organizations and people are discovering how mobile phones can be used for social impact, including how to use mobile technology for environmental protection, sensing, and to leverage just-in-time information to make our movements and actions more environmentally friendly. In this paper we have described comprehensively all those systems which are using smart phones and mobile phone sensors for humans good will and better human phone interaction.

Monitoring the impacts of trade agreements on food environments

The liberalization of international trade and foreign direct investment through multilateral, regional and bilateral agreements has had profound implications for the structure and nature of food systems, and therefore, for the availability, nutritional quality, accessibility, price and promotion of foods in different locations. Public health attention has only relatively recently turned to the links between trade and investment agreements, diets and health, and there is currently no systematic monitoring of this area. This paper reviews the available evidence on the links between trade agreements, food environments and diets from an obesity and non-communicable disease (NCD) perspective. Based on the key issues identified through the review, the paper outlines an approach for monitoring the potential impact of trade agreements on food environments and obesity/NCD risks. The proposed monitoring approach encompasses a set of guiding principles, recommended procedures for data collection and analysis, and quantifiable 'minimal', 'expanded' and 'optimal' measurement indicators to be tailored to national priorities, capacity and resources. Formal risk assessment processes of existing and evolving trade and investment agreements, which focus on their impacts on food environments will help inform the development of healthy trade policy, strengthen domestic nutrition and health policy space and ultimately protect population nutrition.

Cloud-based non-invasive tele-rehabilitation exercise monitoring

Exercise based rehabilitation plays a vital role in the recovery of various conditions, such as stroke, Parkinson’s disease (PD), chronic pain, and so on. Recently, telerehabilitation has become increasingly popular quantitative nature in assessments particularly for systematic monitoring of progress as well as cost saving for the patients as well as for the health care sector at large. However, challenges do exist in implementing a distributed bio-feedback in a cost-effective and efficient way. In this paper, we present the associated conceptual framework of cloud-based tele-rehabilitation system employing affordable non-invasive Microsoft Kinect® allowing patients to perform rehabilitation exercises in non-clinical setting such as home environments without loosing the quality of patients care. More importantly, different from existing tele-rehabilitation systems, our system not only measures whether patients can perform rehabilitation tasks, but also how well they can finish the tasks. Preliminary experiments validate its potential in training healthy subject to perform exercise motions emulating the physical rehabilitation process.

Condition monitoring of induction motors : A review and an application of an ensemble of hybrid intelligent models

In this paper, a review on condition monitoring of induction motors is first presented. Then, an ensemble of hybrid intelligent models that is useful for condition monitoring of induction motors is proposed. The review covers two parts, i.e.; (i) a total of nine commonly used condition monitoring methods of induction motors; and (ii) intelligent learning models for condition monitoring of induction motors subject to single and multiple input signals. Based on the review findings, the Motor Current Signature Analysis (MCSA) method is selected for this study owing to its online, non-invasive properties and its requirement of only single input source; therefore leading to a cost-effective condition monitoring method. A hybrid intelligent model that consists of the Fuzzy Min-Max (FMM) neural network and the Random Forest (RF) model comprising an ensemble of Classification and Regression Trees is developed. The majority voting scheme is used to combine the predictions produced by the resulting FMM-RF ensemble (or FMM-RFE) members. A benchmark problem is first deployed to evaluate the usefulness of the FMM-RFE model. Then, the model is applied to condition monitoring of induction motors using a set of real data samples. Specifically, the stator current signals of induction motors are obtained using the MCSA method. The signals are processed to produce a set of harmonic-based features for classification using the FMM-RFE model. The experimental results show good performances in both noise-free and noisy environments. More importantly, a set of explanatory rules in the form of a decision tree can be extracted from the FMM-RFE model to justify its predictions. The outcomes ascertain the effectiveness of the proposed FMM-RFE model in undertaking condition monitoring tasks, especially for induction motors, under different environments. © 2014 Elsevier Ltd. All rights reserved.

Reduced order functional observers with application to partial state estimation of linear systems with input delay

Reduced order multi-functional observer design for multi-input multi-utput (MIMO) linear time-invariant (LTI) systems with constant delayed inputs is studied. This research is useful in the input estimation of LTI systems with actuator delay, as well as system monitoring and fault detection of these systems. Two approaches for designing an asymptotically stable functional observer for the system are proposed: delay-dependent and delay-free. The delay-dependent observer is infinite-dimensional, while the delay-free structure is finite-dimensional. Moreover, since the delay-free observer does not require any information on the time delay, it is more practical in real applications. However, the delay-dependent observer contains less restrictive assumptions and covers more variety of systems. The proposed observer design schemes are novel, simple to implement, and have improved numerical features compared to some of the other available approaches to design (unknown-input) functional observers. In addition, the proposed observers usually possess lower order than ordinary Luenberger observers, and the design schemes do not need the observability or detectability requirements of the system. The necessary and sufficient conditions of the existence of an asymptoticobserver in each scenario are explored. The extensions of the proposed observers to systems with multiple delayed-inputs are also discussed. Several numerical examples and simulation results are employed to support our theories.

Strengthening of accountability systems to create healthy food environments and reduce global obesity

To achieve WHO's target to halt the rise in obesity and diabetes, dramatic actions are needed to improve the healthiness of food environments. Substantial debate surrounds who is responsible for delivering effective actions and what, specifically, these actions should entail. Arguments are often reduced to a debate between individual and collective responsibilities, and between hard regulatory or fiscal interventions and soft voluntary, education-based approaches. Genuine progress lies beyond the impasse of these entrenched dichotomies. We argue for a strengthening of accountability systems across all actors to substantially improve performance on obesity reduction. In view of the industry opposition and government reluctance to regulate for healthier food environments, quasiregulatory approaches might achieve progress. A four step accountability framework (take the account, share the account, hold to account, and respond to the account) is proposed. The framework identifies multiple levers for change, including quasiregulatory and other approaches that involve government-specified and government-monitored progress of private sector performance, government procurement mechanisms, improved transparency, monitoring of actions, and management of conflicts of interest. Strengthened accountability systems would support government leadership and stewardship, constrain the influence of private sector actors with major conflicts of interest on public policy development, and reinforce the engagement of civil society in creating demand for healthy food environments and in monitoring progress towards obesity action objectives.

A modified fuzzy min-max neural network for data clustering and its application to power quality monitoring

When no prior knowledge is available, clustering is a useful technique for categorizing data into meaningful groups or clusters. In this paper, a modified fuzzy min-max (MFMM) clustering neural network is proposed. Its efficacy for tackling power quality monitoring tasks is demonstrated. A literature review on various clustering techniques is first presented. To evaluate the proposed MFMM model, a performance comparison study using benchmark data sets pertaining to clustering problems is conducted. The results obtained are comparable with those reported in the literature. Then, a real-world case study on power quality monitoring tasks is performed. The results are compared with those from the fuzzy c-means and k-means clustering methods. The experimental outcome positively indicates the potential of MFMM in undertaking data clustering tasks and its applicability to the power systems domain.

Enabling cloud computing in emergency management systems

Emergencies, including both natural and man - made disasters, increasingly pose an immediate threat to life, health, property, and environment. For example, Hurricane Katrina, the deadliest and most destructive Atlantic tropical cyclone of the 2005 Atlantic hurricane season, led to at least 1,883 people's death and an estimated loss of - 108 billion property. To reduce the damage by emergencies, a wide range of cutting-edge technologies on medicine and information are used in all phases of emergency management. This article proposes a cloud-based emergency management system for environmental and structural monitoring that utilizes the powerful computing and storage capability of datacenters to analyze the mass data collected by the wireless intelligent sensor network deployed in civil environment. The system also benefits from smartphone and social network platform to setup the spatial and population models, which enables faster evacuation and better resource allocation.