In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

tions. Bootstrap has found many applications in engineering field, including artificial neural networks, biomedical engineering, environmental engineering, image processing, and radar and sonar signal processing. Basic concepts of the bootstrap are summarized in each section as a step-by-step algorithm for ease of implementation. Most of the applications are taken from the signal processing literature. The principles of the bootstrap are introduced in Chapter 2. Both the nonparametric and parametric bootstrap procedures are explained. Babu and Singh (1984) have demonstrated that in general, these two procedures behave similarly for pivotal (Studentized) statistics. The fact that the bootstrap is not the solution for all of the problems has been known to statistics community for a long time; however, this fact is rarely touched on in the manuscripts meant for practitioners. It was first observed by Babu (1984) that the bootstrap does not work in the infinite variance case. Bootstrap Techniques for Signal Processing explains the limitations of bootstrap method with an example. I especially liked the presentation style. The basic results are stated without proofs; however, the application of each result is presented as a simple step-by-step process, easy for nonstatisticians to follow. The bootstrap procedures, such as moving block bootstrap for dependent data, along with applications to autoregressive models and for estimation of power spectral density, are also presented in Chapter 2. Signal detection in the presence of noise is generally formulated as a testing of hypothesis problem. Chapter 3 introduces principles of bootstrap hypothesis testing. The topics are introduced with interesting real life examples. Flow charts, typical in engineering literature, are used to aid explanations of the bootstrap hypothesis testing procedures. The bootstrap leads to second-order correction due to pivoting; this improvement in the results due to pivoting is also explained. In the second part of Chapter 3, signal processing is treated as a regression problem. The performance of the bootstrap for matched filters as well as constant false-alarm rate matched filters is also illustrated. Chapters 2 and 3 focus on estimation problems. Chapter 4 introduces bootstrap methods used in model selection. Due to the inherent structure of the subject matter, this chapter may be difficult for nonstatisticians to follow. Chapter 5 is the most impressive chapter in the book, especially from the standpoint of statisticians. It provides real data bootstrap applications to illustrate the theory covered in the earlier chapters. These include applications to optimal sensor placement for knock detection and land-mine detection. The authors also provide a MATLAB toolbox comprising frequently used routines. Overall, this is a very useful handbook for engineers, especially those working in signal processing.

Probability and Random Processes

http://www.eis.mdx.ac.uk/staffpages/juanaugusto/CookAJ2009.pdf

Review: Ambient intelligence: Technologies, applications, and opportunities

Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes. It can be applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning. Moreover, we also investigate the application of these methods in reinforcement learning (RL). Then, we outline a few important applications of UQ methods. Finally, we briefly highlight the fundamental research challenges faced by UQ methods and discuss the future research directions in this field.

A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges

The role of big data in smart city

"This is the pre-peer reviewed version of the following article: Ramasamy Ramamurthy S, Roy N. Recent trends in machine learning for human activity recognition—A survey. WIREs Data Mining Knowl Discov. 2018;e1254. https://doi.org/10.1002/widm.1254, which has been published in final form at https://doi.org/10.1002/widm.1254. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving."

https://par.nsf.gov/servlets/purl/10087464

Recent trends in machine learning for human activity recognition—A survey

Activity 
recognition in smart environments is an evolving research problem due to the advancement and proliferation of sensing, monitoring and actuation technologies to make it possible for large scale and real deployment. While activities in smart home are interleaved, complex and volatile; the number of inhabitants in the environment is also dynamic. A key challenge in designing robust smart home activity recognition approaches is to exploit the users’ spatiotemporal behavior and location, focus on the availability of multitude of devices capable of providing different dimensions of information and fulfill the underpinning needs for scaling the system beyond a single user or a home environment. In this paper, we propose a hybrid approach for recognizing complex activities of daily living (ADL), that lie in between the two extremes of intensive use of body-worn sensors and the use of ambient sensors. Our approach harnesses the power of simple ambient sensors (e.g., motion sensors) to provide additional ‘hidden’ context (e.g., room-level location) of an individual, and then combines this context with smartphone-based sensing of micro-level postural/locomotive states. The major novelty is our focus on multi-inhabitant environments, where we show how the use of spatiotemporal constraints along with multitude of data sources can be used to significantly improve the accuracy and computational overhead of traditional activity recognition based approaches such as coupled-hidden Markov models. Experimental results on two separate smart home datasets demonstrate that this approach improves the accuracy of complex ADL classification by over 30 %, compared to pure smartphone-based solutions.

/pdf/ambient-and-smartphone-sensor-assisted-adl-recognition-in-4dlt9ekow7.pdf

Ambient and smartphone sensor assisted ADL recognition in multi-inhabitant smart environments

We investigate the problem of making human activity recognition (AR) scalable-i.e., allowing AR classifiers trained in one context to be readily adapted to a different contextual domain. This is important because AR technologies can achieve high accuracy if the classifiers are trained for a specific individual or device, but show significant degradation when the same classifier is applied context-e.g., to a different device located at a different on-body position. To allow such adaptation without requiring the onerous step of collecting large volumes of labeled training data in the target domain, we proposed a transductive transfer learning model that is specifically tuned to the properties of convolutional neural networks (CNNs). Our model, called HDCNN, assumes that the relative distribution of weights in the different CNN layers will remain invariant, as long as the set of activities being monitored does not change. Evaluation on real-world data shows that HDCNN is able to achieve high accuracy even without any labeled training data in the target domain, and offers even higher accuracy (significantly outperforming competitive shallow and deep classifiers) when even a modest amount of labeled training data is available.

https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=4979&context=sis_research

Scaling Human Activity Recognition via Deep Learning-based Domain Adaptation

A smart home aims at building intelligence automation with a goal to provide its inhabitants with maximum possible comfort, minimize the resource consumption and thus overall cost of maintaining the home. 'Context awareness' is perhaps the most salient feature of such an intelligent environment. Clearly, an inhabitant's mobility and activities play a significant role in defining his contexts in and around the home. Although there exists an optimal algorithm for location and activity tracking of a single inhabitant, the correlation and dependence between multiple inhabitants' contexts within the same environment make the location and activity tracking more challenging. In this paper, we first prove that the optimal location prediction across multiple inhabitants in smart homes is an NP-hard problem. Next, to capture the correlation and interactions of different inhabitants' movements (and hence activities), we develop a novel framework based on a game theoretic, Nash H-learning approach that attempts to minimize the joint location uncertainty. The framework achieves a Nash equilibrium such that no inhabitant is given preference over others. This results in more accurate prediction of contexts and better adaptive control of automated devices, leading to a mobility-aware resource (say, energy) management scheme in multi-inhabitant smart homes. Experimental results demonstrate that the proposed framework is capable of adaptively controlling a smart environment, thus reducing energy consumption and enhancing the comfort of the inhabitants.

Context-aware resource management in multi-inhabitant smart homes a Nash H-learning based approach

Summary form only given. This article realizes the vision of mobile grid computing by proposing a fair pricing strategy and an optimal, static job allocation scheme. Mobile devices has not yet been integrated into grid computing platforms mainly due to their inherent limitations in processing and storage capacity, power and bandwidth shortages. However, millions of laptops, PDAs and other mobile devices remain unused most of the time and this huge resource repository can be potentially utilized in the grid environment. Here, we propose a game theoretic pricing model, to address load balancing issues in mobile grids. In particular, by drawing upon the Nash bargaining solution (NBS), we show that we can obtain an unified framework for addressing such issues as network efficiency, fairness, utility maximization, and pricing. The advantage of this framework is that we have a precise mathematical characterization of the solutions and their properties. Our current endeavor characterizes a two-player alternating-offer bargaining game between the wireless access point (WAP) server and the mobile devices to determine the pricing strategy. This pricing strategy is then made use of to effectively distribute jobs to the mobile devices. Our job allocation scheme maximizes the revenue of the grid user, and yet is comparable to the overall system response time of other load balancing schemes.

Nirmalya Roy

Papers

Recent trends in machine learning for human activity recognition—A survey

Ambient and smartphone sensor assisted ADL recognition in multi-inhabitant smart environments

Scaling Human Activity Recognition via Deep Learning-based Domain Adaptation

Context-aware resource management in multi-inhabitant smart homes a Nash H-learning based approach

A game theory based pricing strategy for job allocation in mobile grids