Towards universal and statistical-driven heuristics for automatic classification of sports video events

Researchers worldwide have been actively seeking for the most robust and powerful solutions to detect and classify key events (or highlights) in various sports domains. Most approaches have employed manual heuristics that model the typical pattern of audio-visual features within particular sport events To avoid manual observation and knowledge, machine-learning can be used as an alternative approach. To bridge the gaps between these two alternatives, an attempt is made to integrate statistics into heuristic models during highlight detection in our investigation. The models can be designed with a modest amount of domain-knowledge, making them less subjective and more robust for different sports. We have also successfully used a universal scope of detection and a standard set of features that can be applied for different sports that include soccer, basketball and Australian football. An experiment on a large dataset of sport videos, with a total of around 15 hours, has demonstrated the effectiveness and robustness of our
aIlgorithms.

Using decision-tree to automatically construct learned-heuristics for events classification in sports video

Automatic events classification is an essential requirement for constructing an effective sports video summary. It has become a well-known theory that the high-level semantics in sport video can be “computationally interpreted” based on the occurrences of specific audio and visual features which can be extracted automatically. State-of-the-art solutions for features-based event classification have only relied on either manual-knowledge based heuristics or machine learning. To bridge the gaps, we have successfully combined the two approaches by using learning-based heuristics. The heuristics are constructed automatically using decision tree while manual supervision is only required to check the features and highlight contained in each training segment. Thus, fully automated construction of classification system for sports video events has been achieved. A comprehensive experiment on 10 hours video dataset, with five full-match soccer and five full-match basketball videos, has demonstrated the effectiveness/robustness of our algorithms.

Agent-based heuristics to solve NP-hard scheduling problems

A novel agent-driven heuristic approach was developed to control the operational scheduling for a local manufacturer. This approach outperformed the traditional kanban control mechanism under numerous simulated benchmarking tests. Using this approach, the individual machine loading was reduced by, on average, 28%, with the loading spread reduced by 85%

The use of heuristics in valuation practice : implications in a changing market

Despite the existence of prescribed frameworks, valuation remains a cause of much controversy and variety of opinion. It does not matter whether procedures are undertaken in exactly the same way, the conclusion of ‘value’ will vary from valuer to valuer – sometimes considerably. This uncertainty within valuation is founded on property’s heterogeneous nature and the imperfect market that is the property market; in addition to the unpredictability of human behaviour in making judgements (French and Gabrielli 2004). Uncertainty, in valuation is found in the amalgam of locational, physical and legal characteristics and innumerable other forces which control and energise the property market (Whipple 1995). Particular irregular occurrences, or drastic changes in property markets, from either within market evolution or external forces, for example the creation of global financial markets, cause further uncertainty for valuers and provides challenges in identifying ‘market value’ in valuation practice. The praxis of valuation in a commercial sense navigates this complexity using a combination of algorithms and heuristics to identify the value of a property. The application of theoretical mathematical algorithms based on economic theory (Brown 1995), is augmented by valuers’ ability to apply appropriate adjustment based on their knowledge of the market, their ability to analyse, assess and compare the attributes of a property in comparison to its market, and their practical experience (Sliogeriene 2008). Despite the necessity of algorithms, the application of appropriate adjustments and assumptions are important in arriving at a value. This paper is a critical reflection on the basis of valuation practice as guided by standards, methods, and ethics (algorithms), and the use of heuristics in practice. This is important because changes within property markets challenge the inter-relationship between these two aspects of valuation practice. Through the authors’ industry experience and a review of previous research and statements of practice norms this paper provides an analysis of the ability of valuers to address market change in their valuation practices.

Modelling interplay in normative social systems: towards a heuristics formalism of agents and networks

The need for guiding model formulation of normative social systems in support of a digital ecosystem is introduced. Normative social systems improve the understanding of computational social processes in simulation and experimentation, and provide support for digital ecosystem developments. However, a successful simulation requires the appropriate implementation of a conceptual model. It is proposed that an heuristic formalism of agents, networks and environments, complements the conventional creative approach to model formulation by guiding the formulation of conceptual models via abstract components and facilitate interface with other components in a digital environment.

Heuristics-based Indoor positioning systems: a systematic literature review

Context: Many heuristics-based indoor positioning approaches havebeen developed to enhance positioning estimation. However, thereis no comprehensive survey of these heuristics information and methods. 

Implementation of novel methods of global and nonsmooth optimization : GANSO programming library

We discuss the implementation of a number of modern methods of global and nonsmooth continuous optimization, based on the ideas of Rubinov, in a programming library GANSO. GANSO implements the derivative-free bundle method, the extended cutting angle method, dynamical system-based optimization and their various combinations and heuristics. We outline the main ideas behind each method, and report on the interfacing with Matlab and Maple packages.

Simulating autonomous robot teams with Microsoft robotics studio

This paper presents an application of Microsoft Robotics Studio (MSRS) in which a team of six four wheel drive, ground based robots explore and map simulated terrain. The user has the ability to modify the terrain and assign destination objectives to the team while the simulation is running. The terrain is initially generated using a gray scale image, in which the intensity of each pixel in the image gives an altitude datum. The robots start with no knowledge of their surroundings, and map the terrain as they attempt to reach user-defined target objectives. The mapping process simulates the use of common sensory hardware to determine datum points, including provision for field of view, detection range, and measurement accuracy. If traversal of a mapped area is indicated by the users’ targeting commands, path planning heuristics developed for MSRS by the author in earlier work are used to determine an efficient series of waypoints to reach the objective. Mutability of terrain is also explored- the user is able to modify the terrain without stopping the simulation. This forces the robots to adapt to changing environmental conditions, and permits analysis of the robustness of mapping algorithms used when faced with a changing world.

Fuzzy logic in clinical practice decision support systems

Computerized clinical guidelines can provide significant benefits to health outcomes and costs, however, their effective implementation presents significant problems. Vagueness and ambiguity inherent in natural (textual) clinical guidelines is not readily amenable to formulating automated alerts or advice. Fuzzy logic allows us to formalize the treatment of vagueness in a decision support architecture. This paper discusses sources of fuzziness in clinical practice guidelines. We consider how fuzzy logic can be applied and give a set of heuristics for the clinical guideline knowledge engineer for addressing uncertainty in practice guidelines. We describe the specific applicability of fuzzy logic to the decision support behavior of Care Plan On-Line, an intranet-based chronic care planning system for General Practitioners.

Towards insightful algorithm selection for optimisation using meta-learning concepts

In this paper we propose a meta-learning inspired framework for analysing the performance of meta-heuristics for optimization problems, and developing insights into the relationships between search space characteristics of the problem instances and algorithm performance. Preliminary results based on several meta-heuristics for well-known instances of the Quadratic Assignment Problem are presented to illustrate the approach using both supervised and unsupervised learning methods.

Clinical judgements : research and practice

This paper explores issues that are relevant to the judgements routinely made by clinical psychologists. It first considers the relative merits of clinical and statistical approaches to decision making and notes that although much of the empirical evidence demonstrates the greater accuracy of statistical approaches to making judgements (where appropriate methods exist), they are rarely routinely used. Instead, clinical approaches to making judgements continue to dominate in the majority of clinical settings. Second, common sources of errors in clinical judgement are reviewed, including the misuse of heuristics, clinician biases, the limitations of human information-processing capacities, and the overreliance on clinical interviews. Finally, some of the basic strategies that can be useful to clinicians in improving the accuracy of clinical judgement are described. These include advanced level training programs, using quality instruments and procedures, being wary of overreliance on theories, adhering to the scientist-practitioner approach, and being selective in the distribution of professional efforts and time.