Abbreviation: (GTSH) Gator Tech smart houseKeywords: activity recognition, assessment consoles, connected health, health monitoring, sensor data analysis, smart homes

Scene change detection (SCD) is one of several fundamental problems in the design of a video database management system (VDBMS). It is the first step towards the automatic segmentation, annotation, and indexing of video data. SCD is also used in other aspects of VDBMS, e.g., hierarchical representation and efficient browsing of the video data. In this paper, we provide a taxonomy that classifies existing SCD algorithms into three categories: full-videoimage-based, compressed-video-based, and model-based algorithms. The capabilities and limitations of the SCD algorithms are discussed in detail. The paper also proposes a set of criteria for measuring and comparing the performance of various SCD algorithms. We conclude by discussing some important research directions.

Workflow and process automation : concepts and technology I by AndrzejCichocki ... [et al.]. p. cm. --(Kluwer international series in engineering and computer science ; SECS 432) Includes bibliographical references and index. ISBN 978-1-4613-7599-9 ISBN 978-1-4615-5677-0 (eBook)This chapter is focused on the first phase of the workflow application life cycle (Figure 2.1) that is responsible for process modeling and investigation of its properties.The purpose of modeling is to produce an abstraction of a process (mode~ that serves as a basis for the workflow specification. The model of a process enables us to understand what activities, dependencies among activities, and roles (human or information system skills) are necessary to the process.Process modeling methodologies can be mainly divided into the following three categories: communication-based, artifact-based and activity-based. Communication-based ModelingThe communication-based methodologies are based on Winograd/Flores "Conversation for Action Model" [92]. This methodology type represents an action in a workflow based on communication between a customer and a performer. This communication consists of four phases that are defined as follows (Figure 2.2):1. Request -a customer requests an action to be performed CHAPTER 2 Analysis Administration Development Execution Figure 2.1 Life cycle of a workflow application [41] Request ~ \ B9 Offstlon Customer ~ow ~ Pertonner Acceptance Performance Figure 2.2 Conversation for action model 2. Negotiation -customer and performer agree on the action to be performed 3. Performance -the action is performed 4. Acceptance -the customer reports satisfaction with the action Process Technology Customer r::~ Equipment Proc't Office Proc't Office Verify ~ Accounts ~J~ Get~ Vendors k J ~~ V~dM Figure 2.3 Communication-based workflow of procure equipment process 7

In this paper, we introduce Ant-Miner MA to tackle mixedattribute classification problems. Most classification problems involve continuous, ordinal and categorical attributes. The majority of Ant Colony Optimization (ACO) classification algorithms have the limitation of being able to handle categorical attributes only, with few exceptions that use a discretisation procedure when handling continuous attributes either in a preprocessing stage or during the rule creation. Using a solution archive as a pheromone model, inspired by the ACO for mixed-variable optimization (ACO MV ), we eliminate the need for a discretisation procedure and attributes can be treated directly as continuous, ordinal, or categorical. We compared the proposed Ant-Miner MA against cAnt-Miner, an ACO-based classification algorithm that uses a discretisation procedure in the rule construction process. Our results show that Ant-Miner MA achieved significant improvements on computational time due to the elimination of the discretisation procedure without affecting the predictive performance.