An evaluation of different features and learning models for anomalous event detection

The huge amount of CCTV footage available makes it very burdensome to process these videos manually through human operators. This has made automated processing of video footage through computer vision technologies necessary. During the past several years, there has been a large effort to detect abnormal activities through computer vision techniques. Typically, the problem is formulated as a novelty detection task where the system is trained on normal data and is required to detect events which do not fit the learned ‘normal’ model. There is no precise and exact definition for an abnormal activity; it is dependent on the context of the scene. Hence there is a requirement for different feature sets to detect different kinds of abnormal activities. In this work we evaluate the performance of different state of the art features to detect the presence of the abnormal objects in the scene. These include optical flow vectors to detect motion related anomalies, textures of optical flow and image textures to detect the presence of abnormal objects. These extracted features in different combinations are modeled using different state of the art models such as Gaussian mixture model(GMM) and Semi- 2D Hidden Markov model(HMM) to analyse the performances. Further we apply perspective normalization to the extracted features to compensate for perspective distortion due to the distance between the camera and objects of consideration. The proposed approach is evaluated using the publicly available UCSD datasets and we demonstrate improved performance compared to other state of the art methods.

A methodology for effective implementation of lean strategies and its performance evaluation in manufacturing organizations

Purpose – The purpose of this paper is to develop an effective methodology for implementing lean manufacturing strategies and a leanness evaluation metric using continuous performance measurement (CPM). Design/methodology/approach – Based on five lean principles, a systematic lean implementation methodology for manufacturing organizations has been proposed. A simplified leanness evaluation metric consisting of both efficiency and effectiveness attributes of manufacturing performance has been developed for continuous evaluation of lean implementation. A case study to validate the proposed methodology has been conducted and proposed CPM metric has been used to assess the manufacturing leanness. Findings – Proposed methodology is able to systematically identify manufacturing wastes, select appropriate lean tools, identify relevant performance indicators, achieve significant performance improvement and establish lean culture in the organization. Continuous performance measurement matrices in terms of efficiency and effectiveness are proved to be appropriate methods for continuous evaluation of lean performance. Research limitations/implications – Effectiveness of the method developed has been demonstrated by applying it in a real life assembly process. However, more tests/applications will be necessary to generalize the findings. Practical implications – Results show that applying the methods developed, managers can successfully identify and remove manufacturing wastes from their production processes. By improving process efficiency, they can optimize their resource allocations. Manufacturers now have a validated step by step methodology for successfully implementing lean strategies. Originality/value – According to the authors’ best knowledge, this is the first known study that proposed a systematic lean implementation methodology based on lean principles and continuous improvement techniques. Evaluation of performance improvement by lean strategies is a critical issue. This study develops a simplified leanness evaluation metric considering both efficiency and effectiveness attributes and integrates it with the lean implementation methodology.

Anticipated user experience in the early stages of product development

This research investigates users' anticipation of their future experiences with interactive products to support design for experience in the early stages of product development. This research generates new knowledge of anticipated user experience (AUX), which reveals users' tendency to perceive the pragmatic quality of products as the main determinant of their positive future experiences. The AUX Framework has been an important outcome of this study. The exploration of the components of this framework allows a better prediction and understanding of users' underlying needs and potential usage contexts valuable for the early design phases.

Metrics for Understanding Communication on Twitter

As the systematic investigation of Twitter as a communications platform continues, the question of developing reliable comparative metrics for the evaluation of public, communicative phenomena on Twitter becomes paramount. What is necessary here is the establishment of an accepted standard for the quantitative description of user activities on Twitter. This needs to be flexible enough in order to be applied to a wide range of communicative situations, such as the evaluation of individual users’ and groups of users’ Twitter communication strategies, the examination of communicative patterns within hashtags and other identifiable ad hoc publics on Twitter (Bruns & Burgess, 2011), and even the analysis of very large datasets of everyday interactions on the platform. By providing a framework for quantitative analysis on Twitter communication, researchers in different areas (e.g., communication studies, sociology, information systems) are enabled to adapt methodological approaches and to conduct analyses on their own. Besides general findings about communication structure on Twitter, large amounts of data might be used to better understand issues or events retrospectively, detect issues or events in an early stage, or even to predict certain real-world developments (e.g., election results; cf. Tumasjan, Sprenger, Sandner, & Welpe, 2010, for an early attempt to do so).

A survey of user modelling in social media websites

With the widespread of social media websites in the internet, and the huge number of users participating and generating infinite number of contents in these websites, the need for personalisation increases dramatically to become a necessity. One of the major issues in personalisation is building users’ profiles, which depend on many elements; such as the used data, the application domain they aim to serve, the representation method and the construction methodology. Recently, this area of research has been a focus for many researchers, and hence, the proposed methods are increasing very quickly. This survey aims to discuss the available user modelling techniques for social media websites, and to highlight the weakness and strength of these methods and to provide a vision for future work in user modelling in social media websites.

Optimal camera planning under versatile user constraints in multi-camera image processing systems

The selection of optimal camera configurations (camera locations, orientations, etc.) for multi-camera networks remains an unsolved problem. Previous approaches largely focus on proposing various objective functions to achieve different tasks. Most of them, however, do not generalize well to large scale networks. To tackle this, we propose a statistical framework of the problem as well as propose a trans-dimensional simulated annealing algorithm to effectively deal with it. We compare our approach with a state-of-the-art method based on binary integer programming (BIP) and show that our approach offers similar performance on small scale problems. However, we also demonstrate the capability of our approach in dealing with large scale problems and show that our approach produces better results than two alternative heuristics designed to deal with the scalability issue of BIP. Last, we show the versatility of our approach using a number of specific scenarios.

Evaluation framework for green procurement in road construction

Purpose Most barriers and enablers of sustainable projects are related to procurement. This study proposes a framework for evaluating green procurement practices throughout the lifecycle of road construction projects and demonstrates its application through an Australian case study. Design/methodology/approach The study is based on linking the phases of road construction with incentive mechanisms for proactively motivating behavioural change. A holistic view on utilised and potential incentives is attempted with a literature review and a state-of-practice review. The latter is based on interviews and 90 policy and procurement documents across five Australian states. Findings An evaluation framework with seven procurement stages is suggested to describe current state green procurement incentives throughout the delivery lifecycle of road construction projects. The Australian case study was found to provide useful data to identify gaps and strong points of the different states regarding their level of integration of sustainability and greenhouse gas emissions GHG) reduction elements in their procurement practices. This understanding was used to draw recommendations on future advancement of green procurement. Originality/value: Government entities across the globe can impact considerably the achievement of sustainability and GHG targets, by using their procurement practices and requirements to create incentives for contractors and suppliers to engage in more GHG conscious practices. The present study provides a systematic account of how green procurement practices can be underpinned using the Australian road construction industry as a case study, and distinguish between strong and weak links in the green procurement chain to draw recommendations for future initiatives.

Teacher Evidence Matrix : an evaluation using multiple lines of evidence

Welcome to the Teacher evidence matrix. This matrix is designed for highly qualified discipline experts to evaluate their teaching in a systematic manner. The primary purpose of the Teacher evidence matrix is to provide a tool that an academic staff member at university can annually review their teaching. The annual review will result in you being ready for performance, planning and review; promotion; awards; or employment application. This tool is designed for individual use and will lead to an action plan for implementation.

Facilitating local stories in post-disaster regional communities : evaluation in narrative-driven oral history projects

Cyclone Yasi struck the Cassowary Coast of Northern Queensland, Australia, in the early hours of February 3, 2011, destroying many homes and property, including the destruction of the Cardwell and district historical society’s premises. With their own homes flattened, many residents were forced to live in mobile accommodation, with extended family, or leave the area altogether. The historical society members seemed, however, particularly devastated by their flattened foreshore museum and loss of their precious collection of material. A call for assistance was made through the Oral History Association of Australia’s Queensland branch (OHAA Qld), which along with a Queensland University of Technology (QUT) research team sponsored a trip to best plan how they could start to pick up the pieces to rebuild the museum. This chapter highlights the need for communities to gather, preserve and present their own stories, in a way that is sustainable and meaningful to them – whether that be because of a disaster, or as they go about life in their contemporary communities – the key being that good advice, professional support and embedded evaluation practices at crucial moments along the way can be critically important.

Visually impaired drivers who use bioptic telescopes : self-assessed driving skills and agreement with on-road driving evaluation

Purpose. To compare self-assessed driving habits and skills of licensed drivers with central visual loss who use bioptic telescopes to those of age-matched normally sighted drivers, and to examine the association between bioptic drivers' impressions of the quality of their driving and ratings by a “backseat” evaluator. Methods. Participants were licensed bioptic drivers (n = 23) and age-matched normally sighted drivers (n = 23). A questionnaire was administered addressing driving difficulty, space, quality, exposure, and, for bioptic drivers, whether the telescope was helpful in on-road situations. Visual acuity and contrast sensitivity were assessed. Information on ocular diagnosis, telescope characteristics, and bioptic driving experience was collected from the medical record or in interview. On-road driving performance in regular traffic conditions was rated independently by two evaluators. Results. Like normally sighted drivers, bioptic drivers reported no or little difficulty in many driving situations (e.g., left turns, rush hour), but reported more difficulty under poor visibility conditions and in unfamiliar areas (P < 0.05). Driving exposure was reduced in bioptic drivers (driving 250 miles per week on average vs. 410 miles per week for normally sighted drivers, P = 0.02), but driving space was similar to that of normally sighted drivers (P = 0.29). All but one bioptic driver used the telescope in at least one driving task, and 56% used the telescope in three or more tasks. Bioptic drivers' judgments about the quality of their driving were very similar to backseat evaluators' ratings. Conclusions. Bioptic drivers show insight into the overall quality of their driving and areas in which they experience driving difficulty. They report using the bioptic telescope while driving, contrary to previous claims that it is primarily used to pass the vision screening test at licensure.

Building indicators in media assistance; four ways evaluation reports present “change”

The international aid and development community has supported programs that aim to build the capacity of media professionals or contribute to an enabling environment throughout the past 20 years. However, two decades on from the first modern media assistance programs, the sector is still struggling to identify, measure and understand the changes effected by their programs. There are questions raised as to whether it is even feasible to identify impacts on society and governance. This paper draws on some preliminary findings from a comparative thematic analysis of 47 evaluation documents of media assistance programs. The aim of this analysis is to identify trends in impact evaluation practice in the media assistance field, as well as the strengths and weaknesses of different evaluation approaches. This paper presents four types of social change claims commonly presented in reports; hypothetical changes, introduction of new opportunities, concrete examples of immediate impacts, and analysis of ongoing social and political changes. Although these types may appear as a spectrum from weak to strong, the interactions are perhaps more accurately understood using metaphors such as building blocks. This paper explores these types in more detail and suggests that a robust set of impacts-types could be useful in developing more grounded theories of change and indicators.

Integrating time forgetting mechanisms into topic-based user interest profiling

The rapid development of the World Wide Web has created massive information leading to the information overload problem. Under this circumstance, personalization techniques have been brought out to help users in finding content which meet their personalized interests or needs out of massively increasing information. User profiling techniques have performed the core role in this research. Traditionally, most user profiling techniques create user representations in a static way. However, changes of user interests may occur with time in real world applications. In this research we develop algorithms for mining user interests by integrating time decay mechanisms into topic-based user interest profiling. Time forgetting functions will be integrated into the calculation of topic interest measurements on in-depth level. The experimental study shows that, considering temporal effects of user interests by integrating time forgetting mechanisms shows better performance of recommendation.

Acquiring user information needs for recommender systems

Most recommender systems attempt to use collaborative filtering, content-based filtering or hybrid approach to recommend items to new users. Collaborative filtering recommends items to new users based on their similar neighbours, and content-based filtering approach tries to recommend items that are similar to new users' profiles. The fundamental issues include how to profile new users, and how to deal with the over-specialization in content-based recommender systems. Indeed, the terms used to describe items can be formed as a concept hierarchy. Therefore, we aim to describe user profiles or information needs by using concepts vectors. This paper presents a new method to acquire user information needs, which allows new users to describe their preferences on a concept hierarchy rather than rating items. It also develops a new ranking function to recommend items to new users based on their information needs. The proposed approach is evaluated on Amazon book datasets. The experimental results demonstrate that the proposed approach can largely improve the effectiveness of recommender systems.

Social event detection at MediaEval 2013 : challenges, datasets and evaluation

In this paper, we provide an overview of the Social Event Detection (SED) task that is part of the MediaEval Bench mark for Multimedia Evaluation 2013. This task requires participants to discover social events and organize the re- lated media items in event-specific clusters within a collection of Web multimedia. Social events are events that are planned by people, attended by people and for which the social multimedia are also captured by people. We describe the challenges, datasets, and the evaluation methodology.

Evaluation of two-view geometry methods with automatic ground-truth generation

A large number of methods have been published that aim to evaluate various components of multi-view geometry systems. Most of these have focused on the feature extraction, description and matching stages (the visual front end), since geometry computation can be evaluated through simulation. Many data sets are constrained to small scale scenes or planar scenes that are not challenging to new algorithms, or require special equipment. This paper presents a method for automatically generating geometry ground truth and challenging test cases from high spatio-temporal resolution video. The objective of the system is to enable data collection at any physical scale, in any location and in various parts of the electromagnetic spectrum. The data generation process consists of collecting high resolution video, computing accurate sparse 3D reconstruction, video frame culling and down sampling, and test case selection. The evaluation process consists of applying a test 2-view geometry method to every test case and comparing the results to the ground truth. This system facilitates the evaluation of the whole geometry computation process or any part thereof against data compatible with a realistic application. A collection of example data sets and evaluations is included to demonstrate the range of applications of the proposed system.