Search

As a high-impact educational practice, service-learning has demonstrated success in positively influencing students’ overall development, and much work has been done on investigating student learning outcomes from service-learning. A particular direction is to model students’ learning outcomes in the context of their learning experience, i.e., the various student, course, and pedagogical elements. It contributes to a better understanding of the learning process, a more accurate prediction of students’ attainments on the learning outcomes, and improvements in the design of learning activities to maximize student learning. However, most of the existing work in this area relies on statistical analysis that makes assumptions about attribute independence or simple linear dependence, which may not accurately reflect real-life scenarios. In contrast, the study described in this paper adopted a neural network-based approach to investigate the impact of students’ learning experience on different service-learning outcomes. A neural network with attention mechanisms was constructed to predict students’ service-learning outcomes by modeling the contextual information from their various learning experiences. In-depth evaluation experiments on a large-scale dataset collected from more than 10,000 students showed that this proposed model achieved better accuracy on predicting service-learning outcomes. More importantly, it could capture the interdependence between different aspects of student learning experience and the learning outcomes. We believe that this framework can be extended to student modeling for other types of learning activities.

Fire fighter fatalities and injuries in the U.S. remain too high and fire fighting too hazardous. Until now, fire fighters rely only on their experience to avoid life-threatening fire events, such as flashover. In this paper, we describe the development of a flashover prediction model which can be used to warn fire fighters before flashover occurs. Specifically, we consider the use of a fire simulation program to generate a set of synthetic data and an attention-based bidirectional long short-term memory to learn the complex relationships between temperature signals and flashover conditions. We first validate the fire simulation program with temperature measurements obtained from full-scale fire experiments. Then, we generate a set of synthetic temperature data which account for the realis-tic fire and vent opening conditions in a multi-compartment structure. Results show that our proposed method achieves promising performance for prediction of flashover even when temperature data is completely lost in the room of fire origin. It is believed that the flashover prediction model can facilitate the transformation of fire fighting tactics from traditional experience-based decision marking to data-driven decision marking and reduce fire fighter deaths and injuries.

Internal thought refers to the process of directing attention away from a primary visual task to internal cognitive processing. It is pervasive and closely related to primary task performance. As such, automatic detection of internal thought has significant potential for user modeling in human-computer interaction and multimedia applications. Despite the close link between the eyes and the human mind, only few studies have investigated vergence behavior during internal thought and none has studied moment-to-moment detection of internal thought from gaze. While prior studies relied on long-term data analysis and required a large number of gaze characteristics, we describe a novel method that is user-independent, computationally light-weight and only requires eye vergence information readily available from binocular eye trackers. We further propose a novel paradigm to obtain ground truth internal thought annotations by exploiting human blur perception. We evaluated our method during natural viewing of lecture videos and achieved a 12.1% improvement over the state of the art. These results demonstrate the effectiveness and robustness of vergence-based detection of internal thought and, as such, open new research directions for attention-aware interfaces.

This paper 1 presents a study to examine the potential use of machine learning models to build a real-time detection algorithm for prevention of kitchen cooktop fires. Sixteen sets of time-dependent sensor signals were obtained from 60 normal/ignition cooking experiments. A total of 200,000 data instances are documented and analyzed. The raw data are preprocessed. Selected features are generated for time series data focusing on real-time detection applications. Utilizing the leave-one-out cross validation method, three machine learning models are built and tested. Parametric studies are carried out to understand the diversity, volume, and tendency of the data. Given the current dataset, the detection algorithm based on Support Vector Machine (SVM) provides the most reliable prediction (with an overall accuracy of 96.9%) on pre-ignition conditions. Analyses indicate that using a multi-step approach can further improve overall prediction accuracy. The development of an accurate detection algorithm can provide reliable feedback to intercept ignition of unattended cooking and help reduce fire losses.

In this paper, we propose an efficient and scalable query processing framework for continuous spatial queries (range and k-nearest-neighbor queries) in mobile peer-to-peer (P2P) environments, where no fixed communication infrastructure or centralized/distributed servers are available. Due to the limitations in mobile P2P environments, for example, user mobility, limited battery power, limited communication range, and scarce communication bandwidth, it is costly to maintain the exact answer of continuous spatial queries. To this end, our framework enables the user to find an approximate answer with quality guarantees. In particular, we design two key features to adapt continuous spatial query processing to mobile P2P environments. 1) Each mobile user can specify his or her desired quality of services (QoS) for a query answer in a personalized QoS profile. The QoS profile consists of two parameters, namely, coverage and accuracy. The coverage parameter indicates the desired level of completeness of the available information for computing an approximate answer, and the accuracy parameter indicates the desired level of accuracy of the approximate answer. 2) We design a continuous answer maintenance scheme to enable the user to collaborate with other peers to continuously maintain a query answer. With these two features in our framework, the user can obtain a query answer from a local cache if the answer satisfies his or her QoS requirements. Otherwise, the user enlists neighbors for help to share their cached information to refine the answer. If the refined answer still cannot satisfy the QoS requirements, the user broadcasts the query to the peers residing within the required search area of the query to find the most accurate answer. Experiment results show that our framework is efficient and scalable and provides an effective trade-off between the communication overhead and the quality of query answers.

This paper presents ''Round-Eye'', a system for tracking nearest surrounding objects (or nearest surrounders) in moving object environments. This system provides a platform for surveillance applications. The core part of this system is continuous nearest surrounder (NS) query that maintains views of the nearest objects at distinct angles from query points. This query differs from conventional spatial queries such as range queries and nearest neighbor queries as NS query considers both distance and angular aspects of objects with respect to a query point at the same time. In our system framework, a centralized server is dedicated (1) to collect location updates of both objects and queries, (2) to determine which NS queries are invalidated in presence of object/query location changes and corresponding result changes if any, and (3) to refresh the affected query answers. To enhance the system performance in terms of processing time and network bandwidth consumption, we propose various techniques, namely, safe region, partial query reevaluation, and incremental query result update. Through simulations, we evaluate our system with the proposed techniques over a wide range of settings.

In this paper, collaborative writing is modeled as a workflow application comprising a number of activities. Each activity is assigned to a co-author to edit certain part(s) of the shared document. The order of editing is governed by a workflow schedule, which can be modified during execution. To enable concurrent editing, a data definition scheme is proposed whereby documents are transformed into the XML format for internal storage. Effectively, a hierarchical structure is superimposed on each document, allowing it to be broken down into a number of independent parts. These parts may then be separately edited in parallel. Unlike other approaches, the system supports the use of off-the-shelf editor software. Users can thus adapt to the system easily and existing documents can also be re-used rapidly. A prototype has been built which supports collaborative editing of Microsoft WordTM documents.

XML (extensible Markup Language) has been developed and deployed by domain-specific standardization bodies and commercial companies. Studies have been conducted on a wide variety of issues encompassing XML. In the use of XML for wireless computing, the focus has been on investigating ways to efficiently represent XML data for transmission over a wireless environment. We propose a middleware, Xstream (XML Streaming), for efficiently streaming XML contents over a wireless environment by leveraging the rich semantics and structural characteristics of XML documents and by flexibly managing units containing fragments of data into autonomous units, known as XDU (Xstream Data Unit) fragments. The concept of an XDU is fundamental to the operation of Xstream. It provides for the efficient transfer of documents across a wireless link and allows other issues and challenges pertaining to wireless transmission to be addressed. By fragmenting and organizing an XML document into XDU fragments, we are able to incrementally send fragments across a wireless link, while the receiver is able to perform look-ahead processing of the document without having to wait for the entire document to be downloaded. We propose a fragmenting strategy based on the value of the wireless link's Maximum Transfer Units (MTUs). In addition, we present and evaluate several packetizing strategies, i.e., strategies wherein a collection of XDUs are grouped into a packet to optimize packet delivery and processing. At the receiving end of this process, a reassembly strategy incrementally reconstructs the XML document as XDU fragments are being received, thereby facilitating client application implementation of look-ahead processing.

A mobile environment is characterized by low communication bandwidth and poor network connectivity. Accessing web documents in a mobile environment is thus both inefficient and ineffective. To combat for the low bandwidth problem, we employ the multi-resolution transmission and browsing mechanism for web documents, in which a web document is partitioned into multiple units, to enable a mobile client to explore the more content-bearing portion earlier. To combat for the poor network connectivity problem, we utilize a mobile agent model in the distributed agent environment (DAE). A mobile agent has the capability of migrating to a base station that is currently serving a mobile client, establishing a virtual connection to the client. The agent, acting on behalf of the client, travels along the wired network to carry out its tasks and collect results, returning to the client at the end of its itinerary. We have implemented the DAE architecture, which supports mobile agent in a mobile environment, and demonstrated its usefulness in supporting our multi-resolution mechanism. We have also conducted experimental study, comparing performance between conventional mobile client/server model and different mobile agent models in accessing a database server through both wireless and wired networks.

Database broadcast is an effective and scalable approach to disseminate information of high affinity to a large collection of mobile clients. A common problem of existing broadcast approaches is the lack of knowledge for a client to determine if all data items satisfying its query could be obtained from the broadcast. We therefore propose a semantic-based broadcast approach. A semantic descriptor is attached to each broadcast unit, called a data chunk. This semantic descriptor allows a client to determine if a query can be answered entirely based on broadcast items and, if needed, identify the precise definition of the remaining items in the form of a "supplementary" query. Data chunks can be of static or dynamic sizes and organized hierarchically. Their boundary can be determined on-the-fly, adaptive to the nature of client queries. We investigate different ways of organizing the data chunks over a broadcast channel to improve access performance. We introduce the data affinity index metric, which more accurately reflects client-perceived performance. A simulation model is built to evaluate our semantic-based broadcast schemes.

Workflow is an important class of applications in the daily business. A number of web-based workflow systems have been de veloped recently as a natural extension to traditional workflow systems to exploit the growing popularity of the Internet. However, most of them are designed based on the specific application at hand. In this paper, we distill out the fundamental elements of a workflow system into a general workflow framework. The framework provides appropriate application programming interfaces for programmers to fill in the application specific requirements of a workflow system at hand. This is realized through two object-wrappers: the Task interface and the Resource interface, which support the specification of the tasks involved in the workflow schedule and the resources accessed re spectively. A major characteristic of the framework is that the particular workflow schedule under execution is fluid, in the sense that the tasks involved as well as their precedence relationships can be modified dynamically. Consistency constraints will be examined in this paper which determine when such modifications are allowed. To maximize flexibility, we adhere our design to the CORBA architecture, which has been becoming highly popular in recent years, thus allowing tasks and resources of different types to interoperate in our framework. We demonstrate the feasibility of our framework with a small prototype that allows tasks in a workflow system to be sched uled and executed.

In a mobile computing environment, database servers disseminate information to multiple mobile clients via wireless channels. Due to the low bandwidth and low reliability of wireless channels, it is important for a mobile client to cache its frequently accessed database items into its local storage. This improves performance of database queries and improves availability of database items for query processing during disconnection. In this paper, we investigate issues on caching granularity, coherence strategy, and replacement policy of caching mechanisms for a mobile environment utilizing point-to-point communication paradigm. We first illustrate that page-based caching is not suitable in the mobile context due to the lack of locality among database items. We propose three different levels of caching granularity: attribute caching, object caching, and hybrid caching, a hybrid approach of attribute and object caching. Next, we show that existing coherence strategies are inappropriate due to frequent disconnection in a mobile environment, and propose a cache coherence strategy, based on the update patterns of database items. Via a detail simulation model, we examine the performance of various levels of caching granularity with our cache coherence strategy. We observe, in general, that hybrid caching could achieve a better performance. Finally, we propose several cache replacement policies that can adapt to the access patterns of database items. For each given caching granularity, we discover that our replacement policies outperform conventional ones in most situations.

Advanced Traveler Information Systems (ATIS) require efficient information retrieval and updating in a dynamic environment at different geographical scales. ATIS applications are useful in yielding a better utilization of the limited costly transportation arteries and providing value-added traveler information. Many ATIS applications are built on the functionalities provided by Geographical Information Systems (GIS), which often cannot meet extra requirements like real-time response. We investigate GIS-based systems in ATIS and propose a system architecture based on GIS and distributed database technology. Issues on data modeling, data representation, storage and retrieval, data aggregation, and parallel processing of queries are discussed. This paper introduces a distributed system architecture for ATIS based on recent technology. It presents new data models for information representation and proposes data shipping for efficient query processing and function shipping for reducing communication overhead. The paper also examines the use of a network of computers for solving complex problems more timely and privacy protection for sensitive data.

An inherent limitation in mobile data access is due to the unreliable and low bandwidth wireless communication channel. Caching of useful database items from database server in local storage of mobile clients is effective in reducing data access latency and wireless bandwidth consumption. In the event of disconnection, cached data can also serve the purpose of partial query processing. In this paper, we present the implementation and evaluate a new caching mechanism for object-oriented database systems in a mobile environment called MODEC. MODEC possesses the capabilities of performing caching at multiple granularities and adapting to changes in data access pattern, providing improved performance through tolerating limited inconsistency to read-only transactions. This caching capabilities is supported via standard ODMG modeling constructs. The prototype of MODEC is implemented using ODE database. Empirical system performance results are obtained from experiments on the prototype with data from a real-life database. The results are validated against results obtained via detailed simulation studies on MODEC. Both sets of results are found to be consistent and are in favor of our MODEC mechanism in providing a feasible solution to the mobile data access problem under the constraints in a mobile environment.

In mobile environments, mobile clients can access information with respect to their locations by submitting Location-Dependent Spatial Queries (LDSQs) to Location- Based Service (LBS) servers. Owing to scarce wireless channel bandwidth and limited client battery life, frequent LDSQ submission from clients must be avoided. Observing that LDSQs issued from a client located at nearby positions would likely return the same query results, we explore the idea of valid scope , which represents a spatial area in which a set of LDSQs will retrieve exactly the same set of query results. With a valid scope derived and an LDSQ result cached, a client can assert whether the new LDSQs can be answered with the maintained LDSQ result, thus eliminating the need of sending LDSQs to the server. Contention on the wireless channel and client energy consumed for data transmission can be considerably reduced. In this paper, we design efficient algorithms to compute the valid scope for common types of LDSQs, including nearest neighbor queries, range queries and window queries. Through an extensive set of experiments, our proposed valid scope computation algorithms are shown to outperform existing approaches.

Directions search returns the shortest path from a source to a destination on a road network. However, the search interests of users may be exposed to the service providers, thus raising privacy concerns. For instance, a path query that finds a path from a resident address to a clinic may lead to a deduction about "who is related to what disease". To protect user privacy from accessing directions search services, we introduce the OPAQUE system, which consists of two major components: (1) an obfuscator that formulates obfuscated path queries by mixing true and fake sources/destinations; and (2) an obfuscated path query processor installed in the server for obfuscated path query processing. OPAQUE reduces the likelihood of path queries being revealed and allows retrieval of requested paths. We propose two types of obfuscated path queries, namely, independently obfuscated path query and shared obfuscated path query to strike a balance between privacy protection strength and query processing overhead, and to enhance privacy protection against collusion attacks.

In mobile and wireless environments, mobile clients can access information with respect to their locations by submitting Location-Dependent Spatial Queries (LDSQs) to Location-Based Service (LBS) servers. Owing to scarce wireless channel bandwidth and limited client battery life, frequent LDSQ submission from clients must be avoided. Observing that LDSQs issued from similar client positions would normally return the same results, we explore the idea of valid scope, that represents a spatial area in which a set of LDSQs will retrieve exactly the same query results. With a valid scope derived and an LDSQ result cached at the client side, a client can assert whether the new LDSQs can be answered with the maintained LDSQ result, thus eliminating the LDSQs sent to the server. As such, contention on wireless channel and client energy consumed for data transmission can be considerably reduced. In this paper, we design efficient algorithms to compute the valid scope for common types of LDSQs, including nearest neighbor queries and range queries. Through an extensive set of experiments, our proposed valid scope computation algorithms are shown to significantly outperform existing approaches.

This paper presents a system framework to support continuous nearest surrounder (NS) queries in moving object environments. NS query finds the nearest objects at individual distinct angles from a query point. This query distinguishes itself from other conventional spatial queries such as range queries and nearest neighbor queries by considering both distance and angular aspects of objects with respect to a query point. One of NS query applications is to monitor the nearest objects around an observation point. In our framework, a centralized server is dedicated to collect object location updates, to determine affected NS queries of each object location update, to compute the incremental result change of affected queries and to deliver result updates to corresponding interested users/applications that initiate the queries. In particular, we propose algorithms namely, safe region formation and partial query evaluation, that can significantly improve the system performance. Through simulations, we validate our proposed algorithms over a wide range of settings

In this paper, we present a new type of spatial queries called Nearest Surrounder (NS) queries. An NS query determines the nearest polygon-shaped spatial objects (referred to as nearest surrounder objects) and their orientations with respect to a query point from an object set. Besides, we derive two NS query variants, namely, multitier NS (m-NS) queries and angle-constrained NS (ANS) queries. An m-NS query searches multiple layers of NS objects for the same range of angles from a query point. An ANS query searches for NS objects within a specified range of angles. To evaluate NS queries and their variants, we explore angle-based and distance-based bound properties of polygons, and devise two efficient algorithms, namely, Sweep and Ripple, based on R-tree. The algorithms access objects in an order according to their orientations and distances with respect to a given query point, respectively. They are efficient as they can finish a search with one index lookup. Besides, they can progressively deliver a query result. Through empirical studies, we evaluate the proposed algorithms and report their performance for both synthetic and real object sets.

Mobile environments are characterized by low communication bandwidth and frequent disconnection. Conventional information retrieval and visualization mechanisms thus pose a serious challenge to mobile clients. There is a need for these clients to quickly perceive an overall picture of the information available to them, so as to enable them to discontinue the transmission of information units that are unlikely useful to them. We had proposed amulti-resolution transmission mechanismfor web documents. In particular, various organizational units of a document are transmitted to a mobile client in an order according to their information content, thereby allowing the client to terminate the transmission of a useless document at an earlier moment. In this paper, we generalize themulti-resolution transmission modelfor a document, and then extend that model into the multi-resolution transmission framework to cater for not only units within a document, but also for a collection of documents. We refer to the multi-resolution transmission mechanism for a particular document asintra-document multi-resolution transmissionmechanism and the extension to a document cluster asinter-document multi-resolution transmissionmechanism. With the integrated multi-resolution transmission framework, a mobile client can examine the important portions of the document cluster for an early grasp of the information therein, with the most important contents for each of those documents more readily available as well.

We consider an environment in which a collection of mobile clients interacts with a stationary database server. Due to the low bandwidth of wireless communication channels, it is necessary to broadcast highly popular data items and deliver other data items on a demand basis to the mobile clients. This broadcast wireless media can be considered as an extra layer of cache storage, which we term air-storage. We investigate several mechanisms in selecting the data items to be placed over this new layer of air-storage, and illustrate their effectiveness by means of simulation.

Advanced Traveler Information Systems (ATIS) under the Intelligent Vehicle Highway Systems (IVHS) context require efficient information retrieval and updating in a dynamic environment and at different geographical scales. Some problems in ATIS can be solved based on the functionalities provided by GIS systems. However, extra requirements such as real-time response are not readily met in existing GIS systems. We investigate the use of GIS-based systems for applications in ATIS and we propose a new system architecture based on existing GIS technology and distributed computing technology. Issues on data modeling, data representation, storage and retrieval, data aggregation, and parallel processing of online queries in the proposed GIS-based systems are discussed. >

Advances in VLSI technology have rendered the implementation of complex operation sequences or transactions inside the body of hardware memory chips a concrete possibility. We show that such an implementation will provide an attractive performance gain and demonstrate the effectiveness through simulation.

Statistical operators such as the exponentially weighted moving average operator are useful in adapting to changes in data access patterns in a mobile database application. The authors investigate the effectiveness of such operators in selecting suitable data items to be broadcast over scarce wireless channels through simulation.

A distributed virtual walkthrough environment allows users connected to the geometry server to walk through a specific place of interest, without having to travel physically. This place of interest may be a virtual museum, virtual library or virtual university. There are two basic approaches to distribute the virtual environment from the geometry server to the clients, complete replication and on-demand transmission. Although the on-demand transmission approach saves waiting time and optimizes network usage, many technical issues need to be addressed in order for the system to be interactive. CyberWalk is a web-based distributed virtual walkthrough system developed based on the on-demand transmission approach. It achieves the necessary performance with a multiresolution caching mechanism. First, it reduces the model transmission and rendering times by employing a progressive multiresolution modeling technique. Second, it reduces the Internet response time by providing a caching and prefetching mechanism. Third, it allows a client to continue to operate, at least partially, when the Internet is disconnected. The caching mechanism of CyberWalk tries to maintain at least a minimum resolution of the object models in order to provide at least a coarse view of the objects to the viewer. All these features allow CyberWalk to provide sufficient interactivity to the user for virtual walkthrough over the Internet environment. In this paper, we demonstrate the design and implementation of CyberWalk. We investigate the effectiveness of the multiresolution caching mechanism of CyberWalk in supporting virtual walkthrough applications in the Internet environment through numerous experiments, both on the simulation system and on the prototype system.

Minimizing the communication overhead is always a hot topic in wireless sensor networks. In a multirate query system, data sources disseminate the data streams to users at the frequency they request. However, sending data in different frequencies to individual users is very costly. We address this problem by broadcasting a single consolidated data stream, aiming at reducing the amount of transmitted data. Taking into account the data correlation, we can reconstruct the data streams at lower frequencies from the consolidated stream at a higher frequency. In this paper, we propose an energy-efficient framework to process multirate queries and investigate the path-sharing routing tree construction method together with the rate conversion mechanism. We evaluate both the accuracy and energy efficiency by simulation. Simulation results indicate that with a reasonable level of tolerance, the performance gain is significant. As far as we know, this is the first energy-efficient solution for multirate query in wireless sensor networks.