Jingyu Zhou

TASA: Tag-Free Activity Sensing Using RFID Tag Arrays

Radio Frequency IDentification (RFID) has attracted considerable attention in recent years for its low cost, general availability, and location sensing functionality. Most existing schemes require the tracked persons to be labeled with RFID tags. This requirement may not be satisfied for some activity sensing applications due to privacy and security concerns and uncertainty of objects to be monitored, e.g., group behavior monitoring in warehouses with privacy limitations, and abnormal customers in banks. In this paper, we propose TASA-Tag-free Activity Sensing using RFID tag Arrays for location sensing and frequent route detection. TASA relaxes the monitored objects from attaching RFID tags, online recovers and checks frequent trajectories by capturing the Received Signal Strength Indicator (RSSI) series for passive RFID tag arrays where objects traverse. In order to improve the accuracy for estimated trajectories and accelerate location sensing, TASA introduces reference tags with known positions. With the readings from reference tags, TASA can locate objects more accurately. Extensive experiment shows that TASA is an effective approach for certain activity sensing applications.

A class-feature-centroid classifier for text categorization

Automated text categorization is an important technique for many web applications, such as document indexing, document filtering, and cataloging web resources. Many different approaches have been proposed for the automated text categorization problem. Among them, centroid-based approaches have the advantages of short training time and testing time due to its computational efficiency. As a result, centroid-based classifiers have been widely used in many web applications. However, the accuracy of centroid-based classifiers is inferior to SVM, mainly because centroids found during construction are far from perfect locations. We design a fast Class-Feature-Centroid (CFC) classifier for multi-class, single-label text categorization. In CFC, a centroid is built from two important class distributions: inter-class term index and inner-class term index. CFC proposes a novel combination of these indices and employs a denormalized cosine measure to calculate the similarity score between a text vector and a centroid. Experiments on the Reuters-21578 corpus and 20-newsgroup email collection show that CFC consistently outperforms the state-of-the-art SVM classifiers on both micro-F1 and macro-F1 scores. Particularly, CFC is more effective and robust than SVM when data is sparse.

A Self-Organizing Storage Cluster for Parallel Data-Intensive Applications

Cluster-based storage systems are popular for data-intensive applications and it is desirable yet challenging to provide incremental expansion and high availability while achieving scalability and strong consistency. This paper presents the design and implementation of a self-organizing storage cluster called Sorrento, which targets data-intensive workload with highly parallel requests and low write-sharing patterns. Sorrento automatically adapts to storage node joins and departures, and the system can be configured and maintained incrementally without interrupting its normal operation. Data location information is distributed across storage nodes using consistent hashing and the location protocol differentiates small and large data objects for access efficiency. It adopts versioning to achieve single-file serializability and replication consistency. In this paper, we present experimental results to demonstrate features and performance of Sorrento using microbenchmarks, application benchmarks, and application trace replay.

Context reasoning using extended evidence theory in pervasive computing environments

Most existing context reasoning approaches implicitly assume that contexts are precise and complete. This assumption cannot be held in pervasive computing environments, where contexts are often imprecise and incomplete due to unreliable connectivity, user mobility and resource constraints. To this end, we propose an approach called CRET: Context Reasoning using extended Evidence Theory. CRET applies the evidence theory to context reasoning in pervasive computing environments. Because evidence theory is limited by two fundamental problems-computation-intensiveness and Zadeh paradox, CRET presents evidence selection and conflict resolution strategies. Empirical study shows that CRET is desirable for pervasive applications.

CAB: Cache Aware Bi-tier Task-Stealing in Multi-socket Multi-core Architecture

Modern multi-core computers often adopt a multi-socket multi-core architecture with shared caches in each socket. However, traditional task-stealing schedulers tend to pollute the shared cache and incur more cache misses due to their random stealing. To relieve this problem, this paper proposes a Cache Aware Bi-tier (CAB) task-stealing scheduler, which improves the performance of memory-bound applications by reducing memory footprint and cache misses of tasks running inside the same CPU socket. CAB uses an automatic partitioning method to divide an execution Directed Acyclic Graph (DAG) into the inter-socket tier and the intra-socket tier. Tasks generated in the inter-socket tier are scheduled across sockets, while tasks generated in the intra-socket tier are scheduled within the same socket. Experimental results show that CAB can improve the performance of memory-bound applications up to 68.7% compared with the traditional task-stealing.

Selective early request termination for busy internet services

Internet traffic is bursty and network servers are often overloaded with surprising events or abnormal client request patterns. This paper studies a load shedding mechanism called selective early request termination (SERT) for network services that use threads to handle multiple incoming requests continuously and concurrently. Our investigation with applications from Ask.com shows that during overloaded situations, a relatively small percentage of long requests that require excessive computing resource can dramatically affect other short requests and reduce the overall system throughput. By actively detecting and aborting overdue long requests, services can perform significantly better to achieve QoS objectives compared to a purely admission based approach. We have proposed a termination scheme that monitors running time of requests, accounts for their resource usage, adaptively adjusts the selection threshold, and performs a safe termination for a class of requests. This paper presents the design and implementation of this scheme and describes experimental results to validate the proposed approach.

An Efficient Collaborative Filtering Approach Using Smoothing and Fusing

Collaborative Filtering (CF) has achieved widespread success in recommender systems such as Amazon and Yahoo! music. However, CF usually suffers from two fundamental problems - data sparsity and limited scalability. Among the two broad classes of CF approaches, namely, memory-based and model-based, the former usually falls short of the system scalability demands, because these approaches predict user preferences over the entire item-user matrix. The latter often achieves unsatisfactory accuracy, because they cannot capture precisely the diversity in user rating styles. In this paper, we propose an efficient Collaborative Filtering approach using Smoothing and Fusing (CFSF) strategies. CFSF formulates the CF problem as a local prediction problem by mapping it from the entire large-scale item-user matrix to a locally reduced item-user matrix. Given an active item and a user, CFSF dynamically constructs a local item-user matrix as the basis of prediction. To alleviate data sparsity, CFSF presents a fusion strategy for the local item-user matrix that fuses ratings of the same user makes on similar items, and ratings of like-minded users make on the same and similar items. To eliminate diversity in user rating styles, CFSF uses a smoothing strategy that clusters users over the entire item-user matrix and then smoothes ratings within each user cluster. Empirical study shows that CFSF outperforms the state-of-the-art CF approaches in terms of both accuracy and scalability.

Extended Dempster-Shafer Theory in Context Reasoning for Ubiquitous Computing Environments

Context, the pieces of information that capture the characteristics of ubiquitous computing environment, is often imprecise and incomplete due to user mobility, unreliable wireless connectivity and resource constraints. While many context reasoning schemes have been proposed to assist ubiquitous applications, these schemes often suffer from the assumption that the contexts are complete and precise. The main challenge for context reasoning is how to interpret and infer contexts from existing contexts that are imprecise and incomplete. To this end, we propose the DSCR× approach — extended Dempster-Shafer theory for Context Reasoning, which applies Dempster-Shafer theory to ubiquitous computing environments by following a new context-aware architecture. DSCR× solves the fundamental problem in Dempster-Shafer theory – intensive computation through evidence selection strategy. This strategy takes advantage of the k−l algorithm to select evidence with the highest beliefs, which considerably reduces the computation overhead. The proposed approach is evaluated through extensive experiments. The results show that DSCR× is appropriate to reason contexts from incomplete and imprecise contexts in ubiquitous computing environments.

Dependency isolation for thread-based multi-tier Internet services

Multi-tier Internet service clusters often contain complex calling dependencies among service components spreading across cluster nodes. Without proper handling, partial failure or overload at one component can cause cascading performance degradation in the entire system. While dependency management may not present significant challenges for even-driven services (particularly in the context of staged event-driven architecture), there is a lack of system support for thread-based online services to achieve dependency isolation automatically. To this end, we propose dependency capsule, a new mechanism that supports automatic recognition of dependency states and per-dependency management for thread-based services. Our design employs a number of dependency capsules at each service node: one for each remote service component. Dependency capsules monitor and manage threads that block on supporting services and isolate their performance impact on the capsule host and the rest of the system. In addition to the failure and overload isolation, each capsule can also maintain dependency-specific feedback information to adjust control strategies for better availability and performance. In our implementation, dependency capsules are transparent to application-level services and clustering middleware, which is achieved by intercepting dependency-induced system calls. Additionally, we employ two-level thread management so that only light-weight user-level threads block in dependency capsules. Using four applications on two different clustering middleware platforms, we demonstrate the effectiveness of dependency capsules in improving service availability and throughput during component failures and overload.

Detecting attacks that exploit application-logic errors through application-level auditing

Host security is achieved by securing both the operating system kernel and the privileged applications that run on top of it. Application-level bugs are more frequent than kernel-level bugs, and, therefore, applications are often the means to compromise the security of a system. Detecting these attacks can be difficult, especially in the case of attacks that exploit application-logic errors. These attacks seldom exhibit characterizing patterns as in the case of buffer overflows and format string attacks. In addition, the data used by intrusion detection systems is either too low-level, as in the case of system calls, or incomplete, as in the case of syslog entries. This paper presents a technique to enforce nonbypassable, application-level auditing that does not require the recompilation of legacy systems. The technique is implemented as a kernel-level component, a privileged daemon, and an offline language tool. The technique uses binary rewriting to instrument applications so that meaningful and complete audit information can be extracted. This information is then matched against application-specific signatures to detect attacks that exploit application-logic errors. The technique has been successfully applied to detect attacks against widely-deployed applications, including the Apache Web server and the OpenSSH server.