Radio Frequency Identification Data Streams Research Articles

A Temporal and Spatial Data Redundancy Processing Algorithm for RFID Surveillance Data

The Radio Frequency Identification (RFID) data acquisition rate used for monitoring is so high that the RFID data stream contains a large amount of redundant data, which increases the system overhead. To balance the accuracy and real-time performance of monitoring, it is necessary to filter out redundant RFID data. We propose an algorithm called Time-Distance Bloom Filter (TDBF) that takes into account the read time and read distance of RFID tags, which greatly reduces data redundancy. In addition, we have proposed a measurement of the filter performance evaluation indicators. In experiments, we found that the performance score of the TDBF algorithm was 5.2, while the Time Bloom Filter (TBF) score was only 0.03, which indicates that the TDBF algorithm can achieve a lower false negative rate, lower false positive rate, and higher data compression rate. Furthermore, in a dynamic scenario, the TDBF algorithm can filter out valid data according to the actual scenario requirements.

Optimization RFID-enabled Retail Store Management with Complex Event Processing

Radio frequency identification (RFID) enabled retail store management needs workflow optimization to facilitate real-time decision making. In this paper, complex event processing (CEP) based RFID-enabled retail store management is studied, particularly focusing on automated shelf replenishment decisions. We define different types of event queries to describe retailer store workflow action over the RFID data streams on multiple tagging levels (e.g., item level and container level). Non-deterministic finite automata (NFA) based evaluation models are used to detect event patterns. To manage pattern match results in the process of event detection, optimization algorithm is applied in the event model to share event detection results. A simulated RFID-enabled retail store is used to verify the effectiveness of the method, experiment results show that the algorithm is effective and could optimize retail store management workflow.

Real-time fluid intake gesture recognition based on batteryless UHF RFID technology

Automatic fluid intake monitoring can be used to ensure adequate hydration in older people. In this study, a real-time fluid intake monitoring system based on the batteryless Ultra High Frequency Radio Frequency Identification (RFID) technology is proposed. The system is simple, unobtrusive, low cost and maintenance-free. Despite the noisy RFID data stream, we demonstrate the efficacy of using a batteryless RFID enabled fluid container to recognize individual instances of drinking (i.e. drinking episodes), in the presence of non-drinking gestures. We conducted experiments with 10 young and 5 older volunteers and achieved F-scores of 87% and 79% for recognizing drinking episodes, respectively.

Fractal-Based Outlier Detection Algorithm over RFID Data Streams

Nowadays, Radio frequency identification (RFID) has been extensively deployed to retailing, supply chain management, object recognition, object monitoring and tracking and many other fields. Detecting outliers in RFID data streams can help us find abnormal activities and thus avoid disasters. In order to detect outliers in RFID data streams efficiently and effectively, we proposed a fractal based outlier detection algorithm. Firstly, we built a monotone searching space based on the self-similarity of fractal. Then, we proposed two piecewise fractal models for RFID data streams, and presented an outlier detection algorithm based on the piecewise fractal model. Finally, we validated the efficiency and effectiveness of the proposed algorithm by massive experiments.

A method of cleaning RFID data streams based on Naive Bayes classifier

Recently, the radio frequency identification (RFID) technology has been widely used in many kinds of applications. However, RFID data streams contain false negative reads and false positive reads leading to the location uncertainty of RFID tags. In view of these problems, we propose a method of cleaning RFID data streams based on Naive Bayes classifier, which could detect effectively tags of false negative reads and false positive reads in RFID data streams. Firstly, we construct a model of a RFID data stream. Then we divide the method into three phases, i.e., preparation phase, training classifier phase and application phase. At last, the result of experiments illustrates our method based on Naive Bayes classifier could acquire the lower percentage of false negative reads and the higher percentage of false positive reads than SMURF algorithm with the increase of the size of sliding window.

Filtering Redundant Data from RFID Data Streams

Radio Frequency Identification (RFID) enabled systems are evolving in many applications that need to know the physical location of objects such as supply chain management. Naturally, RFID systems create large volumes of duplicate data. As the duplicate data wastes communication, processing, and storage resources as well as delaying decision-making, filtering duplicate data from RFID data stream is an important and challenging problem. Existing Bloom Filter-based approaches for filtering duplicate RFID data streams are complex and slow as they use multiple hash functions. In this paper, we propose an approach for filtering duplicate data from RFID data streams. The proposed approach is based on modified Bloom Filter and uses only a single hash function. We performed extensive empirical study of the proposed approach and compared it against the Bloom Filter, d-Left Time Bloom Filter, and the Count Bloom Filter approaches. The results show that the proposed approach outperforms the baseline approaches in terms of false positive rate, execution time, and true positive rate.

Modeling Object Flows from Distributed and Federated RFID Data Streams for Efficient Tracking and Tracing

In the emerging environment of the Internet of things (IoT), through the connection of billions of radio frequency identification (RFID) tags and sensors to the Internet, applications will generate an unprecedented number of transactions and amount of data that require novel approaches in RFID data stream processing and management. Unfortunately, it is difficult to maintain a distributed model without a shared directory or structured index. In this paper, we propose a fully distributed model for federated RFID data streams. This model combines two techniques, namely, tilted time frame and histogram to represent the patterns of object flows. Our model is efficient in space and can be stored in main memory. The model is built on top of an unstructured P2P overlay. To reduce the overhead of distributed data acquisition, we further propose several algorithms that use a statistically minimum number of network calls to maintain the model. The scalability and efficiency of the proposed model are demonstrated through an extensive set of experiments.

A Bayesian Inference-Based Framework for RFID Data Cleansing

The past few years have witnessed the emergence of an increasing number of applications for tracking and tracing based on radio frequency identification (RFID) technologies. However, raw RFID readings are usually of low quality and may contain numerous anomalies. An ideal solution for RFID data cleansing should address the following issues. First, in many applications, duplicate readings of the same object are very common. The solution should take advantage of the resulting data redundancy for data cleaning. Second, prior knowledge about the environment may help improve data quality, and a desired solution must be able to take into account such knowledge. Third, the solution should take advantage of physical constraints in target applications to elevate the accuracy of data cleansing. There are several existing RFID data cleansing techniques. However, none of them support all the aforementioned features. In this paper, we propose a Bayesian inference-based framework for cleaning RFID raw data. We first design an n-state detection model and formally prove that the three-state model can maximize the system performance. Then, we extend the n-state model to support two-dimensional RFID reader arrays and compute the likelihood efficiently. In addition, we devise a Metropolis-Hastings sampler with constraints, which incorporates constraint management to clean RFID data with high efficiency and accuracy. Moreover, to support real-time object monitoring, we present the streaming Bayesian inference method to cope with realtime RFID data streams. Finally, we evaluate the performance of our solutions through extensive experiments.

An Approach for Removing Redundant Data from RFID Data Streams

Radio frequency identification (RFID) systems are emerging as the primary object identification mechanism, especially in supply chain management. However, RFID naturally generates a large amount of duplicate readings. Removing these duplicates from the RFID data stream is paramount as it does not contribute new information to the system and wastes system resources. Existing approaches to deal with this problem cannot fulfill the real time demands to process the massive RFID data stream. We propose a data filtering approach that efficiently detects and removes duplicate readings from RFID data streams. Experimental results show that the proposed approach offers a significant improvement as compared to the existing approaches.

Simulation of a Flexible Manufacturing System with AutoMod Software

A flexible manufacturing system (FMS) is a highly automated, complex system. Simulation is a well-proven method to design or analyze an FMS. Deployment of a radio frequency identification (RFID) system in FMS produces large volumes of RFID data streams, which provide valuable information to improve the operation of FMS. Different frameworks are presented in this paper regarding the use of RFID data streams in an FMS simulation. Simulations are performed with AutoMod software. Related technical details are also presented. The paper’s structure is complied as the following steps: step 1, the introduction of AMHS, FMS and AutoMod; step 2, FMS simulation using AutoMod software; step 3, simulation frameworks driven by RFID data streams; step 4, conclusion.

A new method for data filtering in RFID middleware

With rapidly increasing development of RFID (radio frequency identification) applications, the RFID middleware has become a very hot topic. RFID middleware is a new breed of application software which facilitates data communication between automatic identification equipments (such as RFID readers) and enterprise applications. RFID data, however, contain false readings and duplicates. Such data cannot be used directly by applications unless they are filtered and cleaned. To compensate for the inherent unreliability of RFID data streams, most RFID middleware systems employ a ‘smoothing filter’. In this paper, a new smoothing filter approach is proposed which is based on the concept of processing the status of tag’s readings. The proposed method uses some rules for solving false positives and false negatives to provide accurate RFID data for applications. The simulation results on prototype data show the effectiveness of the proposed method.

A Complex Event Processing Method Based on Pre-grouping for Radio Frequency Identification Data Streams

Radio Frequency Identification (RFID) technology applied ubiquitously uses radio frequency waves to automatically track tagged objects and collect data. After reading tagged objects, the RFID reader generates primitive events that contain very limited semantic information. A complex event is defined to communicate with high level applications. How to efficiently generate a complex event from a large amount of primitive events is an important issue. In this paper, we propose a complex event processing method based on pre-grouping readers. Our approach effectively filters out the unrelated events to reduce the number of redundant checking events. The experimental results show that our method provides a high performance solution for the complex event processing in RFID designs.

RFID data stream processing technology based on CEP

Radio Frequency Identification(RFID) data stream processing technology especially Complex Event Processing(CEP)-based approach is a hot spot in the RFID applications.This paper analyzed the characteristics of RFID data and the disadvantages of the previous CEP-based methods.Moreover a complex event processing method ERD was presented,which combined the detected event and intermediate result sharing mechanism organically and improved the detection efficiency of the overall system.Simulation results validate the effectiveness of the proposed method.