http://www.computer.org/multimedia IEEE MultiMedia covers technical information on a broad range of issues in multimedia systems and applications. Typical topics include hardware and software for media compression, media storage/transport, workstation support for multimedia, data modeling, and abstractions to embed multimedia in application programs. The information consists of articles, product reviews, new product descriptions, book reviews and announcements of conferences and workshops. Articles discuss research as well as advanced practice in hardware/software and span the range from theory to working systems. en-us Wed, 4 Jan 2012 11:00:01 GMT http://csdl.computer.org/common/images/logos/multimedia.gif List of recently published journal articles http://www.computer.org/multimedia http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.74 An overview on recent developments in the field of audio authentication is given in this paper. We first show a block-diagram of an audio generation, compression, transmission and playback system with forgery detection techniques applied at each stage. We then examine basic audio authentication techniques such as the listening test and spectrogram based techniques for preliminary audio analysis. These are followed by a description of methods based on advanced spectrum analysis. Furthermore, we categorize advanced audio authentication techniques into two types, which exploit audio recording conditions and compressed audio features, respectively. Finally, several future research directions in audio authentication are pointed out. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.74 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.57 In this work we study the possibility of improving face detection performance by combining Face/Eye detector systems having different characteristics. In particular, we make an extensive study of combinations of different face and eye detectors resulting in a final face detection system composed by three-steps: in the first step two high performance face detectors are combined together to extract regions of supposed faces from the image, in the second step a novel eye detector is introduced to improve the accuracy of the previous step and to filtering out false positives, the third is a filtering step. The novel eye detector is based on two different texture descriptors: multi-resolution local ternary patterns and local phase quantization descriptors. Our tests show a noticeable performance improvement by extracting the features locally, i.e. dividing the eye region in four sub-windows for extracting separately the features inside each sub-window, instead of from the whole eye region. The extracted features are coupled with Support Vector Machines trained by eye and non-eye samples to perform classification. The quality of the proposed complete system is validated on three different datasets (a self-collected dataset and the well-know BioID and FERET), obtaining interesting results. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.57 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.54 Cellular automata are a powerful computation model that provides a simple way to simulate and solve many difficult problems in different fields. The most widely known example of Cellular Automata is the Game-of-Life. In this paper we introduce a new method for scrambling digital images, based on the Game-of-Life, where the complex behavior characteristics of this cellular automaton are analyzed based on the Lambda parameter. We study the behavior of two-dimensional cellular automata around the critical value of Lambda by means of digital image scrambling, which commonly requires a diffusion mechanism. Our model is simple and robust, as described in the experimental results section. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.54 http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.69 We present a novel approach for creating and exploring annotations in place using mobile phones. The system can be used in large-scale indoor and outdoor scenarios and offers an accurate mapping of the annotations to physical objects. The system uses a drift-free orientation tracking based on panoramic images, which can be initialized using data from a GPS sensor. Given the current position and view direction, we show how annotations can be accurately mapped to the correct objects, even in the case of varying user positions. Possible applications range from Augmented Reality browsers to pedestrian navigation. http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.69 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.77 The extensive development in e-Health services in very heterogeneous environments demands specific studies of traffic and network requirements in order to guarantee Quality of Service (QoS). This paper proposes an evaluation methodology for guaranteeing the technical viability of e-Health services according to the recommended QoS requirements. The proposed evaluation methodology has been implemented in a configurable tool that, among other features, allows characterizing the real service performance, measuring it in a laboratory test bed, extracting traffic models and network parameters and running service simulations according to different scenarios and use cases. This methodology has been applied to the study of the technical viability of several e-Health services in both fixed and mobile scenarios by means of dimensioning the number of simultaneous users and adaptively selecting the algorithms that would optimize the required QoS levels according to those services. The quantitative results obtained can contribute to obtain optimized designs for adapting e-Health services parameters according to the available network resources and moreover to propose new traffic models and adaptive QoS mechanisms. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.77 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.84 Many have criticized the laboratory-based usability evaluation paradigm as inadequate for the era of the post-desktop computer. Although evaluation in the field is recognized as a necessary development, it is still underused. In this paper, I discuss experiences gained in 10 years of evaluation of mobile applications, arguing that field studies challenge us to design evaluations as quasi-experiments that do not assume perfect control and randomization. While field evaluations are expensive, cost-efficiency can be significantly improved. Several new challenges are discussed. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.84 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.83 Modern digital communications, informatics and electronics blend in our daily life, with accelerating pace. Therefore, it becomes increasingly important for electrical engineering university departments to refresh their teaching curricula and reflect such knowledge diversity. This work puts forth a concrete course curriculum example of interdisciplinary, semester-long teaching and details its outcome: a low-cost, multi-hop wireless sensor network (WSN) that enables the "digital garden" and was built from first principles (no utilization of commercial WSN platforms). Diverse knowledge can be communicated in depth during a course semester, enabling student-driven application, limited only by imagination. In that way, electrical engineering graduates are better prepared for the sensor-rich, pervasive computing era that has arrived. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.83 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.76 A real-time video watermarking scheme against geometric distortions is proposed for DCT-encoded compressed video data. The histogram shape of the low-frequency sub-band coefficients in the Discrete Wavelet Transform (DWT) domain has invariant properties to geometric distortions. Therefore we embed the watermark bits into watermark minimal sequences by modulating the relative relations of each two neighboring histogram bins in the DWT domain. To meet the requirement of real-time performance, a fast inter-transformation is employed to construct DWT coefficients directly from block Discrete Cosine Transform (DCT) coefficients. To resist various video format conversions, the watermark detection is performed in the spatial domain. This does not affect the real-time performance because the frames needn’t be re-encoded into compressed data during the watermark detection process, and compressed video can be easily decoded by employing some codec or decoding chips. The experimental results show that the proposed scheme is transparent and robust to many geometric distortions. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.76 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.75 Inspired by multi-resolution histogram, we propose a multi-scale SIFT descriptor to improve the discriminability. A series of SIFT descriptions with different scale are first acquired by varying the actual size of each spatial bin. Then principle component analysis (PCA) is employed to reduce them to low dimensional vectors, which are further combined into one 128-dimension multi-scale SIFT description. Next, an entropy maximization based binarization is employed to encode the descriptions into binary codes called fingerprints for indexing the local features. Furthermore, an efficient search architecture consisting of lookup tables and inverted image ID list is designed to improve the query speed. Since the fingerprint building is of low-complexity, this method is very efficient and scalable to very large databases. In addition, the multi-scale fingerprints are very discriminative such that the copies can be effectively distinguished from similar objects, which leads to an improved performance in the detection of copies. The experimental evaluation shows that our approach outperforms the state of the art methods. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.75 http://opac.ieeecomputersociety.org/opac?year=2011&volume=18&issue=04&acronym=pervasive IEEE Pervasive Computing http://www.computer.org/portal/site/pervasive/ http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.79 Mobile phones are a pervasive platform for opportunistic sensing of behaviors and opinions. We show that location and communication sensors can be used to model individual symptoms, long- term health outcomes, and diffusion of opinions in a community. For individuals, phone-based features can be used to predict changes in health, such as common colds, influenza, and stress, and automatically identify symptomatic days. For longer-term health outcomes such as obesity, we find that weight changes of participants are correlated with exposure to peers who gained weight in the same period, which is in direct contrast to currently accepted theories of social contagion. Finally, as a proxy for understanding health education we examine change in political opinions during the 2008 US presidential election campaign. We discover dynamic patterns of homophily and use topic models (Latent Dirchlet Allocation) to understand the link between specific behaviors and changes in political opinions. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.79 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.59 The continuing growth of and increasing dependence on forensic image databases require fast and reliable image matching and retrieval techniques. We present a content-based image retrieval (CBIR) system for a particular forensic image database, namely a large collection of tattoo images. The system employs a local point descriptor to represent images, and, given a query tattoo image, it retrieves near-duplicate images from a large-scale database. Despite the high retrieval accuracy of the system, the performance heavily relies on the quality of query images. If query images are of low quality, features extracted from the query are noisy and not sufficiently discriminative, resulting in poor retrieval performance. In this paper, we improve the robustness of the system, especially for low quality query images, which, consequently, improves the overall retrieval performance. We introduce effective weighting schemes for matching local keypoints as well as utilize metadata to further improve the retrieval performance. Experimental results on a database of 100,000 images show that our system has excellent retrieval performance with a top-20 retrieval accuracy of 90.5%. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.59 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.58 In this paper we propose a functional mapping between Java Call Control (JCC) and Session Initiation Protocol (SIP). We show its effectiveness in enabling easy service design and implementation through experimental results. For this purpose, we have implemented a JCC-SIP Resource Adaptor for a Jain Service Logic Execution Environment (JSLEE). In particular, we have used the Mobicents JSLEE, which is the only existing open source JSLEE implementation. Results, obtained by implementing a typical VoIP service, show both feasibility and good performance of our proposal. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.58 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.62 Human behavior modeling at a large-scale and under real-world conditions is still an open problem. Existing classification models do not always perform well on a diverse population. Training personalized models that incorporate different contextual conditions and individual user characteristics are effective in addressing this challenge. However, this approach burdens the users with collecting and manually labeling their own training data which is not scalable. In this article, we propose CoCo (Cooperative Communities), a learning framework that leverages different types of everyday social connections between people to personalize classification models. CoCo exploits social networks to selectively combine small contributions of labeled data from people with shared context or user characteristics. Under CoCo a personalized classifier is trained for each individual user, but by exploiting social networks, the burden of providing training data can be spread over the entire community. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.62 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.56 This paper addresses the question of how to build a case-based computer-aided diagnosis system that assists physicians and other medical personnel in the interpretation of optical biopsies obtained through confocal laser endomicroscopy (CLE). CLE is a novel technique for intravital microscopy during ongoing gastrointestinal endoscopy. However, most gastroenterologists are not trained to interpret mucosal pathology, and histopathologist are usually not available in the endoscopy suite. An optical biopsy is an optic diagnostic method capable to analyze the tissue in surface and in deepness without the need to extract it from the body. The system allows users navigating and searching over an image database containing optical biopsies of the human colon recorded with CLE. Users are able to retrieve information about precedent diagnostics by providing an example CLE image for content based image retrieval (CBIR), by using keywords, or by filtering different fields for structured retrieval. The system's CBIR approach involves a novel algorithm for automatic feature extraction in CLE images, showing promising results on inferring semantic metadata from low-level features. In order to effectively ensure the interoperability with potential third-party applications, the system provides an interface compliant with the recent standards ISO/IEC 15938-12:2008 (MPEG Query Format) and ISO/IEC 24800 (JPEG Search). http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.56 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.61 Designing pervasive computing applications for hostile environments presents a particular challenge because of both the greater stakes in terms of potential benefits and risks and the generally greater space of design options. Thoroughly exploring this design space in realistic usage settings is therefore as difficult as it is important to validate design options early on and understand their implications for future work practice. As a contribution to the ongoing discussion of prototyping techniques for pervasive computing, this article presents the FireSim mixed-reality prototyping approach that we developed for and applied to the exploration of the LifeNet system for tactical firefighter navigation support. Based on this concrete case of pervasive computing for hostile environments we explain the related design challenges and present results from a field study of collaborative search and rescue operations with professional firefighters. Results are related to design options, emerging work practices, and the quality of the presented prototyping approach to facilitate user-driven design space explorations. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.61 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.60 With the rapid spread of GPS enabled smart phones and the fact that users are almost permanently connected to the Internet, we see an evolution towards applications and services that adapt themselves using the user’s context. To facilitate the development of such intelligent applications, new enabling platforms are needed to collect, distribute and exchange context information. We present CASP, a Context Aware Service Platform taking care of the aggregation and abstraction of context information. Three use cases in as many different domains are detailed: a personal content service, a desk sharing office service and a person oriented nurse call system. These services combine different kinds of context information in an easy way using the proposed platform. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.60 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.55 The micro grid technology is playing a central role in the semantic evolution of small and medium size services. These flexible applications allow enforcing new functionalities and intelligence into complex and integrated solutions by supporting automated content processing and back office management, controlling content delivering networks, providing services via active and proactive applications on client devices. To this end, they have to provide high flexibility and scalability and a range of features which in the past were unaffordable for small and medium service portal providers, while being available only on large integrated platforms. A solution can be to enforce flexibility and media computing capabilities into micro grid by using a media grid computing language for formalizing processes to produce, post-produce, license and deliver content while meeting a range of scenarios’ requirements. The usage of a media language improves the level of automation in services and applications. This article presents the main requirements and architectures of micro grids for media and semantic computing, and for media grid languages. Semantic computing primitives may be also enforced into final user tools to provide local semantic search, recommendations: a real personal assistant. The experience reported herein has been gained in several years of work in the sector. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.55 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.53 Recent explosive growth of multimedia content on the Web has led to the popularity and proliferation of search technology. However, faced the vast quantity of information content returned by search engines, users are often bewildered and have to painstakingly find her needs and preferences. Multimedia Question Answering emerges as a renewed focus on returning exact and fine-grained answers by leveraging advanced media content and linguistic analysis as well as domain knowledge. In this article, we clarify the emergence of Question Answering and its evolution: from text to multimedia. We identify the challenges in achieving Multimedia Question Answering from the aspects of user intent, data scope, question processing and answer presentation, i.e., peripheral vision into Multimedia Question Answering. In retrospect of what has been achieved so far, we finally conjecture what the future may hold for Multimedia Question Answering. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.53 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.41 In this study, an efficient copyright protection scheme for e-government document images is proposed. The copyright protection scheme is combined by the discrete cosine transform (DCT) and the singular value decomposition (SVD) using a control parameter to avoid the false positive problem, and then an optimization process of the scaling factor is conducted based on the genetic algorithm (GA). We apply the DCT to the host image, map the coefficients of DCT in a zigzag order into four areas that represent the levels from the lowest to highest frequencies, apply the SVD to each area and then modify the singular values of the host image with the control parameter of watermark image. The modification is optimized with GA using the mean singular value of watermark to improve the resilience of the watermarking scheme from all attacks. The experiment results show the improved performance of the proposed scheme in comparison with the previous schemes. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.41 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.59 Spontaneous Networks (SNs) are multi-hop ad-hoc networks where nodes opportunistically exploit peer-to-peer contacts to share content and resources in an impromptu and transient way. Also pushed by the on-going trends of anytime anywhere connectivity, ubiquitous presence of resource-rich portable devices, and social-aware collaboration, SNs are recently gaining relevant attention for their potential of better exploiting all available (and often underutilized) resources. After positioning state-of-the-art SN concepts and solutions with regard to wireless mesh and opportunistic networks, the paper claims the central need of application-driven middleware for effective SN management, in order to fit differentiated application-specific requirements at runtime. The paper practically evaluates the validity of this claim by presenting the design and implementation of our Real Ad-hoc Multi-hop Peer-to-peer (RAMP) middleware, which is easily deployable over existing and heterogeneous wireless networks. The reported experimental results show that the good performance of the RAMP prototype allows adaptive and per-application management strategies even when supporting challenging application scenarios such as multimedia streaming. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.59 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.42 Conventional access control mechanisms rely on the use of a single security token to authenticate a remote user. However, this introduces a single point of failure in the system, which results in various security and reliability issues. Even more, these systems are often vulnerable to relay attacks. To solve these problems, we propose a threshold-based distance bounding protocol, in which the user’s private key is distributed among a group of personal devices, including resource limited devices such as RFID tags. Our solution significantly improves security and reliability, and offers protection against any subset of t compromised devices, with t+1 being an adjustable threshold number. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.42 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.38 Digital Multimedia Broadcasting Application Format (DMB AF) is Part 9 standard of ISO/IEC 23000 MPEG-A Multimedia Application Formats. The DMB AF standard specifies a structured file format for storage and playback of DMB (i.e., T-DMB, S-DMB, DAB, and DAB+) contents, enabling a variety of different types of multimedia components to be easily packaged, managed, exchanged and played, exploiting widely deployed DMB receivers, in governed and protected ways. This paper provides an overview of the DMB AF standard including the usage scenarios that show its advantages and benefits. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.38 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.40 Nowadays, approximately 1.5 to 2 billion passengers travel with commercial airlines each year [1]. During those flights, 10 to 40 percent of all passengers in industrial countries experience a certain degree of fear of flying [2]. Thus, a significant amount of airplane passengers would benefit from assistive support during a flight. The European SEAT project aims to provide this support by detecting the passengers’ well-being. One aspect of the project is the development of unobtrusive sensor technology and algorithms for an ECG monitoring in the airplane seat. To promote acceptance and usage of the ECG monitoring, we integrated a contactless ECG system in an airplane seat. However, movements of the passenger disturb the ECG signal. To systematically analyze these disturbances, we performed a user study investigating the influence of airplane passengers’ activities on the quality of the ECG signal. The results show that the signal quality of the contactless ECG system decreases during activities such as ”eating” or ”working”. This motivates the presentation of a novel method to automatically appraise the quality of ECG signals. Our method transforms the signal appraisal into a binary classification task and is able to predict the signal quality with an accuracy of 91%. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.40 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.21 This paper surveys the work carried out within two large consortia, AMI and IM2, on improving access to records of human meetings using multimodal interfaces called meeting browsers. Their design has emerged as an important goal, with both theoretical interest and practical applications. Meeting browsers are assistance tools that help humans navigate through multimedia records (audio, video, documents, and metadata) in order to obtain a general idea about what happened in a meeting or to find specific pieces of information, for discovery or verification. To explain the importance that meeting browsers have gained in time, the paper summarizes findings of user studies, discusses features of meeting browser prototypes developed in AMI/IM2, and outlines the main evaluation protocol proposed (BET). Reference scores are provided for future benchmarking. These achievements in meeting browsing are the result of an iterative software process, from user studies to prototypes and then to products. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.21 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.20 Power seat functions (PSFs) are important features for power wheelchair users to adjust their posture independently for preventing pressure ulcers, ameliorating other medical conditions, and to assist with daily activities. Appropriate use of PSFs requires a user to analyze his current environmental settings, body position, and recall his clinician’s recommendations, but these can be complex tasks for novice users and people with diminished cognitive function. To assist users we are developing an electronic coach system, entitled “Virtual Seating Coach” (VSC), to remind users when and how to use PSFs appropriately and warn when an adverse event may occur due to improper use of PSFs. In order to design a coaching program that will display user-friendly feedback, we conducted a survey to understand users’ preference for feedback modalities. PSF users and clinicians were recruited to participate in this survey. They reviewed modalities with various features using a computer demonstration program, then answered a questionnaire, and participated in a face-to-face interview. Trends in preferences for indicator and feedback modalities were identified, but some diversity of opinion also revealed itself. Findings from this survey study will guide the selection of feedback modalities to build the VSC with the capacity to accommodate individual differences. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.20 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.19 While numerous projects focus on the design of monitoring and health management technologies for aging in place, few large studies have focused on privacy. In this paper, we describe preliminary results from the Ethical Technologies in the Homes of Seniors (ETHOS project), a three year project to investigate privacy, design, and technologies for home-based pervasive computing for older adults. Using data from focus groups with over 60 elders, we discuss the development of prototypes, privacy conceptualizations among focus group participants, and implications for design. We conclude by discussing implications for end-user control of pervasive computing data and information flow. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.19 http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.20 Although the bag-of-visual-words (BoW) representation has received wide application, it ignores the spatial information. To tackle this problem, we propose to use ‘components’ as the higher-level visual elements to represent images. Then we formulate object recognition into a bi-linear model along with sparsity constraints to indicate two progressive linear relationships among a given concept and the two-level visual elements of images, yielding a sparsity constrained bi-linear model (SBLM). To further enhance robustness and leverage the non-convexity of SBLM, we learn a combination of SBLM in a boosting-like procedure. We also prove that the optimization over each subset (while keeping the other subset fixed) of weighted SBLM is convex, hence the global optimum for each subset can be found. Accordingly, the optimization procedure can keep on refining the two parameter sets with strictly reduced objective cost during each boosting round. Experimental results demonstrate the effectiveness of the proposed boosting SBLM method. http://doi.ieeecomputersociety.org/10.1109/MMUL.2011.20 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.17 Projectors are pervasive as infrastructure devices for large display, but are now also becoming available in small form factors that afford mobile personal use. This article analyzes “projectors on the move” and their interaction space with a survey of input and output concepts, underlying sensing challenges, and emerging applications. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.17 http://doi.ieeecomputersociety.org/10.1109/MMUL.2010.88 This paper proposes an automated system for recognizing disease conditions of human skin in context to health informatics. The disease conditions are recognized by analyzing skin texture images using a set of normalized symmetrical Grey Level Co-occurrence Matrices (GLCM). Directional GLCMs are computed along four directions viz. horizontal, vertical, right diagonal, left diagonal, and a set of features viz. Contrast, Homogeneity, Mean, Variance and Energy computed from each, are averaged to provide an estimation of the texture class. The results are compared with another technique based on Wavelet decomposition of the images. A Wavelet coefficient, computed from a set of correlation matrices resulting from the approximation and detail components following a multi-level 2-D Haar Wavelet decomposition, is used as a feature for texture discrimination. The system is tested on a set of medical images displaying three dermatological skin conditions viz. Acne, Eczema, and Urticaria. The features are considered in various combinations viz. individually, in joint 2-D and 3-D feature spaces, and in hybrid 2-D and 3-D feature spaces, using L1 and L2 metrics as well as neural network classifiers, to study which combination produces best recognition accuracies. http://doi.ieeecomputersociety.org/10.1109/MMUL.2010.88 http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.91 Many wearable biosensors have failed to be adopted outside of a lab setting or gain popular acceptance. The Heartphones project seeks to address this by integrating physiological sensing capabilities into a platform already accepted for everyday use comprising sensor-embedded earphones and a smart phone. http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.91 http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.70 This paper describes a wireless sensor network that monitored water extraction rate, salinity and water table level. The network collected real-time water quality measurements in order to investigate the impacts of current irrigation practice on the environment, in particular underground water salination. Particular challenges included a large coverage area, a sparse network with mean link distances of 800 metres, and strong diurnal and seasonal effects on communications performance. In response we developed protocols that provided high end-to-end packet delivery rate requirements, and hostile deployment environment. We describe the design, implementation, performance and lessons learned for 18 months of remote operation. The results show that the technology has promise for ensuring large-scale sustainable irrigation. http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.70 http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.68 We present an unobtrusive technique for supporting and improving object recognition approaches on mobile phones. To accomplish this we determine the present and future locations of museum visitors by evaluating user-generated spatio-temporal pathway data. In the context of our adaptive mobile museum guidance system called PhoneGuide we show that this improves the classification performance significantly and can achieve recognition rates comparable to those of traditional location-based image classification approaches. http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.68 http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.67 Two dimensional (2D) barcode is gaining popularity as a pervasive technology for mobile applications. When used together with camera phones, the 2D-barcode can provide a link between the digital and the real world. Currently, there exists a number of different 2D-barcodes that can be used in a variety of mobile applications. However, this development is still in its infancy. Some of the popular 2D-barcodes currently used for mobile applications were not originally designed for camera phones. This is more pronounced for color 2D-barcodes, where many technical challenges still exist. This paper proposes a new color 2D-barcode that is specifically designed for mobile applications. It identifies some key factors that can improve the robustness of the color 2D-barcode on mobile devices, which in turn would enhance the user’s experience of this pervasive mobile technology. http://doi.ieeecomputersociety.org/10.1109/MPRV.2010.67